Baosteel＇s 60000 m^3/h air separation unit （ASU） is the largest oxygen generating system in China. The operational cost of such a giant system is very high. How to reduce the operational cost is a critical issue. T...Baosteel＇s 60000 m^3/h air separation unit （ASU） is the largest oxygen generating system in China. The operational cost of such a giant system is very high. How to reduce the operational cost is a critical issue. This paper discusses the system＇s characteristics,the current operational status and the difficulties in reducing the cost,and analyzes relevant indicators, such as the technical and economical indicators of individual units and systems as well as the indicators concerning the costs. The relationship between the cost and each economical indicator and measures to optimize an economical operation of the oxygen generating system are also discussed in this paper.展开更多
Nowadays,there are some problems in the area of distributed operating system(DOS)and its research methods.To solve these problems,we have provided a Distributed Operat-ing System Auto-generating System(DOSAGS)model,wh...Nowadays,there are some problems in the area of distributed operating system(DOS)and its research methods.To solve these problems,we have provided a Distributed Operat-ing System Auto-generating System(DOSAGS)model,which is characterized by intelli-gence,integration and moldability.DOSAGS’ system structure,functions,work principlesand key problems in its implementation are presented.It is obvious that the DOS generatedby DOSAGS is a real new generation distributed OS.展开更多
Distributed Operating System Formalization Generating System(DOSFGS)consists of agrammar subsystem DOSFSG and a semantics subsystem DOSFSS.DOSFSG is a kind ofContext-free grammar.DOSFSS is a semantics system with an o...Distributed Operating System Formalization Generating System(DOSFGS)consists of agrammar subsystem DOSFSG and a semantics subsystem DOSFSS.DOSFSG is a kind ofContext-free grammar.DOSFSS is a semantics system with an operating set.DOSFGS gen-erates a distributed operating system automatically according to the process of abstraction,description,and refinement.This paper discusses data structures,operating set and defini-tion of DOSFSS.展开更多
Among the available options for renewable energy integration in existing power system, wind power is being considered as one of the suited options for future electrical power generation. The major constraint of wind p...Among the available options for renewable energy integration in existing power system, wind power is being considered as one of the suited options for future electrical power generation. The major constraint of wind power generating system （WPGS） is that it does not provide inertial support because of power electronic converters between the grid and the WPGS to facilitate frequency stabilization. The proposed control strategy suggests a substantial contribution to system inertia in terms of short-term active power support in a two area restructured power system. The control scheme uses fuzzy logic based design and takes frequency deviation as input to provide quick active power support, which balances the drop in frequency and tie-line power during transient conditions. This paper presents a comprehensive study of the wind power impact with increasing wind power penetration on frequency stabilization in restructured power system scenario. Variation of load conditions are also analyzed in simulation studies for the same power system model with the proposed control scheme. Simula- tion results advocates the justification of control scheme over other schemes.展开更多
We propose a scheme for generating squeezed states based on a superconducting hybrid system. Our system consists of a nanomeehanical resonator, a superconducting flux qubit, and a superconducting transmission line res...We propose a scheme for generating squeezed states based on a superconducting hybrid system. Our system consists of a nanomeehanical resonator, a superconducting flux qubit, and a superconducting transmission line resonator. Using our proposal, one can easily generate the squeezed states of the nanomechanical resonator. In our scheme, the nonlinear interaction between the nanomechanical resonator and the superconducting transmission line resonator can be implemented by the flux qubit as ＇nonlinear media＇ with a tunable Josephson energy. The realization of the nonlinearity does not need any operations on the flux qubit and just needs to adiabatically keep it at the ground state, which can greatly decrease the effect of the decoherenee of the flux qubit on the squeezed ef^ciency.展开更多
After an introductiou of the Plucker coordinate geometry, a discussion is made of the expression of screws in Plucker coordiuates and the addition of screws’ As a result, the geometry or geuerating gears is re-studie...After an introductiou of the Plucker coordinate geometry, a discussion is made of the expression of screws in Plucker coordiuates and the addition of screws’ As a result, the geometry or geuerating gears is re-studied and a formula is derived for calculating the axode leugth or hypoid gears’展开更多
We investigate a kind of chaos generating technique on a type of n-dimensional linear differential systems by adding feedback control items under a discontinuous state. This method is checked with some examples of num...We investigate a kind of chaos generating technique on a type of n-dimensional linear differential systems by adding feedback control items under a discontinuous state. This method is checked with some examples of numeric simulation. A constructive theorem is proposed for generalized synchronization related to the above chaotic system.展开更多
In view of the complexity and uncertainty of system, both the state performances and state probabilities of multi-state components can be expressed by interval numbers. The belief function theory is used to characteri...In view of the complexity and uncertainty of system, both the state performances and state probabilities of multi-state components can be expressed by interval numbers. The belief function theory is used to characterize the uncertainty caused by various factors. A modified Markov model is proposed to obtain the state probabilities of components at any given moment and subsequently the mass function is used to represent the precise belief degree of state probabilities. Based on the primary studies of universal generating function(UGF)method, a belief UGF(BUGF) method is utilized to analyze the reliability and the uncertainty of excavator rectifier feedback system. This paper provides an available method to evaluate the reliability of multi-state systems(MSSs) with interval state performances and state probabilities, and also avoid the interval expansion problem.展开更多
At present, universal generating function(UGF) is a reliability evaluation technique which holds the bare-looking and easily program-realized merits in multi-state system. Thus, it is meaningful to apply this method t...At present, universal generating function(UGF) is a reliability evaluation technique which holds the bare-looking and easily program-realized merits in multi-state system. Thus, it is meaningful to apply this method to an actual industry system. Compressor systems in natural gas pipelines are series-parallel multi-state systems,where the compressor units in each compressor station work in a parallel way and these pressure-boosting stations in the pipeline are series connected. Considering the characteristic of gas pipelines, this paper develops two different UGFs to evaluate the system reliability. One(Model 1) establishes a system model from every compressor unit while the other(Model 2) considers the whole system as a combination of multi-state components. Besides, all the parameters of "weight" in UGFs are obtained from thermal-hydraulic models based on the actual engineering and"probability" from Monte Carlo simulation. The results show that the system reliabilities calculated by different UGFs are approximately equal. In addition, the demand of gas and the gas pipeline transportation system show a reverse trend. Because the number of parameters needed in Model 2 is far less than that needed in Model 1,Model 2 is simpler programming and faster solved.展开更多
We discuss three-dimensional uniform distribution and its property in a sphere;give a method of assessing the tactical and technical indices of cartridge ejection uniformity in some type of weapon systems. Meanwhile w...We discuss three-dimensional uniform distribution and its property in a sphere;give a method of assessing the tactical and technical indices of cartridge ejection uniformity in some type of weapon systems. Meanwhile we obtain the test of generating function and the estimation of equivalent radius. The uniformity of distribution is tested and verified with ω2 test method on the basis of stochastic simulation example.展开更多
The original version of this article incorrectly declared no conflicts of interest.The correct conflict of interest statement on behalf of the author has now been included.
This paper introduces an applicable test plan for emergency diesel generator in nuclear power plant. It advances improvement approaches with problems found during field commissioning test and its trouble-shooting proc...This paper introduces an applicable test plan for emergency diesel generator in nuclear power plant. It advances improvement approaches with problems found during field commissioning test and its trouble-shooting processes. The method is based on the integration of complementary through, the extension theory of matter-element model and neural network theory combine to overcome a neural network to learn shelters, and other defects. The purpose of this paper is to provide the better running and commissioning experience for the similar emergency generator unit.展开更多
Neuroinflammation is associated with Parkinson’s disease:Reactive gliosis and neuroinflammation are hallmarks of Parkinson’s disease(PD),a multisystem neurodegenerative disorder characterized by a progressive loss o...Neuroinflammation is associated with Parkinson’s disease:Reactive gliosis and neuroinflammation are hallmarks of Parkinson’s disease(PD),a multisystem neurodegenerative disorder characterized by a progressive loss of dopaminergic neurons.Neuroinflammation has long been considered a mere consequence of neuronal loss,but whether it promotes PD or is a key player in disease progression remains to be determined.Human leukocyte antigen.展开更多
In the scenario of a steam generator tube rupture accident in a lead-cooled fast reactor,secondary circuit subcooled water under high pressure is injected into an ordinary-pressure primary vessel,where a molten lead-b...In the scenario of a steam generator tube rupture accident in a lead-cooled fast reactor,secondary circuit subcooled water under high pressure is injected into an ordinary-pressure primary vessel,where a molten lead-based alloy(typically pure lead or lead-bismuth eutectic(LBE))is used as the coolant.To clarify the pressure build-up characteristics under water-jet injection,this study conducted several experiments by injecting pressurized water into a molten LBE pool at Sun Yat-sen University.To obtain a further understanding,several new experimental parameters were adopted,including the melt temperature,water subcooling,injection pressure,injection duration,and nozzle diameter.Through detailed analyses,it was found that the pressure and temperature during the water-melt interaction exhibited a consistent variation trend with our previous water-droplet injection mode LBE experiment.Similarly,the existence of a steam explosion was confirmed,which typically results in a much stronger pressure build-up.For the non-explosion cases,increasing the injection pressure,melt-pool temperature,nozzle diameter,and water subcooling promoted pressure build-up in the melt pool.However,a limited enhancement effect was observed when increasing the injection duration,which may be owing to the continually rising pressure in the interaction vessel or the isolation effect of the generated steam cavity.Regardless of whether a steam explosion occurred,the calculated mechanical and kinetic energy conversion efficiencies of the melt were relatively small(not exceeding 4.1%and 0.7%,respectively).Moreover,the range of the conversion efficiency was similar to that of previous water-droplet experiments,although the upper limit of the jet mode was slightly lower.展开更多
Due to randomness of wind generator＇s availability, power system planners have big concern on EEG （expected energy generation） and system reliability of power system with wind generators. This paper presents a meth...Due to randomness of wind generator＇s availability, power system planners have big concern on EEG （expected energy generation） and system reliability of power system with wind generators. This paper presents a methodology to evaluate the EEG as well as overall LOLP （loss of load probability）, which is an index for system reliability of multi-area interconnected systems with wind generators, as well as conventional fossil fuel based generating units. The proposed model is also capable of tracking the energy export incorporating the multi-state probability model for wind generator which output varies with time and season.展开更多
The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by...The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.展开更多
We give a new result on the construction of K-frame generators for unitary systems by using the pseudo-inverses of involved operators,which provides an improvement to one known result on this topic.We also introduce t...We give a new result on the construction of K-frame generators for unitary systems by using the pseudo-inverses of involved operators,which provides an improvement to one known result on this topic.We also introduce the concept of K-woven generators for unitary systems,by means of which we investigate the weaving properties of K-frame generators for unitary systems.展开更多
New renewable energy exploitation technologies in offshore structures are vital for future energy production systems.Offshore hybrid wind-wave power generation(HWWPG)systems face increased component failure rates beca...New renewable energy exploitation technologies in offshore structures are vital for future energy production systems.Offshore hybrid wind-wave power generation(HWWPG)systems face increased component failure rates because of harsh weather,significantly affecting the maintenance procedures and reliability.Different types of failure rates of the wind turbine(WT)and wave energy converter(WEC),e.g.,the degradation and failure rates during regular wind speed fluctuation,the degradation and failure rates during intense wind speed fluctuation are considered.By incorporating both WT and WEC,the HWWPG system is designed to enhance the overall amount of electrical energy produced by the system over a given period under varying weather conditions.The universal generating function technique is used to calculate the HWWPG system dependability measures in a structured and efficient manner.This research highlights that intense weather conditions increase the failure rates of both WT and WEC,resulting in higher maintenance costs and more frequent downtimes,thus impacting the HWWPG system’s reliability.Although the HWWPG system can meet the energy demands in the presence of high failure rates,the reliance of the hybrid system on both WT and WEC helps maintain a relatively stable demand satisfaction during periods of high energy demand despite adverse weather conditions.To confirm the added value and applicability of the developed model,a case study of an offshore hybrid platform is conducted.The findings underscore the system’s robustness in maintaining energy production under varied weather conditions,though higher failure rates and maintenance costs arise in intense scenarios.展开更多
1 Introduction In recent years,the rapid development of industrial big data and artificial intelligence(AI)technologies has revolutionized the industrial landscape.Industrial systems,such as manufacturing,energy,trans...1 Introduction In recent years,the rapid development of industrial big data and artificial intelligence(AI)technologies has revolutionized the industrial landscape.Industrial systems,such as manufacturing,energy,transportation,and logistics,have become increasingly complex,generating vast amounts of data[1–3].These big data encompass a wide range of data sources,including sensor data,production logs,and maintenance records,which hold valuable insights[4–6].Moreover,machine learning-based AI techniques can be applied to extract meaningful insights from this big data[7].展开更多
This study presents a comparative analysis of a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of...This study presents a comparative analysis of a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of structural complexity compared to the other two benchmarks. This underscores the need for more intricate benchmarks to simulate realistic scenarios effectively. To facilitate this comparison, we devised several measures of structural complexity and applied them across all three benchmarks. The results of this study can guide future research in the development of more sophisticated text-to-SQL benchmarks. We utilized 11 distinct Language Models (LLMs) to generate SQL queries based on the query descriptions provided by the TPC-DS benchmark. The prompt engineering process incorporated both the query description as outlined in the TPC-DS specification and the database schema of TPC-DS. Our findings indicate that the current state-of-the-art generative AI models fall short in generating accurate decision-making queries. We conducted a comparison of the generated queries with the TPC-DS gold standard queries using a series of fuzzy structure matching techniques based on query features. The results demonstrated that the accuracy of the generated queries is insufficient for practical real-world application.展开更多
文摘Baosteel＇s 60000 m^3/h air separation unit （ASU） is the largest oxygen generating system in China. The operational cost of such a giant system is very high. How to reduce the operational cost is a critical issue. This paper discusses the system＇s characteristics,the current operational status and the difficulties in reducing the cost,and analyzes relevant indicators, such as the technical and economical indicators of individual units and systems as well as the indicators concerning the costs. The relationship between the cost and each economical indicator and measures to optimize an economical operation of the oxygen generating system are also discussed in this paper.
基金Software-Engineering National Key Laboratory of Wuhan University.
文摘Nowadays,there are some problems in the area of distributed operating system(DOS)and its research methods.To solve these problems,we have provided a Distributed Operat-ing System Auto-generating System(DOSAGS)model,which is characterized by intelli-gence,integration and moldability.DOSAGS’ system structure,functions,work principlesand key problems in its implementation are presented.It is obvious that the DOS generatedby DOSAGS is a real new generation distributed OS.
基金Supported by the High Technology Research and Development Programme of China.
文摘Distributed Operating System Formalization Generating System(DOSFGS)consists of agrammar subsystem DOSFSG and a semantics subsystem DOSFSS.DOSFSG is a kind ofContext-free grammar.DOSFSS is a semantics system with an operating set.DOSFGS gen-erates a distributed operating system automatically according to the process of abstraction,description,and refinement.This paper discusses data structures,operating set and defini-tion of DOSFSS.
文摘Among the available options for renewable energy integration in existing power system, wind power is being considered as one of the suited options for future electrical power generation. The major constraint of wind power generating system （WPGS） is that it does not provide inertial support because of power electronic converters between the grid and the WPGS to facilitate frequency stabilization. The proposed control strategy suggests a substantial contribution to system inertia in terms of short-term active power support in a two area restructured power system. The control scheme uses fuzzy logic based design and takes frequency deviation as input to provide quick active power support, which balances the drop in frequency and tie-line power during transient conditions. This paper presents a comprehensive study of the wind power impact with increasing wind power penetration on frequency stabilization in restructured power system scenario. Variation of load conditions are also analyzed in simulation studies for the same power system model with the proposed control scheme. Simula- tion results advocates the justification of control scheme over other schemes.
基金Supported by the National Natural Science Foundation of China under Grant Nos 11274043 and 60978009the Major Research Plan of the National Natural Science Foundation of China under Grant No 91121023
文摘We propose a scheme for generating squeezed states based on a superconducting hybrid system. Our system consists of a nanomeehanical resonator, a superconducting flux qubit, and a superconducting transmission line resonator. Using our proposal, one can easily generate the squeezed states of the nanomechanical resonator. In our scheme, the nonlinear interaction between the nanomechanical resonator and the superconducting transmission line resonator can be implemented by the flux qubit as ＇nonlinear media＇ with a tunable Josephson energy. The realization of the nonlinearity does not need any operations on the flux qubit and just needs to adiabatically keep it at the ground state, which can greatly decrease the effect of the decoherenee of the flux qubit on the squeezed ef^ciency.
文摘After an introductiou of the Plucker coordinate geometry, a discussion is made of the expression of screws in Plucker coordiuates and the addition of screws’ As a result, the geometry or geuerating gears is re-studied and a formula is derived for calculating the axode leugth or hypoid gears’
基金Supported by the National Nature Science Foundation of China under Grant No 70271068.
文摘We investigate a kind of chaos generating technique on a type of n-dimensional linear differential systems by adding feedback control items under a discontinuous state. This method is checked with some examples of numeric simulation. A constructive theorem is proposed for generalized synchronization related to the above chaotic system.
基金the National High Technology Research and Development Program(863)of China(No.2012AA062001)
文摘In view of the complexity and uncertainty of system, both the state performances and state probabilities of multi-state components can be expressed by interval numbers. The belief function theory is used to characterize the uncertainty caused by various factors. A modified Markov model is proposed to obtain the state probabilities of components at any given moment and subsequently the mass function is used to represent the precise belief degree of state probabilities. Based on the primary studies of universal generating function(UGF)method, a belief UGF(BUGF) method is utilized to analyze the reliability and the uncertainty of excavator rectifier feedback system. This paper provides an available method to evaluate the reliability of multi-state systems(MSSs) with interval state performances and state probabilities, and also avoid the interval expansion problem.
基金the National Natural Science Foundation of China(No.51504271)the National Science & Technology Specific Project(No.2016ZX05066005-001)
文摘At present, universal generating function(UGF) is a reliability evaluation technique which holds the bare-looking and easily program-realized merits in multi-state system. Thus, it is meaningful to apply this method to an actual industry system. Compressor systems in natural gas pipelines are series-parallel multi-state systems,where the compressor units in each compressor station work in a parallel way and these pressure-boosting stations in the pipeline are series connected. Considering the characteristic of gas pipelines, this paper develops two different UGFs to evaluate the system reliability. One(Model 1) establishes a system model from every compressor unit while the other(Model 2) considers the whole system as a combination of multi-state components. Besides, all the parameters of "weight" in UGFs are obtained from thermal-hydraulic models based on the actual engineering and"probability" from Monte Carlo simulation. The results show that the system reliabilities calculated by different UGFs are approximately equal. In addition, the demand of gas and the gas pipeline transportation system show a reverse trend. Because the number of parameters needed in Model 2 is far less than that needed in Model 1,Model 2 is simpler programming and faster solved.
文摘We discuss three-dimensional uniform distribution and its property in a sphere;give a method of assessing the tactical and technical indices of cartridge ejection uniformity in some type of weapon systems. Meanwhile we obtain the test of generating function and the estimation of equivalent radius. The uniformity of distribution is tested and verified with ω2 test method on the basis of stochastic simulation example.
文摘The original version of this article incorrectly declared no conflicts of interest.The correct conflict of interest statement on behalf of the author has now been included.
文摘This paper introduces an applicable test plan for emergency diesel generator in nuclear power plant. It advances improvement approaches with problems found during field commissioning test and its trouble-shooting processes. The method is based on the integration of complementary through, the extension theory of matter-element model and neural network theory combine to overcome a neural network to learn shelters, and other defects. The purpose of this paper is to provide the better running and commissioning experience for the similar emergency generator unit.
基金supported by the Spanish Government(ISCIII-FEDER)PI20/01063by Navarra Government(PC 060-061 and PC 192-193)Fundación Gangoiti(to MSA).LA was funded by FPU19/03255.
文摘Neuroinflammation is associated with Parkinson’s disease:Reactive gliosis and neuroinflammation are hallmarks of Parkinson’s disease(PD),a multisystem neurodegenerative disorder characterized by a progressive loss of dopaminergic neurons.Neuroinflammation has long been considered a mere consequence of neuronal loss,but whether it promotes PD or is a key player in disease progression remains to be determined.Human leukocyte antigen.
基金supported by Basic and Applied Basic research foundation of Guangdong province(Nos.2021A1515010343 and 2022A1515011582)the Science and Technology Program of Guangdong Province(Nos.2021A0505030026 and 2022A0505050029).
文摘In the scenario of a steam generator tube rupture accident in a lead-cooled fast reactor,secondary circuit subcooled water under high pressure is injected into an ordinary-pressure primary vessel,where a molten lead-based alloy(typically pure lead or lead-bismuth eutectic(LBE))is used as the coolant.To clarify the pressure build-up characteristics under water-jet injection,this study conducted several experiments by injecting pressurized water into a molten LBE pool at Sun Yat-sen University.To obtain a further understanding,several new experimental parameters were adopted,including the melt temperature,water subcooling,injection pressure,injection duration,and nozzle diameter.Through detailed analyses,it was found that the pressure and temperature during the water-melt interaction exhibited a consistent variation trend with our previous water-droplet injection mode LBE experiment.Similarly,the existence of a steam explosion was confirmed,which typically results in a much stronger pressure build-up.For the non-explosion cases,increasing the injection pressure,melt-pool temperature,nozzle diameter,and water subcooling promoted pressure build-up in the melt pool.However,a limited enhancement effect was observed when increasing the injection duration,which may be owing to the continually rising pressure in the interaction vessel or the isolation effect of the generated steam cavity.Regardless of whether a steam explosion occurred,the calculated mechanical and kinetic energy conversion efficiencies of the melt were relatively small(not exceeding 4.1%and 0.7%,respectively).Moreover,the range of the conversion efficiency was similar to that of previous water-droplet experiments,although the upper limit of the jet mode was slightly lower.
文摘Due to randomness of wind generator＇s availability, power system planners have big concern on EEG （expected energy generation） and system reliability of power system with wind generators. This paper presents a methodology to evaluate the EEG as well as overall LOLP （loss of load probability）, which is an index for system reliability of multi-area interconnected systems with wind generators, as well as conventional fossil fuel based generating units. The proposed model is also capable of tracking the energy export incorporating the multi-state probability model for wind generator which output varies with time and season.
基金described in this paper has been developed with in the project PRESECREL(PID2021-124502OB-C43)。
文摘The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.
基金Supported by NSFC(Nos.12361028,11761057)Science Foundation of Jiangxi Education Department(Nos.GJJ202302,GJJ202303,GJJ202319).
文摘We give a new result on the construction of K-frame generators for unitary systems by using the pseudo-inverses of involved operators,which provides an improvement to one known result on this topic.We also introduce the concept of K-woven generators for unitary systems,by means of which we investigate the weaving properties of K-frame generators for unitary systems.
文摘New renewable energy exploitation technologies in offshore structures are vital for future energy production systems.Offshore hybrid wind-wave power generation(HWWPG)systems face increased component failure rates because of harsh weather,significantly affecting the maintenance procedures and reliability.Different types of failure rates of the wind turbine(WT)and wave energy converter(WEC),e.g.,the degradation and failure rates during regular wind speed fluctuation,the degradation and failure rates during intense wind speed fluctuation are considered.By incorporating both WT and WEC,the HWWPG system is designed to enhance the overall amount of electrical energy produced by the system over a given period under varying weather conditions.The universal generating function technique is used to calculate the HWWPG system dependability measures in a structured and efficient manner.This research highlights that intense weather conditions increase the failure rates of both WT and WEC,resulting in higher maintenance costs and more frequent downtimes,thus impacting the HWWPG system’s reliability.Although the HWWPG system can meet the energy demands in the presence of high failure rates,the reliance of the hybrid system on both WT and WEC helps maintain a relatively stable demand satisfaction during periods of high energy demand despite adverse weather conditions.To confirm the added value and applicability of the developed model,a case study of an offshore hybrid platform is conducted.The findings underscore the system’s robustness in maintaining energy production under varied weather conditions,though higher failure rates and maintenance costs arise in intense scenarios.
基金supported by the Science and Technology Innovation Program of Hunan Province(No.2023RC3097)in part the National Natural Science Foundation of China(No.52105108)in part Young Elite Scientists Sponsorship Program by CAST(No.2023QNRC001).
文摘1 Introduction In recent years,the rapid development of industrial big data and artificial intelligence(AI)technologies has revolutionized the industrial landscape.Industrial systems,such as manufacturing,energy,transportation,and logistics,have become increasingly complex,generating vast amounts of data[1–3].These big data encompass a wide range of data sources,including sensor data,production logs,and maintenance records,which hold valuable insights[4–6].Moreover,machine learning-based AI techniques can be applied to extract meaningful insights from this big data[7].
文摘This study presents a comparative analysis of a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of structural complexity compared to the other two benchmarks. This underscores the need for more intricate benchmarks to simulate realistic scenarios effectively. To facilitate this comparison, we devised several measures of structural complexity and applied them across all three benchmarks. The results of this study can guide future research in the development of more sophisticated text-to-SQL benchmarks. We utilized 11 distinct Language Models (LLMs) to generate SQL queries based on the query descriptions provided by the TPC-DS benchmark. The prompt engineering process incorporated both the query description as outlined in the TPC-DS specification and the database schema of TPC-DS. Our findings indicate that the current state-of-the-art generative AI models fall short in generating accurate decision-making queries. We conducted a comparison of the generated queries with the TPC-DS gold standard queries using a series of fuzzy structure matching techniques based on query features. The results demonstrated that the accuracy of the generated queries is insufficient for practical real-world application.
