Proposed a novel approach to detect changes in the product quality of process systems by using negative selection algorithms inspired by the natural immune system. The most important input variables of the process sys...Proposed a novel approach to detect changes in the product quality of process systems by using negative selection algorithms inspired by the natural immune system. The most important input variables of the process system was represented by artificial immune cells, from which product quality was inferred, instead of directly using the prod- uct quality which was hard to measure online, e.g. the ash content of coal flotation con- centrate. The experiment was presented and then the result was analyzed.展开更多
Conceptual process design (CPD) research focuses on finding design alternatives that address various design problems. It has a long history of well-established methodologies to answer these complex questions, such as ...Conceptual process design (CPD) research focuses on finding design alternatives that address various design problems. It has a long history of well-established methodologies to answer these complex questions, such as heuristics, mathematical programming, and pinch analysis. Nonetheless, progress continues from different formulations of design problems using bottom-up approaches, to the utilization of new tools such as artificial intelligence (AI). It was not until recently that AI methods were involved again in assisting the decision-making steps for chemical engineers. This has led to a gap in understanding AI's capabilities and limitations within the field of CPD research. Thus, this article aims to provide an overview of conventional methods for process synthesis, integration, and intensification approaches and survey emerging AI-assisted process design applications to bridge the gap. A review of all AI-assisted methods is highlighted, where AI is used as a key component within a design framework, to explain the utility of AI with comparative examples. The studies were categorized into supervised and reinforcement learning based on the machine learning training principles they used to enhance the understanding of requirements, benefits, and challenges that come with it. Furthermore, we provide challenges and prospects that can facilitate or hinder the progress of AI-assisted approaches in the future.展开更多
In this paper,a new model free adaptive control method based on self-adjusting PID algorithm(MFACSA-PID)is proposed to solve the problem that the pH process with strong nonlinearity is difficult to control near the ne...In this paper,a new model free adaptive control method based on self-adjusting PID algorithm(MFACSA-PID)is proposed to solve the problem that the pH process with strong nonlinearity is difficult to control near the neutralization point.The MFAC-SA-PID method also solves the problem that the parameters of the model free adaptive control(MFAC)method are not easy to be adjusted and the effect is not obvious by introducing a fuzzy self-adjusting algorithm to adjust the controller parameters.Then the convergence and stability of the MFAC-SA-PID method are proved in this paper.In the simulation study,the control performance of the MFAC-SA-PID method proposed in this paper is compared with the traditional MFAC method and the improved model free adaptive control(IMFAC)method,respectively.The results show that the proposed MFAC-SA-PID method has better control effect on the pH neutralization process.The MFAC-SA-PID control performance also outperforms the traditional MFAC method and IMFAC method when step input disturbances are added,which indicates that the MFAC-SA-PID method has better robustness and stability.展开更多
This survey paper provides a review and perspective on intermediate and advanced reinforcement learning(RL)techniques in process industries. It offers a holistic approach by covering all levels of the process control ...This survey paper provides a review and perspective on intermediate and advanced reinforcement learning(RL)techniques in process industries. It offers a holistic approach by covering all levels of the process control hierarchy. The survey paper presents a comprehensive overview of RL algorithms,including fundamental concepts like Markov decision processes and different approaches to RL, such as value-based, policy-based, and actor-critic methods, while also discussing the relationship between classical control and RL. It further reviews the wide-ranging applications of RL in process industries, such as soft sensors, low-level control, high-level control, distributed process control, fault detection and fault tolerant control, optimization,planning, scheduling, and supply chain. The survey paper discusses the limitations and advantages, trends and new applications, and opportunities and future prospects for RL in process industries. Moreover, it highlights the need for a holistic approach in complex systems due to the growing importance of digitalization in the process industries.展开更多
The rock mass engineering system （RMES） basically consists ofrock mass engineering （RME）, water system and surroundingecological environments, etc. The RMES is characterized by nonlinearity,occurrence of chaos and...The rock mass engineering system （RMES） basically consists ofrock mass engineering （RME）, water system and surroundingecological environments, etc. The RMES is characterized by nonlinearity,occurrence of chaos and self-organization （Tazaka, 1998;Tsuda, 1998; Kishida, 2000）. From construction to abandonmentof RME, the RMES will experience four stages, i.e. initial phase,development phase, declining phase and failure phase. In thiscircumstance, the RMES boundary conditions, structural safetyand surrounding environments are varied at each phase, so arethe evolution characteristics and disasters （Wang et al., 2014）.展开更多
Many process control systems are a kind of hybrid systems. In order to develop a satisfied control strategy, i. e., to make the whole system satisfy some processing requirements, the knowledge of plant is indispensabl...Many process control systems are a kind of hybrid systems. In order to develop a satisfied control strategy, i. e., to make the whole system satisfy some processing requirements, the knowledge of plant is indispensable. This paper proposes a formal model for the general plant for a kind of process control systems. Based on the model, requirements for the system can be specified from goals, and the controller can be designed according to plant based formal approach . An industrial process control system is used to illustrate our models and methods. Duration Calculus, a real time interval logic, is utilized to specify some characters of the model and development of control program for the exemplified system.展开更多
Energy efficiency is closely related to the evolution of biological systems and is important to their information processing. In this work, we calculate the excitation probability of a simple model of a bistable biolo...Energy efficiency is closely related to the evolution of biological systems and is important to their information processing. In this work, we calculate the excitation probability of a simple model of a bistable biological unit in response to pulsatile inputs, and its spontaneous excitation rate due to noise perturbation. Then we analytically calculate the mutual information, energy cost, and energy efficiency of an array of these bistable units. We find that the optimal number of units could maximize this array＇s energy efficiency in encoding pulse inputs, which depends on the fixed energy cost. We conclude that demand for energy efficiency in biological systems may strongly influence the size of these systems under the pressure of natural selection.展开更多
The rapid developing of the fourth generation(4G)wireless communications has aroused tremendous demands for high speed data transmission due to the dissemination of various types of the intelligent user terminals as w...The rapid developing of the fourth generation(4G)wireless communications has aroused tremendous demands for high speed data transmission due to the dissemination of various types of the intelligent user terminals as well as the wireless multi-media services.It is predicted that the network throughput will increase展开更多
Waste heat generation,upgrading,and refrigeration are the fundamental ways to recover and utilize waste heat.Rationalizing the use of refrigerants also contributes to creating energy savings and minimizing carbon emis...Waste heat generation,upgrading,and refrigeration are the fundamental ways to recover and utilize waste heat.Rationalizing the use of refrigerants also contributes to creating energy savings and minimizing carbon emissions.This study evaluates the thermodynamics,economics,and environment of different refrigerants in three waste heat recovery schemes:generate electricity,heat pump,and refrigeration.Based on this,the entropy weight and technique for order preference by similarity to an ideal solution are combined to assess the overall performance of the refrigerants.A thorough analysis reveals that R1234ze(E)could replace R245fa and R123 in the organic Rankine cycle.The best refrigerant for vapor compression refrigeration and high-temperature heat pump systems is R1243zf.In addition,the multi-objective decision analysis shows that the performance difference among the nine selected refrigerants is the total cost,followed by the environmental impact.The approach successfully recognizes the variations between different refrigerants in the same waste heat recovery scheme and gives a thorough evaluation.It sets instructions for the future use of eco-friendly refrigerants and their application of waste heat recovery schemes.展开更多
Safe, ef cient, and sustainable operations and control are primary objectives in industrial manufacturing processes. State-of-the-art technologies heavily rely on human intervention, thereby showing apparent limitatio...Safe, ef cient, and sustainable operations and control are primary objectives in industrial manufacturing processes. State-of-the-art technologies heavily rely on human intervention, thereby showing apparent limitations in practice. The burgeoning era of big data is in uencing the process industries tremendously, providing unprecedented opportunities to achieve smart manufacturing. This kind of manufacturing requires machines to not only be capable of relieving humans from intensive physical work, but also be effective in taking on intellectual labor and even producing innovations on their own. To attain this goal, data analytics and machine learning are indispensable. In this paper, we review recent advances in data analytics and machine learning applied to the monitoring, control, and optimization of industrial processes, paying particular attention to the interpretability and functionality of machine learning mod- els. By analyzing the gap between practical requirements and the current research status, promising future research directions are identi ed.展开更多
A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively ...A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.展开更多
Reliable process monitoring is important for ensuring process safety and product quality.A production process is generally characterized bymultiple operation modes,and monitoring thesemultimodal processes is challengi...Reliable process monitoring is important for ensuring process safety and product quality.A production process is generally characterized bymultiple operation modes,and monitoring thesemultimodal processes is challenging.Most multimodal monitoring methods rely on the assumption that the modes are independent of each other,which may not be appropriate for practical application.This study proposes a transition-constrained Gaussian mixture model method for efficient multimodal process monitoring.This technique can reduce falsely and frequently occurring mode transitions by considering the time series information in the mode identification of historical and online data.This process enables the identified modes to reflect the stability of actual working conditions,improve mode identification accuracy,and enhance monitoring reliability in cases of mode overlap.Case studies on a numerical simulation example and simulation of the penicillin fermentation process are provided to verify the effectiveness of the proposed approach inmultimodal process monitoring with mode overlap.展开更多
Methanol to olefin(MTO)technology provides the opportunity to produce olefins from nonpetroleum sources such as coal,biomass and natural gas.More than 20 commercial MTO plants have been put into operation.Till now,con...Methanol to olefin(MTO)technology provides the opportunity to produce olefins from nonpetroleum sources such as coal,biomass and natural gas.More than 20 commercial MTO plants have been put into operation.Till now,contributions on optimal operation of industrial MTO plants from a process systems engineering perspective are rare.Based on relevance vector machine(RVM),a data-driven framework for optimal operation of the industrial MTO process is established to fully utilize the plentiful industrial data sets.RVM correlates the yield distribution prediction of main products and the operation conditions.These correlations then serve as the constraints for the multi-objective optimization model to pursue the optimal operation of the plant.Nondominated sorting genetic algorithmⅡis used to solve the optimization problem.Comprehensive tests demonstrate that the ethylene yield is effectively improved based on the proposed framework.Since RVM does provide the distribution prediction instead of point estimation,the established model is expected to provide guidance for actual production operations under uncertainty.展开更多
With the increase in the complexity of industrial system, simply detecting and diagnosing a fault may be insufficient in some cases, and prognosing the fault ahead of time could have a certain necessity. Accurate pred...With the increase in the complexity of industrial system, simply detecting and diagnosing a fault may be insufficient in some cases, and prognosing the fault ahead of time could have a certain necessity. Accurate prediction of key alarm variables in chemical process can indicate the possible change to reduce the probability of abnormal conditions. According to the characteristics of chemical process data, this work proposed a key alarm variables prediction model in chemical process based on dynamic-inner principal component analysis(DiPCA) and long short-term memory(LSTM). DiPCA is used to extract the most dynamic components for prediction. While LSTM is used to learn the relationship and predict the key alarm variables. This work used a simulation data set and a real hydrogenation process data set for applications and explained the model validity from the essential characteristics. Comparison of results with different models shows that our model has better prediction accuracy and performance, which can provide the basis for fault prognosis and health management.展开更多
Steam cracking is the dominant technology for producing light olefins,which are believed to be the foundation of the chemical industry.Predictive models of the cracking process can boost production efficiency and prof...Steam cracking is the dominant technology for producing light olefins,which are believed to be the foundation of the chemical industry.Predictive models of the cracking process can boost production efficiency and profit margin.Rapid advancements in machine learning research have recently enabled data-driven solutions to usher in a new era of process modeling.Meanwhile,its practical application to steam cracking is still hindered by the trade-off between prediction accuracy and computational speed.This research presents a framework for data-driven intelligent modeling of the steam cracking process.Industrial data preparation and feature engineering techniques provide computational-ready datasets for the framework,and feedstock similarities are exploited using k-means clustering.We propose LArge-Residuals-Deletion Multivariate Adaptive Regression Spline(LARD-MARS),a modeling approach that explicitly generates output formulas and eliminates potentially outlying instances.The framework is validated further by the presentation of clustering results,the explanation of variable importance,and the testing and comparison of model performance.展开更多
The dynamic soft sensor based on a single Gaussian process regression(GPR) model has been developed in fermentation processes.However,limitations of single regression models,for multiphase/multimode fermentation proce...The dynamic soft sensor based on a single Gaussian process regression(GPR) model has been developed in fermentation processes.However,limitations of single regression models,for multiphase/multimode fermentation processes,may result in large prediction errors and complexity of the soft sensor.Therefore,a dynamic soft sensor based on Gaussian mixture regression(GMR) was proposed to overcome the problems.Two structure parameters,the number of Gaussian components and the order of the model,are crucial to the soft sensor model.To achieve a simple and effective soft sensor,an iterative strategy was proposed to optimize the two structure parameters synchronously.For the aim of comparisons,the proposed dynamic GMR soft sensor and the existing dynamic GPR soft sensor were both investigated to estimate biomass concentration in a Penicillin simulation process and an industrial Erythromycin fermentation process.Results show that the proposed dynamic GMR soft sensor has higher prediction accuracy and is more suitable for dynamic multiphase/multimode fermentation processes.展开更多
A novel process monitoring method based on convolutional neural network(CNN)is proposed and applied to detect faults in industrial process.By utilizing the CNN algorithm,cross-correlation and autocorrelation among var...A novel process monitoring method based on convolutional neural network(CNN)is proposed and applied to detect faults in industrial process.By utilizing the CNN algorithm,cross-correlation and autocorrelation among variables are captured to establish a prediction model for each process variable to approximate the first-principle of physical/chemical relationships among different variables under normal operating conditions.When the process is operated under pre-set operating conditions,prediction residuals can be assumed as noise if a proper model is employed.Once process faults occur,the residuals will increase due to the changes of correlation among variables.A principal component analysis(PCA)model based on the residuals is established to realize process monitoring.By monitoring the changes in main feature of prediction residuals,the faults can be promptly detected.Case studies on a numerical nonlinear example and data from two industrial processes are presented to validate the performance of process monitoring based on CNN.展开更多
This work presents a simulation study of several Ca-Cu looping variants with CO(2)capture,aiming at both parameter optimization and exergy analysis of these Ca-Cu looping systems.Three kinds of Ca-Cu looping are consi...This work presents a simulation study of several Ca-Cu looping variants with CO(2)capture,aiming at both parameter optimization and exergy analysis of these Ca-Cu looping systems.Three kinds of Ca-Cu looping are considered:(1)carbonation-calcination/reduction-oxidation;(2)carbonation-oxidation-calcination/reduction and (3)carbona tion/oxidation-calcination/reduction.A conventional Ca looping is also simulated for comparison.The influences of the calcination temperature on the mole fractions of CO(2)and CaO at the calciner outlet,the CaCO3 flow rate on the carbonator performance and the Cu/Ca ratio on the calciner performance are analyzed.The second kind of Ca-Cu looping has the highest carbonation conversion.At 1×10^5 Pa and 820℃,complete decomposition of CaCO3 can be achieved in three Ca-Cu looping systems,while the operation condition of 1×10^5 Pa,840℃is required for the conventional Ca looping system.Furthermore,the Cu/Ca molar ratio of 5.13-5.19 is required for the Ca-Cu looping.Exergy analyses show that the maximum exergy destruction occurs in the calciner for the four modes and the second Ca-Cu looping system(i.e.,carbonation-oxidation-calcination/reduction)performs the highest exergy efficiency,up to 65.04%,which is about 30%higher than that of the conventional Ca looping.展开更多
This paper is standing on the recent viewpoint originated from relevant industrial practices that well or-ganized tracing, representing and feedback(TRF) mechanism of material-flow information is crucial for system ut...This paper is standing on the recent viewpoint originated from relevant industrial practices that well or-ganized tracing, representing and feedback(TRF) mechanism of material-flow information is crucial for system utility and usability of manufacturing execution systems(MES), essentially, for activities on the side of multi-level decision making and optimization mainly in the planning and scheduling. In this paper, we investigate a key issue emphasized on a route of multi-level information evolution on the side of large-scale feedback, where material-flow states could evolve from the measuring data(local states) to networked event-type information cells(global states) and consequently to the key performance indicators(KPI) type information(gross states). Importantly, with adapta-bilities to frequent structural dynamics residing in running material flows, this evolving route should be modeled as a suit of sophisticated mechanism for large-scale dynamic states tracking and representing so as to upgrade accu-racy and usability of the feedback information in MES. To clarify inherent complexities of this evolving route, the investigated issue is demonstrated from extended process systems engineering(PSE) point of view, and the TRF principles of the multi-level feedback information(states) are highlighted under the multi-scale methodology. As the main contribution, a novel mechanism called TRF modeling mechanism is introduced.展开更多
In this paper,we present a review of the current literature on distributed(or partially decentralized) control of chemical process networks.In particular,we focus on recent developments in distributed model predictive...In this paper,we present a review of the current literature on distributed(or partially decentralized) control of chemical process networks.In particular,we focus on recent developments in distributed model predictive control,in the context of the specific challenges faced in the control of chemical process networks.The paper is concluded with some open problems and some possible future research directions in the area.展开更多
文摘Proposed a novel approach to detect changes in the product quality of process systems by using negative selection algorithms inspired by the natural immune system. The most important input variables of the process system was represented by artificial immune cells, from which product quality was inferred, instead of directly using the prod- uct quality which was hard to measure online, e.g. the ash content of coal flotation con- centrate. The experiment was presented and then the result was analyzed.
基金financial support from The University of Manchester
文摘Conceptual process design (CPD) research focuses on finding design alternatives that address various design problems. It has a long history of well-established methodologies to answer these complex questions, such as heuristics, mathematical programming, and pinch analysis. Nonetheless, progress continues from different formulations of design problems using bottom-up approaches, to the utilization of new tools such as artificial intelligence (AI). It was not until recently that AI methods were involved again in assisting the decision-making steps for chemical engineers. This has led to a gap in understanding AI's capabilities and limitations within the field of CPD research. Thus, this article aims to provide an overview of conventional methods for process synthesis, integration, and intensification approaches and survey emerging AI-assisted process design applications to bridge the gap. A review of all AI-assisted methods is highlighted, where AI is used as a key component within a design framework, to explain the utility of AI with comparative examples. The studies were categorized into supervised and reinforcement learning based on the machine learning training principles they used to enhance the understanding of requirements, benefits, and challenges that come with it. Furthermore, we provide challenges and prospects that can facilitate or hinder the progress of AI-assisted approaches in the future.
基金supported by the National Natural Science Foundation of China(61771034).
文摘In this paper,a new model free adaptive control method based on self-adjusting PID algorithm(MFACSA-PID)is proposed to solve the problem that the pH process with strong nonlinearity is difficult to control near the neutralization point.The MFAC-SA-PID method also solves the problem that the parameters of the model free adaptive control(MFAC)method are not easy to be adjusted and the effect is not obvious by introducing a fuzzy self-adjusting algorithm to adjust the controller parameters.Then the convergence and stability of the MFAC-SA-PID method are proved in this paper.In the simulation study,the control performance of the MFAC-SA-PID method proposed in this paper is compared with the traditional MFAC method and the improved model free adaptive control(IMFAC)method,respectively.The results show that the proposed MFAC-SA-PID method has better control effect on the pH neutralization process.The MFAC-SA-PID control performance also outperforms the traditional MFAC method and IMFAC method when step input disturbances are added,which indicates that the MFAC-SA-PID method has better robustness and stability.
基金supported in part by the Natural Sciences Engineering Research Council of Canada (NSERC)。
文摘This survey paper provides a review and perspective on intermediate and advanced reinforcement learning(RL)techniques in process industries. It offers a holistic approach by covering all levels of the process control hierarchy. The survey paper presents a comprehensive overview of RL algorithms,including fundamental concepts like Markov decision processes and different approaches to RL, such as value-based, policy-based, and actor-critic methods, while also discussing the relationship between classical control and RL. It further reviews the wide-ranging applications of RL in process industries, such as soft sensors, low-level control, high-level control, distributed process control, fault detection and fault tolerant control, optimization,planning, scheduling, and supply chain. The survey paper discusses the limitations and advantages, trends and new applications, and opportunities and future prospects for RL in process industries. Moreover, it highlights the need for a holistic approach in complex systems due to the growing importance of digitalization in the process industries.
基金funded by the National Natural Science Foundation of China(Grant Nos.51274110,51304108,U1361211)
文摘The rock mass engineering system （RMES） basically consists ofrock mass engineering （RME）, water system and surroundingecological environments, etc. The RMES is characterized by nonlinearity,occurrence of chaos and self-organization （Tazaka, 1998;Tsuda, 1998; Kishida, 2000）. From construction to abandonmentof RME, the RMES will experience four stages, i.e. initial phase,development phase, declining phase and failure phase. In thiscircumstance, the RMES boundary conditions, structural safetyand surrounding environments are varied at each phase, so arethe evolution characteristics and disasters （Wang et al., 2014）.
文摘Many process control systems are a kind of hybrid systems. In order to develop a satisfied control strategy, i. e., to make the whole system satisfy some processing requirements, the knowledge of plant is indispensable. This paper proposes a formal model for the general plant for a kind of process control systems. Based on the model, requirements for the system can be specified from goals, and the controller can be designed according to plant based formal approach . An industrial process control system is used to illustrate our models and methods. Duration Calculus, a real time interval logic, is utilized to specify some characters of the model and development of control program for the exemplified system.
基金Supported by the National Natural Science Foundation of China under Grant Nos 11105062 and 11265014the Fundamental Research Funds for the Central Universities under Grant Nos LZUJBKY-2011-57 and LZUJBKY-2015-119
文摘Energy efficiency is closely related to the evolution of biological systems and is important to their information processing. In this work, we calculate the excitation probability of a simple model of a bistable biological unit in response to pulsatile inputs, and its spontaneous excitation rate due to noise perturbation. Then we analytically calculate the mutual information, energy cost, and energy efficiency of an array of these bistable units. We find that the optimal number of units could maximize this array＇s energy efficiency in encoding pulse inputs, which depends on the fixed energy cost. We conclude that demand for energy efficiency in biological systems may strongly influence the size of these systems under the pressure of natural selection.
文摘The rapid developing of the fourth generation(4G)wireless communications has aroused tremendous demands for high speed data transmission due to the dissemination of various types of the intelligent user terminals as well as the wireless multi-media services.It is predicted that the network throughput will increase
基金supported by the National Natural Science Foundation of China(22178190)the National Youth Natural Science Foundation of China(22408195).
文摘Waste heat generation,upgrading,and refrigeration are the fundamental ways to recover and utilize waste heat.Rationalizing the use of refrigerants also contributes to creating energy savings and minimizing carbon emissions.This study evaluates the thermodynamics,economics,and environment of different refrigerants in three waste heat recovery schemes:generate electricity,heat pump,and refrigeration.Based on this,the entropy weight and technique for order preference by similarity to an ideal solution are combined to assess the overall performance of the refrigerants.A thorough analysis reveals that R1234ze(E)could replace R245fa and R123 in the organic Rankine cycle.The best refrigerant for vapor compression refrigeration and high-temperature heat pump systems is R1243zf.In addition,the multi-objective decision analysis shows that the performance difference among the nine selected refrigerants is the total cost,followed by the environmental impact.The approach successfully recognizes the variations between different refrigerants in the same waste heat recovery scheme and gives a thorough evaluation.It sets instructions for the future use of eco-friendly refrigerants and their application of waste heat recovery schemes.
文摘Safe, ef cient, and sustainable operations and control are primary objectives in industrial manufacturing processes. State-of-the-art technologies heavily rely on human intervention, thereby showing apparent limitations in practice. The burgeoning era of big data is in uencing the process industries tremendously, providing unprecedented opportunities to achieve smart manufacturing. This kind of manufacturing requires machines to not only be capable of relieving humans from intensive physical work, but also be effective in taking on intellectual labor and even producing innovations on their own. To attain this goal, data analytics and machine learning are indispensable. In this paper, we review recent advances in data analytics and machine learning applied to the monitoring, control, and optimization of industrial processes, paying particular attention to the interpretability and functionality of machine learning mod- els. By analyzing the gap between practical requirements and the current research status, promising future research directions are identi ed.
文摘A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.
基金supported in part by National Natural Science Foundation of China under Grants 61973119 and 61603138in part by Shanghai Rising-Star Program under Grant 20QA1402600+1 种基金in part by the Open Funding from Shandong Key Laboratory of Big-data Driven Safety Control Technology for Complex Systems under Grant SKDN202001in part by the Programme of Introducing Talents of Discipline to Universities(the 111 Project)under Grant B17017.
文摘Reliable process monitoring is important for ensuring process safety and product quality.A production process is generally characterized bymultiple operation modes,and monitoring thesemultimodal processes is challenging.Most multimodal monitoring methods rely on the assumption that the modes are independent of each other,which may not be appropriate for practical application.This study proposes a transition-constrained Gaussian mixture model method for efficient multimodal process monitoring.This technique can reduce falsely and frequently occurring mode transitions by considering the time series information in the mode identification of historical and online data.This process enables the identified modes to reflect the stability of actual working conditions,improve mode identification accuracy,and enhance monitoring reliability in cases of mode overlap.Case studies on a numerical simulation example and simulation of the penicillin fermentation process are provided to verify the effectiveness of the proposed approach inmultimodal process monitoring with mode overlap.
基金financial support for this work from National Natural Science Foundation of China(21978150,21706143)。
文摘Methanol to olefin(MTO)technology provides the opportunity to produce olefins from nonpetroleum sources such as coal,biomass and natural gas.More than 20 commercial MTO plants have been put into operation.Till now,contributions on optimal operation of industrial MTO plants from a process systems engineering perspective are rare.Based on relevance vector machine(RVM),a data-driven framework for optimal operation of the industrial MTO process is established to fully utilize the plentiful industrial data sets.RVM correlates the yield distribution prediction of main products and the operation conditions.These correlations then serve as the constraints for the multi-objective optimization model to pursue the optimal operation of the plant.Nondominated sorting genetic algorithmⅡis used to solve the optimization problem.Comprehensive tests demonstrate that the ethylene yield is effectively improved based on the proposed framework.Since RVM does provide the distribution prediction instead of point estimation,the established model is expected to provide guidance for actual production operations under uncertainty.
基金support from the National Natural Science Foundation of China (21878171)。
文摘With the increase in the complexity of industrial system, simply detecting and diagnosing a fault may be insufficient in some cases, and prognosing the fault ahead of time could have a certain necessity. Accurate prediction of key alarm variables in chemical process can indicate the possible change to reduce the probability of abnormal conditions. According to the characteristics of chemical process data, this work proposed a key alarm variables prediction model in chemical process based on dynamic-inner principal component analysis(DiPCA) and long short-term memory(LSTM). DiPCA is used to extract the most dynamic components for prediction. While LSTM is used to learn the relationship and predict the key alarm variables. This work used a simulation data set and a real hydrogenation process data set for applications and explained the model validity from the essential characteristics. Comparison of results with different models shows that our model has better prediction accuracy and performance, which can provide the basis for fault prognosis and health management.
基金supported by the National Key Research and Development Program of China(2021 YFB 4000500,2021 YFB 4000501,and 2021 YFB 4000502)。
文摘Steam cracking is the dominant technology for producing light olefins,which are believed to be the foundation of the chemical industry.Predictive models of the cracking process can boost production efficiency and profit margin.Rapid advancements in machine learning research have recently enabled data-driven solutions to usher in a new era of process modeling.Meanwhile,its practical application to steam cracking is still hindered by the trade-off between prediction accuracy and computational speed.This research presents a framework for data-driven intelligent modeling of the steam cracking process.Industrial data preparation and feature engineering techniques provide computational-ready datasets for the framework,and feedstock similarities are exploited using k-means clustering.We propose LArge-Residuals-Deletion Multivariate Adaptive Regression Spline(LARD-MARS),a modeling approach that explicitly generates output formulas and eliminates potentially outlying instances.The framework is validated further by the presentation of clustering results,the explanation of variable importance,and the testing and comparison of model performance.
基金Supported by the Natural Science Foundation of Jiangsu Province of China(BK20130531)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD[2011]6)Jiangsu Government Scholarship
文摘The dynamic soft sensor based on a single Gaussian process regression(GPR) model has been developed in fermentation processes.However,limitations of single regression models,for multiphase/multimode fermentation processes,may result in large prediction errors and complexity of the soft sensor.Therefore,a dynamic soft sensor based on Gaussian mixture regression(GMR) was proposed to overcome the problems.Two structure parameters,the number of Gaussian components and the order of the model,are crucial to the soft sensor model.To achieve a simple and effective soft sensor,an iterative strategy was proposed to optimize the two structure parameters synchronously.For the aim of comparisons,the proposed dynamic GMR soft sensor and the existing dynamic GPR soft sensor were both investigated to estimate biomass concentration in a Penicillin simulation process and an industrial Erythromycin fermentation process.Results show that the proposed dynamic GMR soft sensor has higher prediction accuracy and is more suitable for dynamic multiphase/multimode fermentation processes.
文摘A novel process monitoring method based on convolutional neural network(CNN)is proposed and applied to detect faults in industrial process.By utilizing the CNN algorithm,cross-correlation and autocorrelation among variables are captured to establish a prediction model for each process variable to approximate the first-principle of physical/chemical relationships among different variables under normal operating conditions.When the process is operated under pre-set operating conditions,prediction residuals can be assumed as noise if a proper model is employed.Once process faults occur,the residuals will increase due to the changes of correlation among variables.A principal component analysis(PCA)model based on the residuals is established to realize process monitoring.By monitoring the changes in main feature of prediction residuals,the faults can be promptly detected.Case studies on a numerical nonlinear example and data from two industrial processes are presented to validate the performance of process monitoring based on CNN.
基金financially supported by National Key R&D Program of China(2019YFE0100100)。
文摘This work presents a simulation study of several Ca-Cu looping variants with CO(2)capture,aiming at both parameter optimization and exergy analysis of these Ca-Cu looping systems.Three kinds of Ca-Cu looping are considered:(1)carbonation-calcination/reduction-oxidation;(2)carbonation-oxidation-calcination/reduction and (3)carbona tion/oxidation-calcination/reduction.A conventional Ca looping is also simulated for comparison.The influences of the calcination temperature on the mole fractions of CO(2)and CaO at the calciner outlet,the CaCO3 flow rate on the carbonator performance and the Cu/Ca ratio on the calciner performance are analyzed.The second kind of Ca-Cu looping has the highest carbonation conversion.At 1×10^5 Pa and 820℃,complete decomposition of CaCO3 can be achieved in three Ca-Cu looping systems,while the operation condition of 1×10^5 Pa,840℃is required for the conventional Ca looping system.Furthermore,the Cu/Ca molar ratio of 5.13-5.19 is required for the Ca-Cu looping.Exergy analyses show that the maximum exergy destruction occurs in the calciner for the four modes and the second Ca-Cu looping system(i.e.,carbonation-oxidation-calcination/reduction)performs the highest exergy efficiency,up to 65.04%,which is about 30%higher than that of the conventional Ca looping.
基金Supported by the National Basic Research Program of China(2012CB720500)the National High Technology Research and Development Program of China(2012AA041102)
文摘This paper is standing on the recent viewpoint originated from relevant industrial practices that well or-ganized tracing, representing and feedback(TRF) mechanism of material-flow information is crucial for system utility and usability of manufacturing execution systems(MES), essentially, for activities on the side of multi-level decision making and optimization mainly in the planning and scheduling. In this paper, we investigate a key issue emphasized on a route of multi-level information evolution on the side of large-scale feedback, where material-flow states could evolve from the measuring data(local states) to networked event-type information cells(global states) and consequently to the key performance indicators(KPI) type information(gross states). Importantly, with adapta-bilities to frequent structural dynamics residing in running material flows, this evolving route should be modeled as a suit of sophisticated mechanism for large-scale dynamic states tracking and representing so as to upgrade accu-racy and usability of the feedback information in MES. To clarify inherent complexities of this evolving route, the investigated issue is demonstrated from extended process systems engineering(PSE) point of view, and the TRF principles of the multi-level feedback information(states) are highlighted under the multi-scale methodology. As the main contribution, a novel mechanism called TRF modeling mechanism is introduced.
基金supported by Australian Research Council(ARC)Discovery Project(No.DP130103330)
文摘In this paper,we present a review of the current literature on distributed(or partially decentralized) control of chemical process networks.In particular,we focus on recent developments in distributed model predictive control,in the context of the specific challenges faced in the control of chemical process networks.The paper is concluded with some open problems and some possible future research directions in the area.
