期刊文献+
共找到6,179篇文章
< 1 2 250 >
每页显示 20 50 100
Causal temporal graph attention network for fault diagnosis of chemical processes 被引量:1
1
作者 Jiaojiao Luo Zhehao Jin +3 位作者 Heping Jin Qian Li Xu Ji Yiyang Dai 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2024年第6期20-32,共13页
Fault detection and diagnosis(FDD)plays a significant role in ensuring the safety and stability of chemical processes.With the development of artificial intelligence(AI)and big data technologies,data-driven approaches... Fault detection and diagnosis(FDD)plays a significant role in ensuring the safety and stability of chemical processes.With the development of artificial intelligence(AI)and big data technologies,data-driven approaches with excellent performance are widely used for FDD in chemical processes.However,improved predictive accuracy has often been achieved through increased model complexity,which turns models into black-box methods and causes uncertainty regarding their decisions.In this study,a causal temporal graph attention network(CTGAN)is proposed for fault diagnosis of chemical processes.A chemical causal graph is built by causal inference to represent the propagation path of faults.The attention mechanism and chemical causal graph were combined to help us notice the key variables relating to fault fluctuations.Experiments in the Tennessee Eastman(TE)process and the green ammonia(GA)process showed that CTGAN achieved high performance and good explainability. 展开更多
关键词 chemical processes Safety Fault diagnosis Causal discovery Attention mechanism Explainability
下载PDF
Real-time risk prediction of chemical processes based on attention-based Bi-LSTM
2
作者 Qianlin Wang Jiaqi Han +5 位作者 Feng Chen Xin Zhang Cheng Yun Zhan Dou Tingjun Yan Guoan Yang 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2024年第11期131-141,共11页
Refined risk prediction must be achieved to guarantee the safe and steady operation of chemical production processes.However,there is high nonlinearity and association coupling among massive,complicated multisource pr... Refined risk prediction must be achieved to guarantee the safe and steady operation of chemical production processes.However,there is high nonlinearity and association coupling among massive,complicated multisource process data,resulting in a low accuracy of existing prediction technology.For that reason,a real-time risk prediction method for chemical processes based on the attention-based bidirectional long short-term memory(Attention-based Bi-LSTM)is proposed in this study.First,multisource process data,such as temperature,pressure,flow rate,and liquid level,are preprocessed for denoising.Data correlation is analyzed in time windows by setting time windows and moving step lengths to explore correlations,thus establishing a complex network model oriented to the chemical production process.Second,network structure entropy is introduced to reduce the dimensions of the multisource process data.Moreover,a 1D relative risk sequence is acquired by maxemin deviation standardization to judge whether the chemical process is in a steady state.Finally,an Attention-based Bi-LSTM algorithm is established by integrating the attention mechanism and the Bi-LSTM network to fit and train 1D relative risk sequences.In that way,the proposed algorithm achieves real-time prediction and intelligent perception of risk states during chemical production.A case study based on the Tennessee Eastman process(TEP)is conducted.The validity and reasonability of the proposed method are verified by analyzing distribution laws of relative risks under normal and fault conditions.Also,the proposed algorithm importantly improves the prediction accuracy of chemical process risks relative to that of existing prediction technologies. 展开更多
关键词 chemical processes PREDICTION Neural networks Network structure entropy Relative risk sequence
下载PDF
Chemical etching process of copper electrode for bioelectrical impedance technology 被引量:2
3
作者 周伟 宋嵘 +4 位作者 蒋乐伦 许文平 梁国开 程德才 刘灵蛟 《Transactions of Nonferrous Metals Society of China》 SCIE EI CAS CSCD 2012年第6期1501-1506,共6页
In order to obtain bioelectrical impedance electrodes with high stability, the chemical etching process was used to fabricate the copper electrode with a series of surface microstructures. By changing the etching proc... In order to obtain bioelectrical impedance electrodes with high stability, the chemical etching process was used to fabricate the copper electrode with a series of surface microstructures. By changing the etching processing parameters, some comparison experiments were performed to reveal the influence of etching time, etching temperature, etching liquid concentration, and sample sizes on the etching rate and surface microstructures of copper electrode. The result shows that the etching rate is decreased with increasing etching time, and is increased with increasing etching temperature. Moreover, it is found that the sample size has little influence on the etching rate. After choosing the reasonable etching liquid composition (formulation 3), the copper electrode with many surface microstructures can be obtained by chemical etching process at room temperature for 20 rain. In addition, using the alternating current impedance test of electrode-electrode for 24 h, the copper electrode with a series of surface microstructures fabricated by the etching process presents a more stable impedance value compared with the electrocardiograph (ECG) electrode, resulting from the reliable surface contact of copper electrode-electrode. 展开更多
关键词 bioelectrical impedance copper electrode chemical etching surface microstructures processing parameters
下载PDF
Mechanism of Formation of the Ozone Valley over the Tibetan Plateau in Summer-Transport and Chemical Process of Ozone 被引量:14
4
作者 刘煜 李维亮 +1 位作者 周秀骥 何金海 《Advances in Atmospheric Sciences》 SCIE CAS CSCD 2003年第1期103-109,共7页
With the 3D chemical transport model OSLO CTM2, the valley of total column ozone over the Tibetan Plateau in summer is reproduced. The results show that when the ozone valley occurs and develops, the transport process... With the 3D chemical transport model OSLO CTM2, the valley of total column ozone over the Tibetan Plateau in summer is reproduced. The results show that when the ozone valley occurs and develops, the transport process plays the main part in the ozone reduction, but the chemical process partly compensates for the transport process. In the dynamic transport process of ozone, the horizontal transport process plays the main part in the ozone reduction in May, but brings about the ozone increase in June and July. The vertical advective process gradually takes the main role in the ozone reduction in June and July. The effect of convective activities rises gradually so that this effect cannot be overlooked in July, as its magnitude is comparable to that of the net changes. The effect of the gaseous chemical process brings about ozone increases which are more than the net changes sometimes, so the chemical effect is also important. 展开更多
关键词 Tibetan Plateau ozone valley dynamic transport process chemical process
下载PDF
Chemical and biological flocculation process to treat municipal sewage and analysis of biological function 被引量:6
5
作者 XIASi-qing YANGDian-hai XUBin ZHAOJian-fu 《Journal of Environmental Sciences》 SCIE EI CAS CSCD 2005年第1期163-167,共5页
The pilot scale experimental apparatus and the procedure of the chemical and biological flocculation process to verify the feasibility in treating Shanghai municipal sewage were introduced in this paper. In addition, ... The pilot scale experimental apparatus and the procedure of the chemical and biological flocculation process to verify the feasibility in treating Shanghai municipal sewage were introduced in this paper. In addition, the biological function of the process was discussed. The results of optimal running showed that in the reaction tank, the concentration of mixed liquor suspended solid(MLSS) was 2 g/L, hydraulic retention time(HRT) was 35 min, dosage of liquid polyaluminium chloride(PAC) was 60 mg/L, and the concentration of polyacrylamide(PAM) was 0 5 mg/L. The effluent average concentrations of COD Cr , TP, SS and BOD 5 were 50 mg/L, 0 62 mg/L, 18 mg/L, and 17 mg/L, respectively. These were better than the designed demand. In addition, the existence of biological degradation in this system was proven by several methods. The removal efficiencies of the chemical and biological flocculation process were 20% higher than that of the chemical flocculation process above at the same coagulant dosage. The treatment process under different situations was evaluated on a pilot scale experiment, and the results provided magnificent parameters and optimal condition for future operation of the plant. 展开更多
关键词 chemical and biological flocculation process municipal water biological function
下载PDF
Multivariable Decoupling Predictive Control with Input Constraints and Its Application on Chemical Process 被引量:13
6
作者 苏佰丽 陈增强 袁著祉 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2006年第2期216-222,共7页
A constrained decoupling (generalized predictive control) GPC algorithm is proposed for MIMO (malti-input multi-output) system. This algorithm takes account of all constraints of inputs and their increments. By solvin... A constrained decoupling (generalized predictive control) GPC algorithm is proposed for MIMO (malti-input multi-output) system. This algorithm takes account of all constraints of inputs and their increments. By solving matrix equations, the multi-step predictive decoupling controllers are realized. This algorithm need not solve Diophantine functions, and weakens the cross-coupling of the variables. At last the simulation results demon- strate the effectiveness of this proposed strategy. 展开更多
关键词 chemical process control multivariable system OPTIMIZATION predictive control input constraint
下载PDF
Chemical oxygen demand reduction in coffee wastewater through chemical flocculation and advanced oxidation processes 被引量:7
7
作者 ZAYAS Pérez Teresa GEISSLER Gunther HERNANDEZ Fernando 《Journal of Environmental Sciences》 SCIE EI CAS CSCD 2007年第3期300-305,共6页
The removal of the natural organic matter present in coffee processing wastewater through chemical coagulation-flocculation and advanced oxidation processes (AOP) had been studied. The effectiveness of the removal o... The removal of the natural organic matter present in coffee processing wastewater through chemical coagulation-flocculation and advanced oxidation processes (AOP) had been studied. The effectiveness of the removal of natural organic matter using commercial flocculants and UV/H202, UV/O3 and UV/H2O2/O3 processes was determined under acidic conditions. For each of these processes, different operational conditions were explored to optimize the treatment efficiency of the coffee wastewater. Coffee wastewater is characterized by a high chemical oxygen demand (COD) and low total suspended solids. The outcomes of coffee wastewater treatment using coagulation-flocculation and photodegradation processes were assessed in terms of reduction of COD, color, and turbidity. It was found that a reduction in COD of 67% could be realized when the coffee wastewater was treated by chemical coagulation-flocculation with lime and coagulant T-1. When coffee wastewater was treated by coagulation-flocculation in combination with UV/H2O2, a COD reduction of 86% was achieved, although only after prolonged UV irradiation. Of the three advanced oxidation processes considered, UV/H2O2, UV/O3 and UV/H2O2/O3, we found that the treatment with UV/H2O2/O3 was the most effective, with an efficiency of color, turbidity and further COD removal of 87%, when applied to the flocculated coffee wastewater. 展开更多
关键词 advanced oxidation processes coagulation-flocculation: coffee wastewater chemical oxygen demand (COD)
下载PDF
Petro-chemical wastewater treatment by biological process 被引量:6
8
作者 Guan, Wei-Sheng Lei, Zi-Xue Zhu, Jun-Huang 《Journal of Environmental Sciences》 SCIE EI CAS CSCD 2000年第2期95-99,共5页
In order to study the feasibility of treating petro chemical wastewater by the combination of anaerobic and aerobic biological process, a research of treating wastewater in UASB reactor and aeration basin has been co... In order to study the feasibility of treating petro chemical wastewater by the combination of anaerobic and aerobic biological process, a research of treating wastewater in UASB reactor and aeration basin has been conducted. The test results shows that under moderate temperature, with 5\^2 kgCOD/(m\+3·d) volumetric load of COD Cr in the UASB reactor and 24h of HRT, 85% removal rate of BOD 5 and 83% of COD \{Cr\} and 1\^34 m\+3/(m\+3·d) volumetric gas production rate can be obtained respectively. The aerobic bio degradability can be increased by 20%—30% after the petro chemical wastewater has been treated by anaerobic process. As Ns=0\^45 kgCOD/(kgMLSS·d), HRT=4h in the aeration tank, 94% removal rate of BOD 5, 93% of COD \{Cr\}, 98\^8% total removal rate of COD \{Cr\} and 99% removal rate of BOD 5 can be reached. 展开更多
关键词 anaerobic aerobic process petro chemical wastewater wastewater treatment CLC number: X703 Document code: A
下载PDF
Modeling and Optimization for Scheduling of Chemical Batch Processes 被引量:7
9
作者 钱宇 潘明 黄亚才 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2009年第1期1-7,共7页
Chemical batch processes have become significant in chemical manufacturing. In these processes, large numbers of chemical products are produced to satisfy human demands in daily life. Recently, economy globalization h... Chemical batch processes have become significant in chemical manufacturing. In these processes, large numbers of chemical products are produced to satisfy human demands in daily life. Recently, economy globalization has resulted, in growing worldwide competitions in tradi.tional chemical .process industry. In order to keep competitive in the global marketplace, each company must optimize its production management and set up a reactive system for market fluctuation. Scheduling is the core of production management in chemical processes. The goal of this paper is to review the recent developments in this challenging area. Classifications of batch scheduling problems and optimization methods are introduced. A comparison of six typical models is shown in a general benchmark example from the literature. Finally, challenges and applications in future research are discussed. 展开更多
关键词 chemical batch processes SCHEDULING optimization methods
下载PDF
SDG-based Model Validation in Chemical Process Simulation 被引量:7
10
作者 张贝克 许欣 +1 位作者 马昕 吴重光 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2013年第8期876-885,共10页
Signed direct graph (SDG) theory provides algorithms and methods that can be applied directly to chemical process modeling and analysis to validate simulation models, and is a basis for the development of a software e... Signed direct graph (SDG) theory provides algorithms and methods that can be applied directly to chemical process modeling and analysis to validate simulation models, and is a basis for the development of a software environment that can automate the validation activity. This paper is concentrated on the pretreatment of the model validation. We use the validation scenarios and standard sequences generated by well-established SDG model to validate the trends fitted from the simulation model. The results are helpful to find potential problems, assess possible bugs in the simulation model and solve the problem effectively. A case study on a simulation model of boiler is presented to demonstrate the effectiveness of this method. 展开更多
关键词 model validation signed direct graph chemical process qualitative trend
下载PDF
Integrated Assessment of Environmental and Economic Performance of Chemical Products Using Analytic Hierarchy Process Approach 被引量:9
11
作者 钱宇 黄智贤 闫志国 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2007年第1期81-87,共7页
With the increasing public consciousness on environmental issues, chemical products and process designs require simultaneous satisfaction and compromise of environmental and economical requirements. To fulfill the two... With the increasing public consciousness on environmental issues, chemical products and process designs require simultaneous satisfaction and compromise of environmental and economical requirements. To fulfill the two conflicting while complementary objectives, a systematic approach for life cycle design of a chemical product is proposed in this article. Multiattribute decision-making is adopted in a trade-off consideration of both technical economical evaluation and environmental impacts assessment using the analytic hierarchy process (AHP) approach. On the basis of an evaluation of the relative importance of the criteria multicriteria decision making is performed. In this study, an AHP model is used to derive single a criteria score by analyzing the environmental impact and life cycle cost of a product, respectively. And a fluctuant weight analysis is put forth to calculate the integrated index of the product to enable products to be ranked or selected intuitionally and conveniently. The proposed AHP model has been applied to a case study, a comparative study on chamber cleaning with NF3 and C2F6. The resuits show that the protposed AHP model is Capable of providing a rational and relevant evaluation. 展开更多
关键词 life cycle assessment life cycle cost analytic hierarchy process chemical product
下载PDF
Computational Mass Transfer Method for Chemical Process Simulation 被引量:10
12
作者 袁希钢 余国琮 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2008年第4期497-502,共6页
The recent works on the development of computational mass transfer (CMT) method and its applications in chemical process simulation are reviewed. Some development strategies and challenges in future research are als... The recent works on the development of computational mass transfer (CMT) method and its applications in chemical process simulation are reviewed. Some development strategies and challenges in future research are also discussed. 展开更多
关键词 computational mass transfer turbulent mass transfer diffusivity chemical process simulation
下载PDF
Microwave enhanced chemical reduction process for nitrite-containing wastewater treatment using sulfaminic acid 被引量:3
13
作者 Nan Li, Peng Wang, Qingsong Liu, Hailei Cao State Key Labaratory of Urban Water Resource and Environment, School of Municipal and Environmental Engineering, Harbin Institute of Technology, Harbin 150090, China 《Journal of Environmental Sciences》 SCIE EI CAS CSCD 2010年第1期56-61,共6页
High-concentration nitrite-containing wastewater that presents extreme toxicity to human health and organisms is difficult to be treated using traditional biological process. In this study, a novel microwave-enhanced ... High-concentration nitrite-containing wastewater that presents extreme toxicity to human health and organisms is difficult to be treated using traditional biological process. In this study, a novel microwave-enhanced chemical reduction process (MECRP) using sulfarninic acid (SA) was proposed as a new manner to treat such type of wastewater. Based on lab-scale experiments, it was shown that 75%-80% nitrite (NO2-) could be removed within time as short as 4 min under 50 W microwave irradiation in pH range 5-10 when molar ratio of SA to nitrite (SA/NO2-) was 0.8. Pilot-scale investigations demonstrated that MECRP was able to achieve nitrite and chemical oxygen demand (COD) removal with efficiency up to 80% and 20%, respectively under operating conditions of SA concentration 80 kg/m3, SA/NO2- ratio 0.8, microwave power 3.4 kW, and stirring time 3 min. Five-day biological oxygen demand (BODs)/COD value of treated effluent after MECRP was increased from 0.05 to 0.36 (by 620%), which clearly suggested a considerable improvement of biodegradability for subsequent biological treatment. This study provided a demonstration of using microwave irradiation to enhance reaction between SA and nitrite in a short time, in which nitrite in wastewater was completely converted into nitrogen gas without leaving any sludge and secondary pollutants. 展开更多
关键词 microwave-enhanced chemical reduction process nitrite-containing wastewater sulfaminic acid
下载PDF
A Hybrid Improved Genetic Algorithm and Its Application in Dynamic Optimization Problems of Chemical Processes 被引量:5
14
作者 SUN Fan DU Wenli QI Rongbin QIAN Feng ZHONG Weimin 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2013年第2期144-154,共11页
The solutions of dynamic optimization problems are usually very difficult due to their highly nonlinear and multidimensional nature. 13enetic algorithm (GA) has been proved to be a teasibte method when the gradient ... The solutions of dynamic optimization problems are usually very difficult due to their highly nonlinear and multidimensional nature. 13enetic algorithm (GA) has been proved to be a teasibte method when the gradient is difficult to calculate. Its advantage is that the control profiles at all time stages are optimized simultaneously, but its convergence is very slow in the later period of evolution and it is easily trapped in the local optimum. In this study, a hybrid improved genetic algorithm (HIGA) for solving dynamic optimization problems is proposed to overcome these defects. Simplex method (SM) is used to perform the local search in the neighborhood of the optimal solution. By using SM, the ideal searching direction of global optimal solution could be found as soon as possible and the convergence speed of the algorithm is improved. The hybrid algorithm presents some improvements, such as protecting the best individual, accepting immigrations, as well as employing adaptive crossover and Ganssian mutation operators. The efficiency of the proposed algorithm is demonstrated by solving several dynamic optimization problems. At last, HIGA is applied to the optimal production of secreted protein in a fed batch reactor and the optimal feed-rate found by HIGA is effective and relatively stable. 展开更多
关键词 genetic algorithm simplex method dynamic optimization chemical process
下载PDF
Dimensionality Reduction with Input Training Neural Network and Its Application in Chemical Process Modelling 被引量:8
15
作者 朱群雄 李澄非 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2006年第5期597-603,共7页
Many applications of principal component analysis (PCA) can be found in dimensionality reduction. But linear PCA method is not well suitable for nonlinear chemical processes. A new PCA method based on im-proved input ... Many applications of principal component analysis (PCA) can be found in dimensionality reduction. But linear PCA method is not well suitable for nonlinear chemical processes. A new PCA method based on im-proved input training neural network (IT-NN) is proposed for the nonlinear system modelling in this paper. Mo-mentum factor and adaptive learning rate are introduced into learning algorithm to improve the training speed of IT-NN. Contrasting to the auto-associative neural network (ANN), IT-NN has less hidden layers and higher training speed. The effectiveness is illustrated through a comparison of IT-NN with linear PCA and ANN with experiments. Moreover, the IT-NN is combined with RBF neural network (RBF-NN) to model the yields of ethylene and propyl-ene in the naphtha pyrolysis system. From the illustrative example and practical application, IT-NN combined with RBF-NN is an effective method of nonlinear chemical process modelling. 展开更多
关键词 chemical process modelling input training neural network nonlinear principal component analysis naphtha pyrolysis
下载PDF
A Strategy for Multi-objective Optimization under Uncertainty in Chemical Process Design 被引量:4
16
作者 孙力 Helen H.Lou 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2008年第1期39-42,共4页
In many circumstances, chemical process design can be formulated as a multi-objective optimization (MOO) problem. Examples include bi-objective optimization problems, where the economic objective is maximized and en... In many circumstances, chemical process design can be formulated as a multi-objective optimization (MOO) problem. Examples include bi-objective optimization problems, where the economic objective is maximized and environmental impact is minimized simultaneously. Moreover, the random behavior in the process,property, market fluctuation, errors in model prediction and so on would affect the performance of a process. Therefore, it is essential to develop a MOO methodology under uncertainty. In this article, the authors propose a generic and systematic optimization methodology for chemical process design under uncertainty. It aims at identifying the optimal design from a number of candidates. The utility of this methodology is demonstrated by a case study based on the design of a condensate treatment unit in an ammonia plant. 展开更多
关键词 multi-objective optimization UNCERTAINTY chemical process design
下载PDF
PCA weight and Johnson transformation based alarm threshold optimization in chemical processes 被引量:4
17
作者 Wende Tian Guixin Zhang +1 位作者 Xiang Zhang Yuxi Dong 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2018年第8期1653-1661,共9页
To alleviate the heavy load of massive alarm on operators, alarm threshold in chemical processes was optimized with principal component analysis(PCA) weight and Johnson transformation in this paper. First, few variabl... To alleviate the heavy load of massive alarm on operators, alarm threshold in chemical processes was optimized with principal component analysis(PCA) weight and Johnson transformation in this paper. First, few variables that have high PCA weight factors are chosen as key variables. Given a total alarm frequency to these variables initially, the allowed alarm number for each variable is determined according to their sampling time and weight factors. Their alarm threshold and then control limit percentage are determined successively. The control limit percentage of non-key variables is determined with 3σ method alternatively. Second, raw data are transformed into normal distribution data with Johnson function for all variables before updating their alarm thresholds via inverse transformation of obtained control limit percentage. Alarm thresholds are optimized by iterating this process until the calculated alarm frequency reaches standard level(normally one alarm per minute). Finally,variables and their alarm thresholds are visualized in parallel coordinate to depict their variation trends concisely and clearly. Case studies on a simulated industrial atmospheric-vacuum crude distillation demonstrate that the proposed alarm threshold optimization strategy can effectively reduce false alarm rate in chemical processes. 展开更多
关键词 Alarm threshold chemical process PCA Johnson transformation Variable weight
下载PDF
Characteristics of the subglacially-formed debris-rich chemical deposits and related subglacial processes of Qiangyong Glacier,Tibet 被引量:2
18
作者 LUO Risheng, CAO Jim, LIU Gengnian, GUI Zhijiu(College of Environmental Sciences, Peking University, Beijing 100871, China) 《Journal of Geographical Sciences》 SCIE CSCD 2003年第4期455-462,共8页
Subglacially-formed debris-rich chemical deposits were found both on bedrock surface and in bedrock crevice on the edge of Qiangyong Glacier, one of the continental glaciers in Tibet. Grain size distribution, internal... Subglacially-formed debris-rich chemical deposits were found both on bedrock surface and in bedrock crevice on the edge of Qiangyong Glacier, one of the continental glaciers in Tibet. Grain size distribution, internal structures and chemical components of the chemical deposits were analyzed. It can be inferred that the temperature of some part of the ice-bedrock interface is close to the melting point and there exists pressure melting water under Qiangyong Glacier. Debris, especially those from continental aerosols, can release Ca++ in the water. At the lee-side of obstacles on glacier bed the CO2 in the melting water might escape from the water and the melting water might refreeze due to the dramatically reduced pressure, making the enrichment and precipitation of CaCO3. The existence of subglacial melting water and the process of regelation under Qiangyong Glacier indicate that sliding could contribute some proportion to the entire movement of Qiangyong Glacier and it belongs to multiplex cold-temperate glaciers. 展开更多
关键词 Qiangyong Glacier Tibet subglacially-formed chemical deposits subglacial process continental glacier
下载PDF
Adaptive multiscale convolutional neural network model for chemical process fault diagnosis 被引量:3
19
作者 Ruoshi Qin Jinsong Zhao 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2022年第10期398-411,共14页
Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing.Due to the variations in material,equipment and environment,the process variables monitored by sensors contai... Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing.Due to the variations in material,equipment and environment,the process variables monitored by sensors contain diverse data characteristics at different time scales or in multiple operating modes.Despite much progress in statistical learning and deep learning for fault recognition,most models are constrained by abundant diagnostic expertise,inefficient multiscale feature extraction and unruly multimode condition.To overcome the above issues,a novel fault diagnosis model called adaptive multiscale convolutional neural network(AMCNN)is developed in this paper.A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data,embedding the adaptive attention module to adjust the selection of relevant fault pattern information.The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition.The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method.Compared with other common models,AMCNN shows its outstanding fault diagnosis performance and great generalization ability. 展开更多
关键词 Neural networks Multiscale Adaptive attentionmodule Triplet lossoptimization Fault diagnosis chemical processes
下载PDF
Identification of abnormal conditions in high-dimensional chemical process based on feature selection and deep learning 被引量:4
20
作者 Wende Tian Zijian Liu +2 位作者 Lening Li Shifa Zhang Chuankun Li 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2020年第7期1875-1883,共9页
Identification of abnormal conditions is essential in the chemical process.With the rapid development of artificial intelligence technology,deep learning has attracted a lot of attention as a promising fault identific... Identification of abnormal conditions is essential in the chemical process.With the rapid development of artificial intelligence technology,deep learning has attracted a lot of attention as a promising fault identification method in chemical process recently.In the high-dimensional data identification using deep neural networks,problems such as insufficient data and missing data,measurement noise,redundant variables,and high coupling of data are often encountered.To tackle these problems,a feature based deep belief networks(DBN)method is proposed in this paper.First,a generative adversarial network(GAN)is used to reconstruct the random and non-random missing data of chemical process.Second,the feature variables are selected by Spearman’s rank correlation coefficient(SRCC)from high-dimensional data to eliminate the noise and redundant variables and,as a consequence,compress data dimension of chemical process.Finally,the feature filtered data is deeply abstracted,learned and tuned by DBN for multi-case fault identification.The application in the Tennessee Eastman(TE)process demonstrates the fast convergence and high accuracy of this proposal in identifying abnormal conditions for chemical process,compared with the traditional fault identification algorithms. 展开更多
关键词 chemical process Deep Belief Networks Fault identification Generative Adversarial Networks Spearman Rank Correlation
下载PDF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部