This page has only limited features, please log in for full access.
Process fault is one of the main reasons that a system may appear unreliable, and it affects the safety of a system. The existence of different degrees of noise in the industry also makes it difficult to extract the effective features of the data for the fault diagnosis method based on deep learning. In order to solve the above problems, this paper improves the deep belief network (DBN) and iterates the optimal penalty term by introducing a penalty factor, avoiding the local optimal situation of a DBN and improving the accuracy of fault diagnosis in order to minimize the impact of noise while improving fault diagnosis and process safety. Using the adaptive noise reduction capability of an adaptive lifting wavelet (ALW), a practical chemical process fault diagnosis model (ALW-DBN) is finally proposed. Then, according to the Tennessee–Eastman (TE) benchmark test process, the ALW-DBN model is compared with other methods, showing that the fault diagnosis performance of the enhanced DBN combined with adaptive wavelet denoising has been significantly improved. In addition, the ALW-DBN shows better performance under the influence of different noise levels in the acid gas absorption process, which proves its high adaptability to different noise levels.
Yuman Yao; Jiaxin Zhang; Wenjia Luo; Yiyang Dai. A Hybrid Intelligent Fault Diagnosis Strategy for Chemical Processes Based on Penalty Iterative Optimization. Processes 2021, 9, 1266 .
AMA StyleYuman Yao, Jiaxin Zhang, Wenjia Luo, Yiyang Dai. A Hybrid Intelligent Fault Diagnosis Strategy for Chemical Processes Based on Penalty Iterative Optimization. Processes. 2021; 9 (8):1266.
Chicago/Turabian StyleYuman Yao; Jiaxin Zhang; Wenjia Luo; Yiyang Dai. 2021. "A Hybrid Intelligent Fault Diagnosis Strategy for Chemical Processes Based on Penalty Iterative Optimization." Processes 9, no. 8: 1266.
Hydrogen management is very important for the production of clean fuels such as low-sulfur gasoline and diesel. As a key contaminant in the hydrogen network, hydrogen sulfide not only deactivates catalysts but also corrodes equipments. Hence, it is necessary to integrate hydrogen sulfide removal process model into the optimization of hydrogen allocation network. However, a desulfurization process model with simplifications and assumptions may yield suboptimal results and a model based on rigorous process mechanism may require high computational cost. To solve this problem, this paper proposes a novel approach for simultaneous optimization of refinery hydrogen allocation network and hydrogen sulfide removal processes. The optimization is realized in two steps. First, surrogate models are developed as approximations to the rigorous process and thermodynamic model for the desulfurization processes. Second, the surrogate model is embedded into the mathematical programming model for hydrogen network optimization. The effectiveness of the proposed approach is illustrated by its application to a case study taken from a real refinery. Result comparison between the proposed method and a literature model based on simplified desulfurization models is carried out, proving that, with the proposed method, more practical optimization result can be obtained with much less computational effort.
Zhipeng Xia; Shihui Wang; Li Zhou; Yiyang Dai; Yagu Dang; Xu Ji. Surrogate-assisted optimization of refinery hydrogen networks with hydrogen sulfide removal. Journal of Cleaner Production 2021, 310, 127477 .
AMA StyleZhipeng Xia, Shihui Wang, Li Zhou, Yiyang Dai, Yagu Dang, Xu Ji. Surrogate-assisted optimization of refinery hydrogen networks with hydrogen sulfide removal. Journal of Cleaner Production. 2021; 310 ():127477.
Chicago/Turabian StyleZhipeng Xia; Shihui Wang; Li Zhou; Yiyang Dai; Yagu Dang; Xu Ji. 2021. "Surrogate-assisted optimization of refinery hydrogen networks with hydrogen sulfide removal." Journal of Cleaner Production 310, no. : 127477.
Considering that compressive strength (CS) is an important mechanical property parameter in many design codes, in order to ensure structural safety, concrete CS needs to be tested before application. However, conducting CS tests with multiple influencing variables is costly and time-consuming. To address this issue, a machine learning-based modeling framework is put forward in this work to evaluate the concrete CS under complex conditions. The influential factors of this process are systematically categorized into five aspects: man, machine, material, method and environment (4M1E). A genetic algorithm (GA) was applied to identify the most important influential factors for CS modeling, after which, random forest (RF) was adopted as the modeling algorithm to predict the CS from the selected influential factors. The effectiveness of the proposed model was tested on a case study, and the high Pearson correlation coefficient (0.9821) and the low mean absolute percentage error and delta (0.0394 and 0.395, respectively) indicate that the proposed model can deliver accurate and reliable results.
Jiajia Xu; Li Zhou; Ge He; Xu Ji; Yiyang Dai; Yagu Dang. Comprehensive Machine Learning-Based Model for Predicting Compressive Strength of Ready-Mix Concrete. Materials 2021, 14, 1068 .
AMA StyleJiajia Xu, Li Zhou, Ge He, Xu Ji, Yiyang Dai, Yagu Dang. Comprehensive Machine Learning-Based Model for Predicting Compressive Strength of Ready-Mix Concrete. Materials. 2021; 14 (5):1068.
Chicago/Turabian StyleJiajia Xu; Li Zhou; Ge He; Xu Ji; Yiyang Dai; Yagu Dang. 2021. "Comprehensive Machine Learning-Based Model for Predicting Compressive Strength of Ready-Mix Concrete." Materials 14, no. 5: 1068.
This study considers the problem of distinguishing between process and sensor faults in nonlinear chemical processes. An integrated fault diagnosis framework is proposed to distinguish chemical process sensor faults from process faults. The key idea of the framework is to embed the cycle temporal algorithm into the dynamic kernel principal component analysis to improve the fault detection speed and accuracy. It is combined with the fault diagnosis method based on the reconstruction-based contribution graph to diagnose the fault variables and then distinguish the two fault types according to their characteristics. Finally, the integrated fault diagnosis framework is applied to the Tennessee Eastman process and acid gas absorption process, and its effectiveness is proved.
Jiaxin Zhang; Wenjia Luo; Yiyang Dai. Integrated Diagnostic Framework for Process and Sensor Faults in Chemical Industry. Sensors 2021, 21, 822 .
AMA StyleJiaxin Zhang, Wenjia Luo, Yiyang Dai. Integrated Diagnostic Framework for Process and Sensor Faults in Chemical Industry. Sensors. 2021; 21 (3):822.
Chicago/Turabian StyleJiaxin Zhang; Wenjia Luo; Yiyang Dai. 2021. "Integrated Diagnostic Framework for Process and Sensor Faults in Chemical Industry." Sensors 21, no. 3: 822.
The mechanism models based on structure-oriented lumping (SOL) deliver a satisfactory prediction on the properties and yield distribution of the products from fluid catalytic cracking (FCC). However, with high complexity and low computing efficiency, such a model is increasingly unable to meet the needs of refineries to produce lighter and greener products using heavier and poorer feedstocks. Therefore, in this paper, a modeling approach hybridizing molecular mechanism and data models was proposed to describe the maximizing iso-paraffins (MIP) technology of the FCC process. This proposed model showed assured prediction accuracy with shortened computing time and thus was appropriate for online application. In this work, model simplification was carried out: less molecules and reactions (3078 and 5216, respectively) were adopted, along with a simplified reactor model, which largely reduced the computation load. CatBoost algorithm was also adopted for constructing a data model, to compensate for the accuracy loss resulting from the simplified SOL mechanism model. Combining with the mechanism model, it ensured the accuracy of prediction while greatly shortened the computing time. Furthermore, to overcome the strong coupling between the process variables to be solved, this work adopted the method of case-based reasoning (CBR) to optimize the process and expanded the case base with the prediction results of the hybrid model, which ensured the feasibility of the solution parameters and shortened the computing time. The hybrid model and the corresponding process optimization strategy proposed were then applied to an industrial FCC MIP process for verification. The results show that the hybrid model could assure the prediction accuracy (comparable with the conventional mechanism model) while the computing time was reduced from more than 20 h to less than 1 min. In the process optimization validation test, the total liquid yield increased by 1.19% on average for 43 out of 50 sets of operating configurations and the coke yield decreased by 1.05% on average. This work provides a good solution for the online process optimization of FCC.
Ge He; Chenglin Zhou; Tao Luo; Li Zhou; Yiyang Dai; Yagu Dang; Xu Ji. Online Optimization of Fluid Catalytic Cracking Process via a Hybrid Model Based on Simplified Structure-Oriented Lumping and Case-Based Reasoning. Industrial & Engineering Chemistry Research 2020, 60, 412 -424.
AMA StyleGe He, Chenglin Zhou, Tao Luo, Li Zhou, Yiyang Dai, Yagu Dang, Xu Ji. Online Optimization of Fluid Catalytic Cracking Process via a Hybrid Model Based on Simplified Structure-Oriented Lumping and Case-Based Reasoning. Industrial & Engineering Chemistry Research. 2020; 60 (1):412-424.
Chicago/Turabian StyleGe He; Chenglin Zhou; Tao Luo; Li Zhou; Yiyang Dai; Yagu Dang; Xu Ji. 2020. "Online Optimization of Fluid Catalytic Cracking Process via a Hybrid Model Based on Simplified Structure-Oriented Lumping and Case-Based Reasoning." Industrial & Engineering Chemistry Research 60, no. 1: 412-424.
To improve integration and achieve better coal industry materials and energy balance, integrated collaborative supply chains (SCs) are needed. However, as single-core SC models are not suitable for complex coal industry systems, a multicore, correlated, conditional SC model, called a supply chain network (SCN), is proposed. SCN collaborative evaluation models are discussed including industrial metabolic balance (IMB), enterprise profitability, contract execution ability and information interaction ability, for which IMB is used as the efficiency index of resource coordination of SCN, also as the constraints of the models on system levels. Further, data modeling by using BP-ANN algorithm is used to predict the profitability of supply chain network. Finally, the feasibility of the above models is illustrated by cases. The proposed evaluation models in this paper form the scientific and quantitative evaluation method of SC, which could be used for both SC planning and operations management helping detect and eliminate risks.
Ge He; Li Zhou; Yiyang Dai; Yagu Dang; Xu Ji. Coal Industrial Supply Chain Network and Associated Evaluation Models. Sustainability 2020, 12, 9919 .
AMA StyleGe He, Li Zhou, Yiyang Dai, Yagu Dang, Xu Ji. Coal Industrial Supply Chain Network and Associated Evaluation Models. Sustainability. 2020; 12 (23):9919.
Chicago/Turabian StyleGe He; Li Zhou; Yiyang Dai; Yagu Dang; Xu Ji. 2020. "Coal Industrial Supply Chain Network and Associated Evaluation Models." Sustainability 12, no. 23: 9919.
Excessive CO2 content will reduce the natural gas calorific value and increase the energy consumption of the regenerator in natural gas desulfurization and decarbonization. This paper uses Aspen HYSYS to model a novel two-stage flash process of acid gas removal process from natural gas. According to the results from the simulation, as well as running experiences in a natural gas processing plant in the middle east, it can be demonstrated that this new process, which has been used in the field of natural gas desulfurization and decarbonization, can meet the requirement of product specifications. Based on the steady state simulation, Aspen HYSYS sensitivity function is used to evaluate influence of key operating parameters, such as the second flash pressure and temperature, on the energy consumption. Compared to the traditional acid gas removal process and acid gas enrichment process, the new two-stage flash acid gas removal process has less energy consumption (2.2 × 109 kJ·h−1). In addition, two-stage flash acid gas removal process also improves the efficiency of acid gas enrichment, while the overall energy consumption is less than combination process of traditional process and acid gas enrichment process.
Yiyang Dai; Yuwei Peng; Yi Qiu; Huimin Liu. Techno-Economic Analysis of a Novel Two-Stage Flashing Process for Acid Gas Removal from Natural Gas. Energies 2019, 12, 4213 .
AMA StyleYiyang Dai, Yuwei Peng, Yi Qiu, Huimin Liu. Techno-Economic Analysis of a Novel Two-Stage Flashing Process for Acid Gas Removal from Natural Gas. Energies. 2019; 12 (21):4213.
Chicago/Turabian StyleYiyang Dai; Yuwei Peng; Yi Qiu; Huimin Liu. 2019. "Techno-Economic Analysis of a Novel Two-Stage Flashing Process for Acid Gas Removal from Natural Gas." Energies 12, no. 21: 4213.
Yi Qiu; Yiyang Dai. A Stacked Auto-Encoder Based Fault Diagnosis Model for Chemical Process. 16th European Symposium on Computer Aided Process Engineering and 9th International Symposium on Process Systems Engineering 2019, 1303 -1308.
AMA StyleYi Qiu, Yiyang Dai. A Stacked Auto-Encoder Based Fault Diagnosis Model for Chemical Process. 16th European Symposium on Computer Aided Process Engineering and 9th International Symposium on Process Systems Engineering. 2019; ():1303-1308.
Chicago/Turabian StyleYi Qiu; Yiyang Dai. 2019. "A Stacked Auto-Encoder Based Fault Diagnosis Model for Chemical Process." 16th European Symposium on Computer Aided Process Engineering and 9th International Symposium on Process Systems Engineering , no. : 1303-1308.
Intelligent evaluation system has been widely used in industries to estimate essential indexes which are unable to be measured directly through physical devices. Due to the complexity of labeling samples, common data-driven techniques such as supervised learning are developed on a small number of labeled data, while a large amount of unlabeled data is discarded. The amount of labeled information greatly limits the improvement of prediction accuracies. Furthermore, conventional evaluation approaches have only static structures, which makes the dynamic characteristics of parameters difficult to be presented. This paper proposes a ladder network (LN) based semi-supervised learning model to evaluate parameter dynamics, and a case of remaining useful life (RUL) prediction for centrifugal pumps is illustrated. LN datasets comprise a small part of labeled data and a large amount of unlabeled data. We exploited fluid-structure interaction (FSI) numerical simulation to replace actual monitoring, as well as built a RUL prediction model to annotate useful life for offline datasets. After that, the RUL was performed in the online stage by substituting real-time monitored variables into the network. The case study indicates that the LN-based intelligent evaluation system identifies the real-time RUL profile and achieves better predictive outcomes than supervised learning approaches.
Rui He; Yiyang Dai; Jiachen Lu; Chuanlin Mou. Developing ladder network for intelligent evaluation system: Case of remaining useful life prediction for centrifugal pumps. Reliability Engineering & System Safety 2018, 180, 385 -393.
AMA StyleRui He, Yiyang Dai, Jiachen Lu, Chuanlin Mou. Developing ladder network for intelligent evaluation system: Case of remaining useful life prediction for centrifugal pumps. Reliability Engineering & System Safety. 2018; 180 ():385-393.
Chicago/Turabian StyleRui He; Yiyang Dai; Jiachen Lu; Chuanlin Mou. 2018. "Developing ladder network for intelligent evaluation system: Case of remaining useful life prediction for centrifugal pumps." Reliability Engineering & System Safety 180, no. : 385-393.
Fault diagnosis is one of the most important methods to ensure the safety of chemical process. With the development of artificial intelligences, many new methods have been introduced into the research of process fault diagnosis in chemical devices. Dynamic artificial immune system (DAIS) is one of the artificial intelligence methodologies with strong ability of self-learning and self-adaptability. However, in traditional AIS-based fault diagnosis strategies, key variables used in antibody cloning phase like total number of antibodies and mutation parameters are determined by experience. In this paper, we propose an approach for faulty antibody library construction in DAIS. Fault antibodies were classified into different types by different fault mechanism, and the size of antibody and mutation parameters of each faulty type were optimized individually. The performance of the modified DAIS-based fault diagnosis strategies is illustrated through the benchmarked Tennessee Eastman process.
Yiyang Dai; Yi Qiu; Ziyun Feng. Research on faulty antibody library of dynamic artificial immune system for fault diagnosis of chemical process. 16th European Symposium on Computer Aided Process Engineering and 9th International Symposium on Process Systems Engineering 2018, 44, 493 -498.
AMA StyleYiyang Dai, Yi Qiu, Ziyun Feng. Research on faulty antibody library of dynamic artificial immune system for fault diagnosis of chemical process. 16th European Symposium on Computer Aided Process Engineering and 9th International Symposium on Process Systems Engineering. 2018; 44 ():493-498.
Chicago/Turabian StyleYiyang Dai; Yi Qiu; Ziyun Feng. 2018. "Research on faulty antibody library of dynamic artificial immune system for fault diagnosis of chemical process." 16th European Symposium on Computer Aided Process Engineering and 9th International Symposium on Process Systems Engineering 44, no. : 493-498.
For the chemical process industry, the goal of Smart Manufacturing should not only maximize economic competitiveness, but also significantly reduce safety incidents. Therefore safety risk intelligence (SRI) should be an essential feature for smart chemical process operation. Abnormal situation management (ASM) of chemical processes has been studied for more than two decades with the aim to gain and utilize the operational intelligence for handling complex abnormal situations which are difficult for operators to detect and prevent. This paper provides an overview on the methods of ASM with SRI. Following a brief introduction of risk assessment methods, different approaches for controlling and mitigating risks of chemical processes, equipment and human operators are reviewed. Finally, future directions and challenges associated with each area of ASM are discussed before the conclusion.
Yiyang Dai; Hangzhou Wang; Faisal Khan; Jinsong Zhao. Abnormal situation management for smart chemical process operation. Current Opinion in Chemical Engineering 2016, 14, 49 -55.
AMA StyleYiyang Dai, Hangzhou Wang, Faisal Khan, Jinsong Zhao. Abnormal situation management for smart chemical process operation. Current Opinion in Chemical Engineering. 2016; 14 ():49-55.
Chicago/Turabian StyleYiyang Dai; Hangzhou Wang; Faisal Khan; Jinsong Zhao. 2016. "Abnormal situation management for smart chemical process operation." Current Opinion in Chemical Engineering 14, no. : 49-55.
Jinsong Zhao; Yidan Shu; Jianfeng Zhu; Yiyang Dai. An Online Fault Diagnosis Strategy for Full Operating Cycles of Chemical Processes. Industrial & Engineering Chemistry Research 2013, 53, 5015 -5027.
AMA StyleJinsong Zhao, Yidan Shu, Jianfeng Zhu, Yiyang Dai. An Online Fault Diagnosis Strategy for Full Operating Cycles of Chemical Processes. Industrial & Engineering Chemistry Research. 2013; 53 (13):5015-5027.
Chicago/Turabian StyleJinsong Zhao; Yidan Shu; Jianfeng Zhu; Yiyang Dai. 2013. "An Online Fault Diagnosis Strategy for Full Operating Cycles of Chemical Processes." Industrial & Engineering Chemistry Research 53, no. 13: 5015-5027.
Fault diagnosis is important for ensuring chemical processes stability and safety. The strong nonlinearity and complexity of batch chemical processes make such diagnosis more difficult than that for continuous processes. In this paper, a new fault diagnosis methodology is proposed for batch chemical processes, based on an artificial immune system (AIS) and dynamic time warping (DTW) algorithm. The system generates diverse antibodies using known normal and fault samples and calculates the difference between the test data and the antibodies by the DTW algorithm. If the difference for an antibody is lower than a threshold, then the test data are deemed to be of the same type of this antibody’s fault. Its application to a simulated penicillin fermentation process demonstrates that the proposed AIS can meet the requirements for online dynamic fault diagnosis of batch processes and can diagnose new faults through self-learning. Compared with dynamic locus analysis and artificial neural networks, the proposed method has better capability in fault diagnosis of batch processes, especially when the number of historical fault samples is limited.
Yiyang Dai; Jinsong Zhao. Fault Diagnosis of Batch Chemical Processes Using a Dynamic Time Warping (DTW)-Based Artificial Immune System. Industrial & Engineering Chemistry Research 2011, 50, 4534 -4544.
AMA StyleYiyang Dai, Jinsong Zhao. Fault Diagnosis of Batch Chemical Processes Using a Dynamic Time Warping (DTW)-Based Artificial Immune System. Industrial & Engineering Chemistry Research. 2011; 50 (8):4534-4544.
Chicago/Turabian StyleYiyang Dai; Jinsong Zhao. 2011. "Fault Diagnosis of Batch Chemical Processes Using a Dynamic Time Warping (DTW)-Based Artificial Immune System." Industrial & Engineering Chemistry Research 50, no. 8: 4534-4544.