A Systematic Design of Emulators for Multivariable Non Square and Nonlinear Systems

In this paper, multimodel and neural emulators are proposed for uncoupled multivariable nonlinear plants with unknown dynamics. The contributions of this paper are to extend the emulators to multivariable non square systems and to propose a systematic method to compute the multimodel synthesis parameters. The effectiveness of the proposed emulators is shown through two simulation examples. The obtained results are very satisfactory, they illustrate the performance of both emulators and show the advantages of the multimodel emulator relatively to the neural one.

Intelligent Multivariable Modeling of Blast Furnace Molten Iron Quality Based on Dynamic AGA-ANN and PCA

Blast furnace （BF） ironmaking process has complex and nonlinear dynamic characteristics. The molten iron temperature （MIT） as well as Si, P and S contents of molten iron is difficult to be directly measured online, and large-time delay exists in offline analysis through laboratory sampling. A nonlinear multivariate intelligent modeling method was proposed for molten iron quality （MIQ） based on principal component analysis （PCA） and dynamic ge- netic neural network. The modeling method used the practical data processed by PCA dimension reduction as inputs of the dynamic artificial neural network （ANN）. A dynamic feedback link was introduced to produce a dynamic neu- ral network on the basis of traditional back propagation ANN. The proposed model improved the dynamic adaptabili- ty of networks and solved the strong fluctuation and resistance problem in a nonlinear dynamic system. Moreover, a new hybrid training method was presented where adaptive genetic algorithms （AGA） and ANN were integrated, which could improve network convergence speed and avoid network into local minima. The proposed method made it easier for operators to understand the inside status of blast furnace and offered real-time and reliable feedback infor- mation for realizing close-loop control for MIQ. Industrial experiments were made through the proposed model based on data collected from a practical steel company. The accuracy could meet the requirements of actual operation.

LEARNING GRANGER CAUSALITY GRAPHS FOR MULTIVARIATE NONLINEAR TIME SERIES

An information theory method is proposed to test the. Granger causality and contemporaneous conditional independence in Granger causality graph models. In the graphs, the vertex set denotes the component series of the multivariate time series, and the directed edges denote causal dependence, while the undirected edges reflect the instantaneous dependence. The presence of the edges is measured by a statistics based on conditional mutual information and tested by a permutation procedure. Furthermore, for the existed relations, a statistics based on the difference between general conditional mutual information and linear conditional mutual information is proposed to test the nonlinearity. The significance of the nonlinear test statistics is determined by a bootstrap method based on surrogate data. We investigate the finite sample behavior of the procedure through simulation time series with different dependence structures, including linear and nonlinear relations.

Unknown fault detection for EGT multi-temperature signals based on self-supervised feature learning and unary classification

Intelligent tpower systems scanimprove operational efficiency by installing a large number of sensors.Data-based methods of supervised learning have gained popularity because of available Big Data and computing resources.However,the common paradigm of the loss function in supervised learning requires large amounts of labeled data and cannot process unlabeled data.The scarcity of fault data and a large amount of normal data in practical use pose great challenges to fault detection algorithms.Moreover,sensor data faults in power systems are dynamically changing and pose another challenge.Therefore,a fault detection method based on self-supervised feature learning was proposed to address the above two challenges.First,self-supervised learning was employed to extract features under various working conditions only using large amounts of normal data.The self-supervised representation learning uses a sequence-based Triplet Loss.The extracted features of large amounts of normal data are then fed into a unary classifier.The proposed method is validated on exhaust gas temperatures(EGTs)of a real-world 9F gas turbine with sudden,progressive,and hybrid faults.A comprehensive comparison study was also conducted with various feature extractors and unary classifiers.The results show that the proposed method can achieve a relatively high recall for all kinds of typical faults.The model can detect progressive faults very quickly and achieve improved results for comparison without feature extractors in terms ofF1 score.

Modified artificial neural network model with an explicit expression to describe flow behavior and processing maps of Ti2AlNb-based superalloy

The elevated-temperature deformation behavior of Ti2AlNb superalloy was observed by isothermal compression experiments in a wide range of temperatures(950–1200°C)and strain rates(0.001–10 s^(-1)).The flow behavior is nonlinear,strongly coupled,and multivariable.The constitutive models,namely the double multivariate nonlinear regression model,artificial neural network model,and modified artificial neural network model with an explicit expression,were applied to describe the Ti2AlNb superalloy plastic deformation behavior.The comparative predictability of those constitutive models was further evaluated by considering the correlation coefficient and average absolute relative error.The comparative results show that the modified artificial network model can describe the flow stress of Ti2AlNb superalloy more accurately than the other developed constitutive models.The explicit expression obtained from the modified artificial neural network model can be directly used for finite element simulation.The modified artificial neural network model solves the problems that the double multivariate nonlinear regression model cannot describe the nonlinear,strongly coupled,and multivariable flow behavior of Ti2AlNb superalloy accurately,and the artificial neural network model cannot be embedded into the finite element software directly.However,the modified artificial neural network model is mainly dependent on the quantity of high-quality experimental data and characteristic variables,and the modified artificial neural network model has not physical meanings.Besides,the processing maps were applied to obtain the optimum processing parameters.