Hard disk drives(HDDs)serve as the primary storage devices in modern data centers.Once a failure occurs,it often leads to severe data loss,significantly degrading the reliability of storage systems.Numerous studies ha...Hard disk drives(HDDs)serve as the primary storage devices in modern data centers.Once a failure occurs,it often leads to severe data loss,significantly degrading the reliability of storage systems.Numerous studies have proposed machine learning-based HDD failure prediction models.However,the Self-Monitoring,Analysis,and Reporting Technology(SMART)attributes differ across HDD manufacturers.We define hard drives of the same brand and model as homogeneous HDD groups,and those from different brands or models as heterogeneous HDD groups.In practical engineering scenarios,a data center is often composed of a heterogeneous population of HDDs,spanning multiple vendors and models.Existing research predominantly focuses on homogeneous datasets,ignoring the model’s generalization capability across heterogeneous HDDs.As a result,HDD models with limited samples often suffer from poor training effectiveness and prediction performance.To address this issue,we investigate generalizable SMART predictors across heterogeneous HDD groups.By extracting time-series features within a fixed sliding time window,we propose a Heterogeneous Disk Failure Prediction Method based on Time Series Features(HDFPM)framework.This method is adaptable to HDD models with limited sample sizes,thereby enhancing its applicability and robustness across diverse drive populations.Experimental results show that the proposed model achieves an F1-score of 0.9518 when applied to two different Seagate HDD models,while maintaining the False Positive Rate(FPR)below 1%.After incorporating the Complexity-Ratio Dynamic Time Warping(CDTW)based feature enhancement method,the best prediction model achieves a True Positive Rate(TPR)of up to 0.93 between the two models.For next-day failure prediction across various Seagate models,the model achieves an F1-score of up to 0.8792.Moreover,the experimental results also show that within the same brand,the higher the proportion of shared SMART attributes across different models,the better the prediction performance.In addition,HDFPMdemonstrates the best stability andmost significant performance in heterogeneous environments.展开更多
This article introduces a novel approach for tricone bit wear condition monitoring and failure prediction for surface mining applications.A successful bit health monitoring system is essential to achieve fully autonom...This article introduces a novel approach for tricone bit wear condition monitoring and failure prediction for surface mining applications.A successful bit health monitoring system is essential to achieve fully autonomous blasthole drilling.In this research in-situ vibration signals were analyzed in timefrequency domain and signals trend during tricone bit life span were investigated and introduced to support the development of artificial intelligence(AI)models.In addition to the signal statistical features,wavelet packet energy distribution proved to be a powerful indicator for bit wear assessment.Backpropagation artificial neural network(ANN)models were designed,trained and evaluated for bit state classification.Finally,an ANN architecture and feature vector were introduced to classify the bit condition and predict the bit failure.展开更多
The occurrence of perioperative heart failure will affect the quality of medical services and threaten the safety of patients.Existing methods depend on the judgment of doctors,the results are affected by many factors...The occurrence of perioperative heart failure will affect the quality of medical services and threaten the safety of patients.Existing methods depend on the judgment of doctors,the results are affected by many factors such as doctors’knowledge and experience.The accuracy is difficult to guarantee and has a serious lag.In this paper,a mixture prediction model is proposed for perioperative adverse events of heart failure,which combined with the advantages of the Deep Pyramid Convolutional Neural Networks(DPCNN)and Extreme Gradient Boosting(XGBOOST).The DPCNN was used to automatically extract features from patient’s diagnostic texts,and the text features were integrated with the preoperative examination and intraoperative monitoring values of patients,then the XGBOOST algorithm was used to construct the prediction model of heart failure.An experimental comparison was conducted on the model based on the data of patients with heart failure in southwest hospital from 2014 to 2018.The results showed that the DPCNN-XGBOOST model improved the predictive sensitivity of the model by 3%and 31%compared with the text-based DPCNN Model and the numeric-based XGBOOST Model.展开更多
The development of cloud computing and virtualization technology has brought great challenges to the reliability of data center services.Data centers typically contain a large number of compute and storage nodes which...The development of cloud computing and virtualization technology has brought great challenges to the reliability of data center services.Data centers typically contain a large number of compute and storage nodes which may fail and affect the quality of service.Failure prediction is an important means of ensuring service availability.Predicting node failure in cloud-based data centers is challenging because the failure symptoms reflected have complex characteristics,and the distribution imbalance between the failure sample and the normal sample is widespread,resulting in inaccurate failure prediction.Targeting these challenges,this paper proposes a novel failure prediction method FP-STE(Failure Prediction based on Spatio-temporal Feature Extraction).Firstly,an improved recurrent neural network HW-GRU(Improved GRU based on HighWay network)and a convolutional neural network CNN are used to extract the temporal features and spatial features of multivariate data respectively to increase the discrimination of different types of failure symptoms which improves the accuracy of prediction.Then the intermediate results of the two models are added as features into SCSXGBoost to predict the possibility and the precise type of node failure in the future.SCS-XGBoost is an ensemble learning model that is improved by the integrated strategy of oversampling and cost-sensitive learning.Experimental results based on real data sets confirm the effectiveness and superiority of FP-STE.展开更多
Lithium ion battery has typical character of distributed parameter system, and can be described precisely by partial differential equations and multi-physics theory because lithium ion battery is a complicated electro...Lithium ion battery has typical character of distributed parameter system, and can be described precisely by partial differential equations and multi-physics theory because lithium ion battery is a complicated electrochemical energy storage system. A novel failure prediction modeling method of lithium ion battery based on distributed parameter estimation and single particle model is proposed in this work. Lithium ion concentration in the anode of lithium ion battery is an unmeasurable distributed variable. Failure prediction system can estimate lithium ion concentration online, track the failure residual which is the difference between the estimated value and the ideal value. The precaution signal will be triggered when the failure residual is beyond the predefined failure precaution threshold, and the failure countdown prediction module will be activated. The remaining time of the severe failure threshold can be estimated by the failure countdown prediction module according to the changing rate of the failure residual. A simulation example verifies that lithium ion concentration in the anode of lithium ion battery can be estimated exactly and effectively by the failure prediction model. The precaution signal can be triggered reliably, and the remaining time of the severe failure can be forecasted accurately by the failure countdown prediction module.展开更多
In the rolling stock sector, the ability to protect passengers, freight and services relies on heavy inborn maintenance. Initiating an accurate model suitable to foresee the change of attitude on components when opera...In the rolling stock sector, the ability to protect passengers, freight and services relies on heavy inborn maintenance. Initiating an accurate model suitable to foresee the change of attitude on components when operating rolling stock systems will assist in reducing lock down and favors heavy productivity. In that light, this paper showcases a suitable methodology to track degradation of components through the blinding of physic laws and artificial intelligent techniques. This model used to foresee failure deterioration rate and remaining useful life (RUL) speculation is case study to showcase its quality and perfection, within which behavioral data are obtained through simulated models initiated in Mathlab. For feature extraction and forecasting issues, different neuro-fuzzy inference systems are designed, learnt and authenticated with powerful outputs gained during this process.展开更多
Failure prediction plays an important role for many tasks such as optimal resource management in large-scale system. However, accurately failure number prediction of repairable large-scale long-running computing （RLL...Failure prediction plays an important role for many tasks such as optimal resource management in large-scale system. However, accurately failure number prediction of repairable large-scale long-running computing （RLLC） is a challenge because of the reparability and large-scale. To address the challenge, a general Bayesian serial revision prediction method based on Bootstrap approach and moving average approach is put forward, which can make an accurately prediction for the failure number. To demonstrate the performance gains of our method, extensive experiments on the data of Los Alamos National Laboratory （LANL） cluster is implemented, which is a typical RLLC system. And experimental results show that the prediction accuracy of our method is 80.2 %, and it is a greatly improvement with 4 % compared with some typical methods. Finally, the managerial implications of the models are discussed.展开更多
Cloud data centers consume high volume of energy for processing and switching the servers among different modes.Virtual Machine(VM)migration enhances the performance of cloud servers in terms of energy efficiency,inte...Cloud data centers consume high volume of energy for processing and switching the servers among different modes.Virtual Machine(VM)migration enhances the performance of cloud servers in terms of energy efficiency,internal failures and availability.On the other end,energy utilization can be minimized by decreasing the number of active,underutilized sources which conversely reduces the dependability of the system.In VM migration process,the VMs are migrated from underutilized physical resources to other resources to minimize energy utilization and optimize the operations.In this view,the current study develops an Improved Metaheuristic Based Failure Prediction with Virtual Machine Migration Optimization(IMFP-VMMO)model in cloud environment.The major intention of the proposed IMFP-VMMO model is to reduce energy utilization with maximum performance in terms of failure prediction.To accomplish this,IMFPVMMO model employs Gradient Boosting Decision Tree(GBDT)classification model at initial stage for effectual prediction of VM failures.At the same time,VMs are optimally migrated using Quasi-Oppositional Artificial Fish Swarm Algorithm(QO-AFSA)which in turn reduces the energy consumption.The performance of the proposed IMFP-VMMO technique was validated and the results established the enhanced performance of the proposed model.The comparative study outcomes confirmed the better performance of the proposed IMFP-VMMO model over recent approaches.展开更多
Scientific workflows have gained the emerging attention in sophisti-cated large-scale scientific problem-solving environments.The pay-per-use model of cloud,its scalability and dynamic deployment enables it suited for ex...Scientific workflows have gained the emerging attention in sophisti-cated large-scale scientific problem-solving environments.The pay-per-use model of cloud,its scalability and dynamic deployment enables it suited for executing scientific workflow applications.Since the cloud is not a utopian environment,failures are inevitable that may result in experiencingfluctuations in the delivered performance.Though a single task failure occurs in workflow based applications,due to its task dependency nature,the reliability of the overall system will be affected drastically.Hence rather than reactive fault-tolerant approaches,proactive measures are vital in scientific workflows.This work puts forth an attempt to con-centrate on the exploration issue of structuring a nature inspired metaheuristics-Intelligent Water Drops Algorithm(IWDA)combined with an efficient machine learning approach-Support Vector Regression(SVR)for task failure prognostica-tion which facilitates proactive fault-tolerance in the scheduling of scientific workflow applications.The failure prediction models in this study have been implemented through SVR-based machine learning approaches and the precision accuracy of prediction is optimized by IWDA and several performance metrics were evaluated on various benchmark workflows.The experimental results prove that the proposed proactive fault-tolerant approach performs better compared with the other existing techniques.展开更多
The “well factory” mode's high-density well placement and multi-stage hydraulic fracturing technology enable efficient development of unconventional oil and gas resources.However,the deployment of platform wells...The “well factory” mode's high-density well placement and multi-stage hydraulic fracturing technology enable efficient development of unconventional oil and gas resources.However,the deployment of platform wells in the “well factory” model results in small wellbore spacing,and the stress disturbances caused by fracturing operations may affect neighboring wells,leading to inter-well interference phenomena that cause casing deformation.This study investigates the issue of inter-well interference causing casing deformation or even failure during multi-stage hydraulic fracturing in the “well factory”model,and predicts high-risk locations for casing failure.A flow-mechanics coupled geomechanical finite element model with retaining geological stratification characteristics was established.Based on the theory of hydraulic fracturing-induced rock fragmentation and fluid action leading to the degradation of rock mechanical properties,the model simulated the four-dimensional evolution of multi-well fracturing areas over time and space,calculating the disturbance in the regional stress field caused by fracturing operations.Subsequently,the stress distribution of multiple well casings at different time points was calculated to predict high-risk locations for casing failure.The research results show that the redistribution of the stress field in the fracturing area increases the stress on the casing.The overlapping fracturing zones between wells cause significant stress interference,greatly increasing the risk of deformation and failure.By analyzing the Mises stress distribution of multi-well casings,high-risk locations for casing failure can be identified.The conclusion is that the key to preventing casing failure in platform wells in the “well factory” model is to optimize the spatial distribution of fracturing zones between wells and reasonably arrange well spacing.The study provides new insights and methods for predicting casing failure in unconventional oil and gas reservoirs and offers references for optimizing drilling and fracturing designs.展开更多
Disk failures,the most common and major failures in storage systems,increase the risk of service interruption and data loss,and bring additional maintenance costs,which reduces system reliability.Disk failure predicti...Disk failures,the most common and major failures in storage systems,increase the risk of service interruption and data loss,and bring additional maintenance costs,which reduces system reliability.Disk failure prediction methods aim to forecast failures,initiating prompt data migration and disk replacement.Existing methods continuously optimize the models with different sampling methods and modeling algorithms.However,due to issues such as inaccurate sample labeling,insufficient data sampling,and improper sample segmentation,the predictive capabilities of existing models within the lookahead-window time are unstable and decline as the lookahead-window time increases.To address this,we propose LWCM(Lookahead-Window Constrained Model)to improve the predictability and stability of failure prediction models within the lookahead-window time.LWCM leverages dynamic sample relabeling methods based on lookahead-window time constraints and failure symptom durations to modify inaccurate sample labels.LWCM utilizes effective sample data by using the two-phase data sampling method including initial expectation sampling and subsequent segmented resampling.LWCM employs dynamic weighted optimization in backpropagation to enhance the predictability and stability of the disk failure prediction model.Experimental results show that LWCM has better failure prediction performance.The true positive and false positive rates surpass those of the offline-RF model by 38.7%and 92.4%,respectively.Furthermore,LWCM demonstrates its applicability across disk models while maintaining stability within the lookahead constraint window.展开更多
This study examines how native pore structures and loading conditions influencethe fracture size distribution and the predictability of catastrophic failure in rocks.Four lithologies with distinct pore characteristics...This study examines how native pore structures and loading conditions influencethe fracture size distribution and the predictability of catastrophic failure in rocks.Four lithologies with distinct pore characteristics,i.e.granite,limestone,red sandstone,and marble,were tested under uniaxial compression and Brazilian splitting.Nuclear magnetic resonance(NMR)was used to characterize pore structures,while acoustic emission(AE)monitoring captured the temporal evolution of microcracking.The relationships among pore properties,AE b-values,and failure predictability were systematically evaluated.Results show that the overall b-value is primarily controlled by native pore size rather than loading condition.Rocks with larger pores display higher b-value and greater temporal variability,whereas those with smaller pores exhibit lower and more stable b-value.To assess failure predictability,the AE count rate was incorporated into an inverse power law model.The model demonstrates higher predictive accuracy for high-porosity rocks.The average predicted failure time(t_(p))decreases monotonically with porosity:under uniaxial compression,t_(p)for granite,marble,limestone,and sandstone are 2.32,1.82,1.42,and 0.03,respectively;under Brazilian splitting,3.54,3.30,0.10,and 0.03.Among the four rock types,sandstone with the highest porosity exhibits the smallest discrepancy between predicted and actual failure time,whereas granite with the lowest porosity shows the largest.As porosity decreases,prediction accuracy progressively declines for limestone and marble.Overall,the findings indicate that native pore heterogeneity governs both fracture scaling behavior and failure predictability,and that these effects are largely independent of the loading conditions examined in this study.展开更多
An effective prognostic program is crucial to the predictive maintenance of complex equipment since it can improve productivity, prolong equipment life, and enhance system safety. This paper proposes a novel technique...An effective prognostic program is crucial to the predictive maintenance of complex equipment since it can improve productivity, prolong equipment life, and enhance system safety. This paper proposes a novel technique for accurate failure prognosis based on back propagation neural network and quantum multi-agent algorithm. Inspired by the extensive research of quantum computing theory and multi-agent systems, the technique employs a quantum multi-agent strategy, with the main characteristics of quantum agent representation and several operations including fitness evaluation, cooperation, crossover and mutation, for parameters optimization of neural network to avoid the deficiencies such as slow convergence and liability of getting stuck to local minima. To validate the feasibility of the proposed approach, several numerical approximation experiments were firstly designed, after which real vibrational data of bearings from the Laboratory of Cincinnati University were analyzed and used to assess the health condition for a given future point. The results were rather encouraging and indicated that the presented forecasting method has the potential to be utilized as an estimation tool for failure prediction in industrial machinery.展开更多
This article investigates autonomic failure prediction in large-scale distributed systems with nonlinear dimensionality reduction to automatically extract failure features. Most existing methods for failure prediction...This article investigates autonomic failure prediction in large-scale distributed systems with nonlinear dimensionality reduction to automatically extract failure features. Most existing methods for failure prediction focus on building prediction models or heuristic rules by discovering failure patterns, but the process of feature extraction before failure patterns recognition is rarely considered due to the increasing complexity of modern distributed systems. In this work, a novel performance-centric approach to automate failure prediction is proposed based on manifold learning （ML）. In addition, the ML algorithm named supervised locally linear embedding （SLLE） is applied to achieve feature extraction. To generalize the dimensionality reduction mapping, the nonlinear mapping approximation and optimization solution is also proposed. In experimental work a file transfer test bed with fault injection is developed which can gather multilevel performance metrics transparently. Based on the runtime monitoring of these metrics, the SLLE method can automatically predict more than 50% of the central processing unit （CPU） and memory failures, and around 70% of the network failure.展开更多
The mitigation of commutation failure(CF)depends on the accuracy of CF prediction.In terms of the large error of the existing extinction angle(EA)calculation during the fault transient period,a method for CF predictio...The mitigation of commutation failure(CF)depends on the accuracy of CF prediction.In terms of the large error of the existing extinction angle(EA)calculation during the fault transient period,a method for CF prediction and mitigation is proposed.Variations in both DC current and overlap angle(OA)are considered in the proposed method to predict the EA rapidly.In addition,variations in critical EA and the effect of firing angle(FA)on both DC current and OA are considered in the proposed method to obtain the accurate FA order for the control system.The proposed method can achieve good performance in terms of CF mitigation and reduce reactive consumption at the inverter side when a fault occurs.Simulation results based on the PSCAD/EMTDC show that the proposed method predicts CF rapidly and exhibits good performance in terms of CF mitigation.展开更多
Disk failure prediction methods have been useful in handing a single issue,e.g.,heterogeneous disks,model aging,and minority samples.However,because these issues often exist simultaneously,prediction models that can h...Disk failure prediction methods have been useful in handing a single issue,e.g.,heterogeneous disks,model aging,and minority samples.However,because these issues often exist simultaneously,prediction models that can handle only one will result in prediction bias in reality.Existing disk failure prediction methods simply fuse various models,lacking discussion of training data preparation and learning patterns when facing multiple issues,although the solutions to different issues often conflict with each other.As a result,we first explore the training data preparation for multiple issues via a data partitioning pattern,i.e.,our proposed multi-property data partitioning(MDP).Then,we consider learning with the partitioned data for multiple issues as learning multiple tasks,and introduce the model-agnostic meta-learning(MAML)framework to achieve the learning.Based on these improvements,we propose a novel disk failure prediction model named MDP-MAML.MDP addresses the challenges of uneven partitioning and difficulty in partitioning by time,and MAML addresses the challenge of learning with multiple domains and minor samples for multiple issues.In addition,MDP-MAML can assimilate emerging issues for learning and prediction.On the datasets reported by two real-world data centers,compared to state-of-the-art methods,MDP-MAML can improve the area under the curve(AUC)and false detection rate(FDR)from 0.85 to0.89 and from 0.85 to 0.91,respectively,while reducing false alarm rate(FAR)from 4.88%to 2.85%.展开更多
An approximate macroscopic yield criterion for anisotropic porous sheet metals is adopted in a failure prediction methodology that can be used to investigate the failure of sheet metals under forming operations. This...An approximate macroscopic yield criterion for anisotropic porous sheet metals is adopted in a failure prediction methodology that can be used to investigate the failure of sheet metals under forming operations. This failure prediction methodology is developed based on the Marciniak-Kuczynski approach by assuming a slightly higher void volume fraction inside randomly oriented imperfecte analysis. Here, a nonproportional deformation history including relative rotation of principal stretch directions is identified in a selected critical element of an aluminum sheet from a FEM fender forming simulation. Based on the failure prediction methodology, the failure of the critical sheet element is investigated under the non-proportional deformation history. The results show that thiven non-proportional deformation history.展开更多
In order to achieve failure prediction without manual intervention for distributed systems, a novel failure feature analysis and extraction approach to automate failure prediction is proposed. Compared with the tradit...In order to achieve failure prediction without manual intervention for distributed systems, a novel failure feature analysis and extraction approach to automate failure prediction is proposed. Compared with the traditional methods which focus on building heuristic rules or models, the autonomic prediction approach analyzes the nonlinear correlation of failure features by recognizing failure patterns. Failure data are sorted according to the nonlinear correlation and failure signature is proposed for autonomic prediction. In addition, the Manifold Learning algorithm named supervised locally linear embedding is applied to achieve feature extraction. Based on the runtime monitoring of failure metrics, the experimental results indicate that the proposed method has better performance in terms of both correlation recognition precision and feature extraction quality and thus it can be used to design efficient autonomic failure prediction for distributed systems.展开更多
The reliability of electrical connectors has critical impact on electronic systems. It is usually characterized by failure rate prediction value according to standard MIL-HDBK-217(or GJB-299 C in Chinese) in engineeri...The reliability of electrical connectors has critical impact on electronic systems. It is usually characterized by failure rate prediction value according to standard MIL-HDBK-217(or GJB-299 C in Chinese) in engineering practice. Given to their limitations and mislead results, a new failure rate prediction models needs to be presented. The presented model aims at the mechanism of increase of film thickness which leads to the increase of contact resistance. The estimated failure rate value can be given at different environmental conditions,and some of the factors affecting the reliability are taken into account. Accelerated degradation test(ADT) was conducted on GJB599 III series electrical connector. The failure rate prediction model can be simply formed and convenient to calculate the expression of failure rate changing with time at various temperature and vibration conditions. This model gives an objective assessment in short time, which makes it convenient to be applied to the engineering.展开更多
Oil and gas pipelines are affected by many factors,such as pipe wall thinning and pipeline rupture.Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety man...Oil and gas pipelines are affected by many factors,such as pipe wall thinning and pipeline rupture.Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety management.Aiming at the shortcomings of the BP Neural Network(BPNN)model,such as low learning efficiency,sensitivity to initial weights,and easy falling into a local optimal state,an Improved Sparrow Search Algorithm(ISSA)is adopted to optimize the initial weights and thresholds of BPNN,and an ISSA-BPNN failure pressure prediction model for corroded pipelines is established.Taking 61 sets of pipelines blasting test data as an example,the prediction model was built and predicted by MATLAB software,and compared with the BPNN model,GA-BPNN model,and SSA-BPNN model.The results show that the MAPE of the ISSA-BPNN model is 3.4177%,and the R2 is 0.9880,both of which are superior to its comparison model.Using the ISSA-BPNN model has high prediction accuracy and stability,and can provide support for pipeline inspection and maintenance.展开更多
基金supported by the Tianjin Manufacturing High Quality Development Special Foundation(No.20232185)the Roycom Foundation(No.70306901).
文摘Hard disk drives(HDDs)serve as the primary storage devices in modern data centers.Once a failure occurs,it often leads to severe data loss,significantly degrading the reliability of storage systems.Numerous studies have proposed machine learning-based HDD failure prediction models.However,the Self-Monitoring,Analysis,and Reporting Technology(SMART)attributes differ across HDD manufacturers.We define hard drives of the same brand and model as homogeneous HDD groups,and those from different brands or models as heterogeneous HDD groups.In practical engineering scenarios,a data center is often composed of a heterogeneous population of HDDs,spanning multiple vendors and models.Existing research predominantly focuses on homogeneous datasets,ignoring the model’s generalization capability across heterogeneous HDDs.As a result,HDD models with limited samples often suffer from poor training effectiveness and prediction performance.To address this issue,we investigate generalizable SMART predictors across heterogeneous HDD groups.By extracting time-series features within a fixed sliding time window,we propose a Heterogeneous Disk Failure Prediction Method based on Time Series Features(HDFPM)framework.This method is adaptable to HDD models with limited sample sizes,thereby enhancing its applicability and robustness across diverse drive populations.Experimental results show that the proposed model achieves an F1-score of 0.9518 when applied to two different Seagate HDD models,while maintaining the False Positive Rate(FPR)below 1%.After incorporating the Complexity-Ratio Dynamic Time Warping(CDTW)based feature enhancement method,the best prediction model achieves a True Positive Rate(TPR)of up to 0.93 between the two models.For next-day failure prediction across various Seagate models,the model achieves an F1-score of up to 0.8792.Moreover,the experimental results also show that within the same brand,the higher the proportion of shared SMART attributes across different models,the better the prediction performance.In addition,HDFPMdemonstrates the best stability andmost significant performance in heterogeneous environments.
基金The authors appreciate generous supports from Canada Natural Sciences and Engineering Research Council,McGill University Engine Centre as well as Faculty of Engineering.
文摘This article introduces a novel approach for tricone bit wear condition monitoring and failure prediction for surface mining applications.A successful bit health monitoring system is essential to achieve fully autonomous blasthole drilling.In this research in-situ vibration signals were analyzed in timefrequency domain and signals trend during tricone bit life span were investigated and introduced to support the development of artificial intelligence(AI)models.In addition to the signal statistical features,wavelet packet energy distribution proved to be a powerful indicator for bit wear assessment.Backpropagation artificial neural network(ANN)models were designed,trained and evaluated for bit state classification.Finally,an ANN architecture and feature vector were introduced to classify the bit condition and predict the bit failure.
基金This study was approved by the Ethics Committee of the First Affiliated Hospital of Army Medical University,PLA,and the Approved No.of ethic committee is KY201936This work is supported by the National Key Research&Development Plan of China(2018YFC0116704)in data collectionIn addition,it is supported by Chongqing Technology Innovation and application research and development project(cstc2019jscx-msxmx0237)in the design of the study.
文摘The occurrence of perioperative heart failure will affect the quality of medical services and threaten the safety of patients.Existing methods depend on the judgment of doctors,the results are affected by many factors such as doctors’knowledge and experience.The accuracy is difficult to guarantee and has a serious lag.In this paper,a mixture prediction model is proposed for perioperative adverse events of heart failure,which combined with the advantages of the Deep Pyramid Convolutional Neural Networks(DPCNN)and Extreme Gradient Boosting(XGBOOST).The DPCNN was used to automatically extract features from patient’s diagnostic texts,and the text features were integrated with the preoperative examination and intraoperative monitoring values of patients,then the XGBOOST algorithm was used to construct the prediction model of heart failure.An experimental comparison was conducted on the model based on the data of patients with heart failure in southwest hospital from 2014 to 2018.The results showed that the DPCNN-XGBOOST model improved the predictive sensitivity of the model by 3%and 31%compared with the text-based DPCNN Model and the numeric-based XGBOOST Model.
基金supported in part by National Key Research and Development Program of China(2019YFB2103200)NSFC(61672108),Open Subject Funds of Science and Technology on Information Transmission and Dissemination in Communication Networks Laboratory(SKX182010049)+1 种基金the Fundamental Research Funds for the Central Universities(5004193192019PTB-019)the Industrial Internet Innovation and Development Project 2018 of China.
文摘The development of cloud computing and virtualization technology has brought great challenges to the reliability of data center services.Data centers typically contain a large number of compute and storage nodes which may fail and affect the quality of service.Failure prediction is an important means of ensuring service availability.Predicting node failure in cloud-based data centers is challenging because the failure symptoms reflected have complex characteristics,and the distribution imbalance between the failure sample and the normal sample is widespread,resulting in inaccurate failure prediction.Targeting these challenges,this paper proposes a novel failure prediction method FP-STE(Failure Prediction based on Spatio-temporal Feature Extraction).Firstly,an improved recurrent neural network HW-GRU(Improved GRU based on HighWay network)and a convolutional neural network CNN are used to extract the temporal features and spatial features of multivariate data respectively to increase the discrimination of different types of failure symptoms which improves the accuracy of prediction.Then the intermediate results of the two models are added as features into SCSXGBoost to predict the possibility and the precise type of node failure in the future.SCS-XGBoost is an ensemble learning model that is improved by the integrated strategy of oversampling and cost-sensitive learning.Experimental results based on real data sets confirm the effectiveness and superiority of FP-STE.
基金This work was supported by the Fundamental Research Funds for the Central Universities （No.2017JBM003）, the National Natural Science Foundation of China （No.61575053, No.61504008）, and the Specialized Research Fund for the Doctoral Program of Higher Education of China （No.20130009120042）.
文摘Lithium ion battery has typical character of distributed parameter system, and can be described precisely by partial differential equations and multi-physics theory because lithium ion battery is a complicated electrochemical energy storage system. A novel failure prediction modeling method of lithium ion battery based on distributed parameter estimation and single particle model is proposed in this work. Lithium ion concentration in the anode of lithium ion battery is an unmeasurable distributed variable. Failure prediction system can estimate lithium ion concentration online, track the failure residual which is the difference between the estimated value and the ideal value. The precaution signal will be triggered when the failure residual is beyond the predefined failure precaution threshold, and the failure countdown prediction module will be activated. The remaining time of the severe failure threshold can be estimated by the failure countdown prediction module according to the changing rate of the failure residual. A simulation example verifies that lithium ion concentration in the anode of lithium ion battery can be estimated exactly and effectively by the failure prediction model. The precaution signal can be triggered reliably, and the remaining time of the severe failure can be forecasted accurately by the failure countdown prediction module.
文摘In the rolling stock sector, the ability to protect passengers, freight and services relies on heavy inborn maintenance. Initiating an accurate model suitable to foresee the change of attitude on components when operating rolling stock systems will assist in reducing lock down and favors heavy productivity. In that light, this paper showcases a suitable methodology to track degradation of components through the blinding of physic laws and artificial intelligent techniques. This model used to foresee failure deterioration rate and remaining useful life (RUL) speculation is case study to showcase its quality and perfection, within which behavioral data are obtained through simulated models initiated in Mathlab. For feature extraction and forecasting issues, different neuro-fuzzy inference systems are designed, learnt and authenticated with powerful outputs gained during this process.
基金supported by the National Natural Science Foundationof China (60701006 60804054 71071158)
文摘Failure prediction plays an important role for many tasks such as optimal resource management in large-scale system. However, accurately failure number prediction of repairable large-scale long-running computing （RLLC） is a challenge because of the reparability and large-scale. To address the challenge, a general Bayesian serial revision prediction method based on Bootstrap approach and moving average approach is put forward, which can make an accurately prediction for the failure number. To demonstrate the performance gains of our method, extensive experiments on the data of Los Alamos National Laboratory （LANL） cluster is implemented, which is a typical RLLC system. And experimental results show that the prediction accuracy of our method is 80.2 %, and it is a greatly improvement with 4 % compared with some typical methods. Finally, the managerial implications of the models are discussed.
基金The authors are very grateful to acknowledge their Deanship of Scientific Research at Prince sattam bin abdulaziz university,Saudi Arabia for technical and financial support in publishing this work successfully.
文摘Cloud data centers consume high volume of energy for processing and switching the servers among different modes.Virtual Machine(VM)migration enhances the performance of cloud servers in terms of energy efficiency,internal failures and availability.On the other end,energy utilization can be minimized by decreasing the number of active,underutilized sources which conversely reduces the dependability of the system.In VM migration process,the VMs are migrated from underutilized physical resources to other resources to minimize energy utilization and optimize the operations.In this view,the current study develops an Improved Metaheuristic Based Failure Prediction with Virtual Machine Migration Optimization(IMFP-VMMO)model in cloud environment.The major intention of the proposed IMFP-VMMO model is to reduce energy utilization with maximum performance in terms of failure prediction.To accomplish this,IMFPVMMO model employs Gradient Boosting Decision Tree(GBDT)classification model at initial stage for effectual prediction of VM failures.At the same time,VMs are optimally migrated using Quasi-Oppositional Artificial Fish Swarm Algorithm(QO-AFSA)which in turn reduces the energy consumption.The performance of the proposed IMFP-VMMO technique was validated and the results established the enhanced performance of the proposed model.The comparative study outcomes confirmed the better performance of the proposed IMFP-VMMO model over recent approaches.
文摘Scientific workflows have gained the emerging attention in sophisti-cated large-scale scientific problem-solving environments.The pay-per-use model of cloud,its scalability and dynamic deployment enables it suited for executing scientific workflow applications.Since the cloud is not a utopian environment,failures are inevitable that may result in experiencingfluctuations in the delivered performance.Though a single task failure occurs in workflow based applications,due to its task dependency nature,the reliability of the overall system will be affected drastically.Hence rather than reactive fault-tolerant approaches,proactive measures are vital in scientific workflows.This work puts forth an attempt to con-centrate on the exploration issue of structuring a nature inspired metaheuristics-Intelligent Water Drops Algorithm(IWDA)combined with an efficient machine learning approach-Support Vector Regression(SVR)for task failure prognostica-tion which facilitates proactive fault-tolerance in the scheduling of scientific workflow applications.The failure prediction models in this study have been implemented through SVR-based machine learning approaches and the precision accuracy of prediction is optimized by IWDA and several performance metrics were evaluated on various benchmark workflows.The experimental results prove that the proposed proactive fault-tolerant approach performs better compared with the other existing techniques.
基金supported by the National Natural Science Foundation of China (No.52104008&No.52274042)the Natural Science Foundation of Sichuan,China (No.2024NSFSC0963)。
文摘The “well factory” mode's high-density well placement and multi-stage hydraulic fracturing technology enable efficient development of unconventional oil and gas resources.However,the deployment of platform wells in the “well factory” model results in small wellbore spacing,and the stress disturbances caused by fracturing operations may affect neighboring wells,leading to inter-well interference phenomena that cause casing deformation.This study investigates the issue of inter-well interference causing casing deformation or even failure during multi-stage hydraulic fracturing in the “well factory”model,and predicts high-risk locations for casing failure.A flow-mechanics coupled geomechanical finite element model with retaining geological stratification characteristics was established.Based on the theory of hydraulic fracturing-induced rock fragmentation and fluid action leading to the degradation of rock mechanical properties,the model simulated the four-dimensional evolution of multi-well fracturing areas over time and space,calculating the disturbance in the regional stress field caused by fracturing operations.Subsequently,the stress distribution of multiple well casings at different time points was calculated to predict high-risk locations for casing failure.The research results show that the redistribution of the stress field in the fracturing area increases the stress on the casing.The overlapping fracturing zones between wells cause significant stress interference,greatly increasing the risk of deformation and failure.By analyzing the Mises stress distribution of multi-well casings,high-risk locations for casing failure can be identified.The conclusion is that the key to preventing casing failure in platform wells in the “well factory” model is to optimize the spatial distribution of fracturing zones between wells and reasonably arrange well spacing.The study provides new insights and methods for predicting casing failure in unconventional oil and gas reservoirs and offers references for optimizing drilling and fracturing designs.
基金supported in part by the National Key Research and Development Program of China under Grant No.2023YFB4502801.
文摘Disk failures,the most common and major failures in storage systems,increase the risk of service interruption and data loss,and bring additional maintenance costs,which reduces system reliability.Disk failure prediction methods aim to forecast failures,initiating prompt data migration and disk replacement.Existing methods continuously optimize the models with different sampling methods and modeling algorithms.However,due to issues such as inaccurate sample labeling,insufficient data sampling,and improper sample segmentation,the predictive capabilities of existing models within the lookahead-window time are unstable and decline as the lookahead-window time increases.To address this,we propose LWCM(Lookahead-Window Constrained Model)to improve the predictability and stability of failure prediction models within the lookahead-window time.LWCM leverages dynamic sample relabeling methods based on lookahead-window time constraints and failure symptom durations to modify inaccurate sample labels.LWCM utilizes effective sample data by using the two-phase data sampling method including initial expectation sampling and subsequent segmented resampling.LWCM employs dynamic weighted optimization in backpropagation to enhance the predictability and stability of the disk failure prediction model.Experimental results show that LWCM has better failure prediction performance.The true positive and false positive rates surpass those of the offline-RF model by 38.7%and 92.4%,respectively.Furthermore,LWCM demonstrates its applicability across disk models while maintaining stability within the lookahead constraint window.
基金supported by the National Natural Science Foundation of China(Grant No.42172316)the Major National Science and Technology Project for Deep Earth(Grant No.2024ZD100380X)the Natural Science Foundation of Hunan Province of China(2025JJ20030).
文摘This study examines how native pore structures and loading conditions influencethe fracture size distribution and the predictability of catastrophic failure in rocks.Four lithologies with distinct pore characteristics,i.e.granite,limestone,red sandstone,and marble,were tested under uniaxial compression and Brazilian splitting.Nuclear magnetic resonance(NMR)was used to characterize pore structures,while acoustic emission(AE)monitoring captured the temporal evolution of microcracking.The relationships among pore properties,AE b-values,and failure predictability were systematically evaluated.Results show that the overall b-value is primarily controlled by native pore size rather than loading condition.Rocks with larger pores display higher b-value and greater temporal variability,whereas those with smaller pores exhibit lower and more stable b-value.To assess failure predictability,the AE count rate was incorporated into an inverse power law model.The model demonstrates higher predictive accuracy for high-porosity rocks.The average predicted failure time(t_(p))decreases monotonically with porosity:under uniaxial compression,t_(p)for granite,marble,limestone,and sandstone are 2.32,1.82,1.42,and 0.03,respectively;under Brazilian splitting,3.54,3.30,0.10,and 0.03.Among the four rock types,sandstone with the highest porosity exhibits the smallest discrepancy between predicted and actual failure time,whereas granite with the lowest porosity shows the largest.As porosity decreases,prediction accuracy progressively declines for limestone and marble.Overall,the findings indicate that native pore heterogeneity governs both fracture scaling behavior and failure predictability,and that these effects are largely independent of the loading conditions examined in this study.
基金Acknowledgments The research work presented in this paper was partialy supported by the National Natural Science Foundation of China （Grant No. 61173015 ＆ 61573257）.
文摘An effective prognostic program is crucial to the predictive maintenance of complex equipment since it can improve productivity, prolong equipment life, and enhance system safety. This paper proposes a novel technique for accurate failure prognosis based on back propagation neural network and quantum multi-agent algorithm. Inspired by the extensive research of quantum computing theory and multi-agent systems, the technique employs a quantum multi-agent strategy, with the main characteristics of quantum agent representation and several operations including fitness evaluation, cooperation, crossover and mutation, for parameters optimization of neural network to avoid the deficiencies such as slow convergence and liability of getting stuck to local minima. To validate the feasibility of the proposed approach, several numerical approximation experiments were firstly designed, after which real vibrational data of bearings from the Laboratory of Cincinnati University were analyzed and used to assess the health condition for a given future point. The results were rather encouraging and indicated that the presented forecasting method has the potential to be utilized as an estimation tool for failure prediction in industrial machinery.
基金Acknowledgements This work was supported by the Hi-Tech Research and Development Program of China （2007AA01Z401）, the National Natural Science Foundation of China （90718003, 60973027）.
文摘This article investigates autonomic failure prediction in large-scale distributed systems with nonlinear dimensionality reduction to automatically extract failure features. Most existing methods for failure prediction focus on building prediction models or heuristic rules by discovering failure patterns, but the process of feature extraction before failure patterns recognition is rarely considered due to the increasing complexity of modern distributed systems. In this work, a novel performance-centric approach to automate failure prediction is proposed based on manifold learning （ML）. In addition, the ML algorithm named supervised locally linear embedding （SLLE） is applied to achieve feature extraction. To generalize the dimensionality reduction mapping, the nonlinear mapping approximation and optimization solution is also proposed. In experimental work a file transfer test bed with fault injection is developed which can gather multilevel performance metrics transparently. Based on the runtime monitoring of these metrics, the SLLE method can automatically predict more than 50% of the central processing unit （CPU） and memory failures, and around 70% of the network failure.
基金supported by the National Natural Science Foundation of China(No.51907058)Project of Hunan Power Co.,Ltd.of the State Grid Corporation of China(No.SGTYHT/18-JS-206)Natural Science Foundation of Hunan Province(No.2020JJ5081)。
文摘The mitigation of commutation failure(CF)depends on the accuracy of CF prediction.In terms of the large error of the existing extinction angle(EA)calculation during the fault transient period,a method for CF prediction and mitigation is proposed.Variations in both DC current and overlap angle(OA)are considered in the proposed method to predict the EA rapidly.In addition,variations in critical EA and the effect of firing angle(FA)on both DC current and OA are considered in the proposed method to obtain the accurate FA order for the control system.The proposed method can achieve good performance in terms of CF mitigation and reduce reactive consumption at the inverter side when a fault occurs.Simulation results based on the PSCAD/EMTDC show that the proposed method predicts CF rapidly and exhibits good performance in terms of CF mitigation.
基金Project supported by the National Natural Science Foundation of China(No.61902135)the Shandong Provincial Natural Science Foundation,China(No.ZR2019LZH003)。
文摘Disk failure prediction methods have been useful in handing a single issue,e.g.,heterogeneous disks,model aging,and minority samples.However,because these issues often exist simultaneously,prediction models that can handle only one will result in prediction bias in reality.Existing disk failure prediction methods simply fuse various models,lacking discussion of training data preparation and learning patterns when facing multiple issues,although the solutions to different issues often conflict with each other.As a result,we first explore the training data preparation for multiple issues via a data partitioning pattern,i.e.,our proposed multi-property data partitioning(MDP).Then,we consider learning with the partitioned data for multiple issues as learning multiple tasks,and introduce the model-agnostic meta-learning(MAML)framework to achieve the learning.Based on these improvements,we propose a novel disk failure prediction model named MDP-MAML.MDP addresses the challenges of uneven partitioning and difficulty in partitioning by time,and MAML addresses the challenge of learning with multiple domains and minor samples for multiple issues.In addition,MDP-MAML can assimilate emerging issues for learning and prediction.On the datasets reported by two real-world data centers,compared to state-of-the-art methods,MDP-MAML can improve the area under the curve(AUC)and false detection rate(FDR)from 0.85 to0.89 and from 0.85 to 0.91,respectively,while reducing false alarm rate(FAR)from 4.88%to 2.85%.
文摘An approximate macroscopic yield criterion for anisotropic porous sheet metals is adopted in a failure prediction methodology that can be used to investigate the failure of sheet metals under forming operations. This failure prediction methodology is developed based on the Marciniak-Kuczynski approach by assuming a slightly higher void volume fraction inside randomly oriented imperfecte analysis. Here, a nonproportional deformation history including relative rotation of principal stretch directions is identified in a selected critical element of an aluminum sheet from a FEM fender forming simulation. Based on the failure prediction methodology, the failure of the critical sheet element is investigated under the non-proportional deformation history. The results show that thiven non-proportional deformation history.
基金Supported by the National High Technology Research and Development Programme of China （ No. 2007AA01Z401 ） and the National Natural Science Foundation of China （No. 90718003, 60973027）.
文摘In order to achieve failure prediction without manual intervention for distributed systems, a novel failure feature analysis and extraction approach to automate failure prediction is proposed. Compared with the traditional methods which focus on building heuristic rules or models, the autonomic prediction approach analyzes the nonlinear correlation of failure features by recognizing failure patterns. Failure data are sorted according to the nonlinear correlation and failure signature is proposed for autonomic prediction. In addition, the Manifold Learning algorithm named supervised locally linear embedding is applied to achieve feature extraction. Based on the runtime monitoring of failure metrics, the experimental results indicate that the proposed method has better performance in terms of both correlation recognition precision and feature extraction quality and thus it can be used to design efficient autonomic failure prediction for distributed systems.
文摘The reliability of electrical connectors has critical impact on electronic systems. It is usually characterized by failure rate prediction value according to standard MIL-HDBK-217(or GJB-299 C in Chinese) in engineering practice. Given to their limitations and mislead results, a new failure rate prediction models needs to be presented. The presented model aims at the mechanism of increase of film thickness which leads to the increase of contact resistance. The estimated failure rate value can be given at different environmental conditions,and some of the factors affecting the reliability are taken into account. Accelerated degradation test(ADT) was conducted on GJB599 III series electrical connector. The failure rate prediction model can be simply formed and convenient to calculate the expression of failure rate changing with time at various temperature and vibration conditions. This model gives an objective assessment in short time, which makes it convenient to be applied to the engineering.
文摘Oil and gas pipelines are affected by many factors,such as pipe wall thinning and pipeline rupture.Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety management.Aiming at the shortcomings of the BP Neural Network(BPNN)model,such as low learning efficiency,sensitivity to initial weights,and easy falling into a local optimal state,an Improved Sparrow Search Algorithm(ISSA)is adopted to optimize the initial weights and thresholds of BPNN,and an ISSA-BPNN failure pressure prediction model for corroded pipelines is established.Taking 61 sets of pipelines blasting test data as an example,the prediction model was built and predicted by MATLAB software,and compared with the BPNN model,GA-BPNN model,and SSA-BPNN model.The results show that the MAPE of the ISSA-BPNN model is 3.4177%,and the R2 is 0.9880,both of which are superior to its comparison model.Using the ISSA-BPNN model has high prediction accuracy and stability,and can provide support for pipeline inspection and maintenance.
