dynamic information is a non-negligible part of time-correlated process data, and its full utilization can improve the performance of faultdetection. Traditional dynamic methods concatenate the current process data w...
详细信息
dynamic information is a non-negligible part of time-correlated process data, and its full utilization can improve the performance of faultdetection. Traditional dynamic methods concatenate the current process data with a certain number of previous process data into an extended vector before performing feature extraction. However, this simple way of using dynamic information inevitably increases the input dimensionality and it is inappropriate to treat previous process data as equally important. To address these problems, this paper proposes a novel nonlinear dynamic method, called graph dynamic autoencoder (GDAE), for faultdetection. GDAE utilizes a graph structure to model the dynamic information between different data points. GDAE firstly embeds the current data point and previous data points as the features of the central node and its neighbors, respectively, then convolves the feature of the central node with the features of its neighbors to derive the updated feature for the central node, and finally, an encoder-decoder structure is adopted to extract the key low-dimensional feature. Due to the utilization of the graph structure, the extended high-dimensional vectors utilized by traditional dynamic fault detection methods are avoided in GDAE. Furthermore, with the dynamically constructed graph, GDAE is able to adaptively assign different weights to its neighbors by updating the adjacency matrix of the graph. Experimental results obtained from a numerical simulation and the Tennessee Eastman process illustrate the superiority of GDAE in terms of missed detection rate (MDR) and false alarm rate (FAR). The source code of GDAE can be found in https://***/luliu-fighting/Graph-dynamic-Autoencoder. (c) 2022 Elsevier Ltd. All rights reserved.
作者：
Ge, ZhiqiangChen, XinruZhejiang Univ
State Key Lab Ind Control Technol Inst Ind Proc Control Coll Control Sci & Engn Hangzhou 310027 Zhejiang Peoples R China
dynamic and uncertainty are two main features of industrial processes data which should be paid attentions when carrying out process monitoring and fault diagnosis. As a typical dynamic Bayesian network model, linear ...
详细信息
dynamic and uncertainty are two main features of industrial processes data which should be paid attentions when carrying out process monitoring and fault diagnosis. As a typical dynamic Bayesian network model, linear dynamic system (LDS) can efficiently deal with both dynamic and uncertain features of the process data. However, the quality information has been ignored by the LDS model, which could serve as a supervised term for information extraction and faultdetection. In this paper, a supervised form of the LDS model is developed, which can successfully incorporate the information of quality variables. With this additional data information, the new supervised LDS model can provide a quality related faultdetection scheme for dynamic processes. A detailed industrial case study on the Tennessee Eastman benchmark process is carried out for performance evaluation of the developed method. (C) 2016 Elsevier Ltd. All rights reserved.
dynamic vehicle routing problems have received increasing attention in the literature due to the rapid IT evolution as well as advances in computing and modelling techniques. In areas subject to critical and often unp...
详细信息
dynamic vehicle routing problems have received increasing attention in the literature due to the rapid IT evolution as well as advances in computing and modelling techniques. In areas subject to critical and often unpredictable traffic congestions, logistics operators often allocate excessive number of collecting tasks to their vehicles, generating unperformed activities due to OEM JIT time constraints and thus violating contractual obligations assumed with their clients. In this paper, a dynamic OEM picking-up (milk-run) routing problem is analysed, in which tasks that likely will exceed the time limit in a route are assigned to supplementary vehicles, thus forming auxiliary dynamic routes formed with the transferred tasks originated from the regular trucks. To solve the problem, a genetic algorithm model was developed in association with a simulation program intended to define some relevant probabilistic parameters. The results have shown that the dynamic formulation considerably improves the service level when compared with the static version. (C) 2015 Elsevier Ltd. All rights reserved.
Based on a dynamic neuron model - the so called dynamic Elementary Processor (DEP) - a dynamic multi layer perceptron neural net (DMLP) is applied to identify black box models of the process. The dynamic adaption algo...
详细信息
ISBN:
(纸本)0780321294
Based on a dynamic neuron model - the so called dynamic Elementary Processor (DEP) - a dynamic multi layer perceptron neural net (DMLP) is applied to identify black box models of the process. The dynamic adaption algorithm is briefly introduced and compared to other adaption procedures. However, the identified models are used to build the first step of a fault diagnosis scheme (FDS) similar to observer based schemes. The residuals between the measured process output and the outputs estimated by the bank models are used as numerical symptoms for the faultdetection and diagnosis. The FDS was successfully applied to monitor the turbine state of a turbosupercharger.
作者：
M. AyoubiTechnical University of Darmstadt
Inst. of Automatic Control Laboratory of Control Engineering and Process Automation Landgraf-Georg 4 64283 Darmstadt Germany
An attempt has been made to establish a nonlinear dynamic time discrete neuron model, the so called dynamic Elementary Processor (DEP). This DEP disposes of local memory, in that it has dynamic states. Based on the DE...
详细信息
An attempt has been made to establish a nonlinear dynamic time discrete neuron model, the so called dynamic Elementary Processor (DEP). This DEP disposes of local memory, in that it has dynamic states. Based on the DEP neuron, a dynamic Multi Layer Perceptron neural net (MLP) is proposed to identify nonparametric, multi-input single-output (MISO) models for nonlinear, dynamic systems. The identified models are used to build a bank similar to observer based schemes. The output residuals between the process and the bank models are used to detect and identify a fault in the process, if it has occurred. An empirical MISO model for the turbine of a turbosupercharger was identified to demonstrate the identification ability of the proposed DEP net with real data. The faultdetection scheme was successfully applied to detect and diagnose a transient fault in the turbine waste gate.
暂无评论