The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
Jinsong Zhao - One of the best experts on this subject based on the ideXlab platform.
-
a new unsupervised data mining method based on the stacked autoencoder for Chemical Process fault diagnosis
Computers & Chemical Engineering, 2020Co-Authors: Shaodong Zheng, Jinsong ZhaoAbstract:Abstract Process monitoring plays an important role in Chemical Process safety management, and fault diagnosis is a vital step of Process monitoring. Among fault diagnosis researches, supervised ones are inappropriate for industrial applications due to the lack of labeled historical data in real situations. Thereby, unsupervised methods which are capable of dealing with unlabeled data should be developed for fault diagnosis. In this work, a new unsupervised data mining method based on deep learning is proposed for isolating different conditions of Chemical Process, including normal operations and faults, and thus labeled database can be created efficiently for constructing fault diagnosis model. The proposed method mainly consists of three steps: feature extraction by the convolutional stacked autoencoder (SAE), feature visualization by the t-distributed stochastic neighbor embedding (t-SNE) algorithm, and clustering. The benchmark Tennessee Eastman Process (TEP) and an industrial hydrocracking instance are utilized to illustrate the effectiveness of the proposed data mining method.
-
deep convolutional neural network model based Chemical Process fault diagnosis
Computers & Chemical Engineering, 2018Co-Authors: Hao Wu, Jinsong ZhaoAbstract:Abstract Numerous accidents in Chemical Processes have caused emergency shutdowns, property losses, casualties and/or environmental disruptions in the Chemical Process industry. Fault detection and diagnosis (FDD) can help operators timely detect and diagnose abnormal situations, and take right actions to avoid adverse consequences. However, FDD is still far from widely practical applications. Over the past few years, deep convolutional neural network (DCNN) has shown excellent performance on machine-learning tasks. In this paper, a fault diagnosis method based on a DCNN model consisting of convolutional layers, pooling layers, dropout, fully connected layers is proposed for Chemical Process fault diagnosis. The benchmark Tennessee Eastman (TE) Process is utilized to verify the outstanding performance of the fault diagnosis method.
-
Abnormal situation management for smart Chemical Process operation
Current Opinion in Chemical Engineering, 2016Co-Authors: Yiyang Dai, Hangzhou Wang, Faisal Khan, Jinsong ZhaoAbstract: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.
-
an integrated quantitative index of stable steady state points in Chemical Process design
Computer-aided chemical engineering, 2012Co-Authors: Hangzhou Wang, H E Xiaorong, Bingzhen Chen, Tong Qiu, Jinsong ZhaoAbstract:Abstract In order to design inherently safer Chemical Processes, researchers proposed many methods and strategies, many quantitative indices have been developed to describe the potential hazard and dangerous of different reaction routes and reactants. Because in emergency situation the disturbance may be so large that the system can not return back to the steady state points. For considering both situations under small and large disturbances, this paper proposed a quantitative index (QI), in which disturbance range index (RI) and convergence speed index (SI) were integrated, considering both capability of resistance to disturbances and speed to return to steady state point. Based on the integrated index, this paper proposed an approach for designing a more stable Chemical Process that can maintain stable within larger region to resist the disturbance and has shorter time to approach to the original stable steady state operation point when disturbance is encountered. The approach is applied to methyl methacrylate polymerization Process and a multi-objective optimization problem considering both economic and stability factors were conducted and a Pareto set is obtained.
D W Edwards - One of the best experts on this subject based on the ideXlab platform.
-
assessing the inherent atmospheric environmental friendliness of Chemical Process routes an unsteady state distribution approach for a catastrophic release
Computers & Chemical Engineering, 2006Co-Authors: M Y Gunasekera, D W EdwardsAbstract:Abstract The inherent environmental friendliness of a Chemical Process plant is assessed quantitatively based on its short-term atmospheric impacts due to a catastrophic release of the entire inventory of Chemicals. In a catastrophic release of Chemicals the environment into which the Chemical is distributed will change with time. Therefore, it is important to account for these model environment changes in the Chemical distribution method used when estimating short-term impacts. This paper proposes a method that uses the dispersion characteristics of the Chemical in the atmospheric environment to estimate the model environmental volumes. Its distribution within this environment, between the different compartments such as air, soil or water is considered to estimate the predicted environmental concentrations (PEC). These values are then used in an index called the atmospheric hazard index (AHI) which assesses the inherent environmental friendliness of the Chemical Process plant. These AHI results are compared with those estimated by a method that uses the unit world model environment to estimate PEC values.
-
Chemical Process route selection based on assessment of inherent environmental hazard
Computers & Chemical Engineering, 1997Co-Authors: S R Cave, D W EdwardsAbstract:Abstract At the preliminary stages of Chemical plant development and design the choice of the Chemical Process route is the key design decision. In the past, economics were the most important criterion in choosing the Chemical Process route. Safety and environmental issues have now become important considerations. Methods are lacking for assessing Chemical Process routes for environmental friendliness. The Environmental Hazard Index (EHI) ranks routes by the estimated environmental impact of a total release of Chemical inventory. The EHI is a function of the environmental effects of the Chemicals and the estimated inventory thereof in a plant that, if designed and built, would implement the route. The lower the EHI the more environmentally friendly is the route. The EHI has been tested on six potential and established routes to Methyl Methacrylate (MMA). These results have been compared with those for the Inherent Safety Index for the same Chemical Process routes. An expression has been derived which relates the EHI to an estimated fish kill.
S K Mallick - One of the best experts on this subject based on the ideXlab platform.
-
pollution prevention with Chemical Process simulators the generalized waste reduction war algorithm full version
Computers & Chemical Engineering, 1999Co-Authors: Heriberto Cabezas, Jane C Bare, S K MallickAbstract:A general theory for the flow and the generation of potential environmental impact through a Chemical Process has been developed. The theory defines six potential environmental impact indexes that characterize the generation of potential impact within a Process, and the output of potential impact from a Process. The indexes are used to quantify pollution reduction and to develop pollution reducing changes to Process flow sheets using Process simulators. The potential environmental impacts are calculated from stream mass flow rates, stream composition, and a relative potential environmental impact score for each Chemical present. The Chemical impact scores include a comprehensive set of nine effects ranging from ozone depletion potential to human toxicity and ecotoxicity. The resulting waste reduction methodology or WAR algorithm is illustrated with two case studies using the Chemical Process simulator Chemcad III (Use does not imply USEPA endorsement or approval of Chemcad III).
-
pollution prevention with Chemical Process simulators the generalized waste reduction war algorithm
Computers & Chemical Engineering, 1997Co-Authors: Heriberto Cabezas, Jane C Bare, S K MallickAbstract:A general theory for the flow and the generation of potential environmental impact through a Chemical Process has been developed. The theory defines six potential impact indexes that characterize the generation of potential impact within a Process, and the output of potential impact from a Process. The indexes are used to quantify and to guide pollution reduction with changes to Process flow sheets using Process simulators. The potential environmental impacts are calculated from stream mass flow rates, stream composition, and a relative potential impact score for each Chemical present. The Chemical impact scores include a comprehensive set of nine effects ranging from ozone depletion potential to human toxicity and ecotoxicity. The resulting Waste Reduction methodology or WAR Algorithm is illustrated with a case study using the Chemical Process simulator Chemcad III (Does not imply USEPA endorsement of Chemcad III).
Heriberto Cabezas - One of the best experts on this subject based on the ideXlab platform.
-
pollution prevention with Chemical Process simulators the generalized waste reduction war algorithm full version
Computers & Chemical Engineering, 1999Co-Authors: Heriberto Cabezas, Jane C Bare, S K MallickAbstract:A general theory for the flow and the generation of potential environmental impact through a Chemical Process has been developed. The theory defines six potential environmental impact indexes that characterize the generation of potential impact within a Process, and the output of potential impact from a Process. The indexes are used to quantify pollution reduction and to develop pollution reducing changes to Process flow sheets using Process simulators. The potential environmental impacts are calculated from stream mass flow rates, stream composition, and a relative potential environmental impact score for each Chemical present. The Chemical impact scores include a comprehensive set of nine effects ranging from ozone depletion potential to human toxicity and ecotoxicity. The resulting waste reduction methodology or WAR algorithm is illustrated with two case studies using the Chemical Process simulator Chemcad III (Use does not imply USEPA endorsement or approval of Chemcad III).
-
pollution prevention with Chemical Process simulators the generalized waste reduction war algorithm
Computers & Chemical Engineering, 1997Co-Authors: Heriberto Cabezas, Jane C Bare, S K MallickAbstract:A general theory for the flow and the generation of potential environmental impact through a Chemical Process has been developed. The theory defines six potential impact indexes that characterize the generation of potential impact within a Process, and the output of potential impact from a Process. The indexes are used to quantify and to guide pollution reduction with changes to Process flow sheets using Process simulators. The potential environmental impacts are calculated from stream mass flow rates, stream composition, and a relative potential impact score for each Chemical present. The Chemical impact scores include a comprehensive set of nine effects ranging from ozone depletion potential to human toxicity and ecotoxicity. The resulting Waste Reduction methodology or WAR Algorithm is illustrated with a case study using the Chemical Process simulator Chemcad III (Does not imply USEPA endorsement of Chemcad III).
Christos T Maravelias - One of the best experts on this subject based on the ideXlab platform.
-
an optimization based approach for simultaneous Chemical Process and heat exchanger network synthesis
Industrial & Engineering Chemistry Research, 2018Co-Authors: Lingxun Kong, Christos T MaraveliasAbstract:We propose a mixed-integer nonlinear programming (MINLP) model for simultaneous Chemical Process and heat exchanger network synthesis. The model allows Process stream inlet/outlet temperatures and flow rates to vary and can be extended to handle unclassified streams, thereby facilitating integration with a Process synthesis model. The proposed model is based on a generalized transshipment approach in which the heat cascade is built upon a “dynamic” temperature grid. Both hot and cold streams can cascade heat so that exchanger inlet and outlet temperature, heat duty, and area can be calculated at each temperature interval. We develop mixed-integer constraints to model the number of heat exchangers in the network. Finally, we present several solution strategies tailored to improve the computation performance of the proposed models.
-
simultaneous Chemical Process synthesis and heat integration with unclassified hot cold Process streams
Computers & Chemical Engineering, 2017Co-Authors: Lingxun Kong, Venkatachalam Avadiappan, Kefeng Huang, Christos T MaraveliasAbstract:Abstract We propose a mixed-integer nonlinear programming (MINLP) model for the simultaneous Chemical Process synthesis and heat integration with unclassified Process streams. The model accounts for (1) streams that cannot be classified as hot or cold, and (2) variable stream temperatures and flow rates, thereby facilitating integration with a Process synthesis model. The hot/cold stream “identities” are represented by classification binary variables which are (de)activated based on the relative stream inlet and outlet temperatures. Variables including stream temperatures and heat loads are disaggregated into hot and cold variables, and each variable is (de)activated by the corresponding classification binary variable. Stream inlet/outlet temperatures are positioned onto “dynamic” temperature intervals so that heat loads at each interval can be properly calculated. The proposed model is applied to two illustrative examples with variable stream flow rates and temperatures, and is integrated with a superstructure-based Process synthesis model to illustrate its applicability.