Data-Driven Model Identification and Control of the Inertial Systems

In the synthesis of the control algorithm for complex systems, we are often faced with imprecise or unknown mathematical models of the dynamical systems, or even with problems in finding a mathematical model of the system in the open loop. To tackle these difficulties, an approach of data-driven model identification and control algorithm design based on the maximum stability degree criterion is proposed in this paper. The data-driven model identification procedure supposes the finding of the mathematical model of the system based on the undamped transient response of the closed-loop system. The system is approximated with the inertial model, where the coefficients are calculated based on the values of the critical transfer coefficient, oscillation amplitude and period of the underdamped response of the closed-loop system. The data driven control design supposes that the tuning parameters of the controller are calculated based on the parameters obtained from the previous step of system identification and there are presented the expressions for the calculation of the tuning parameters. The obtained results of data-driven model identification and algorithm for synthesis the controller were verified by computer simulation.

Pollution source identification methods and remediation technologies of groundwater: A review

Groundwater is an important source of drinking water.Groundwater pollution severely endangers drinking water safety and sustainable social development.In the case of groundwater pollution,the top priority is to identify pollution sources,and accurate information on pollution sources is the premise of efficient remediation.Then,an appropriate pollution remediation scheme should be developed according to information on pollution sources,site conditions,and economic costs.The methods for identifying pollution sources mainly include geophysical exploration,geochemistry,isotopic tracing,and numerical modeling.Among these identification methods,only the numerical modeling can recognize various information on pollution sources,while other methods can only identify a certain aspect of pollution sources.The remediation technologies of groundwater can be divided into in-situ and ex-situ remediation technologies according to the remediation location.The in-situ remediation technologies enjoy low costs and a wide remediation range,but their remediation performance is prone to be affected by environmental conditions and cause secondary pollution.The ex-situ remediation technologies boast high remediation efficiency,high processing capacity,and high treatment concentration but suffer high costs.Different methods for pollution source identification and remediation technologies are applicable to different conditions.To achieve the expected identification and remediation results,it is feasible to combine several methods and technologies according to the actual hydrogeological conditions of contaminated sites and the nature of pollutants.Additionally,detailed knowledge about the hydrogeological conditions and stratigraphic structure of the contaminated site is the basis of all work regardless of the adopted identification methods or remediation technologies.

Data-driven casting defect prediction model for sand casting based on random forest classification algorithm

The complex sand-casting process combined with the interactions between process parameters makes it difficult to control the casting quality,resulting in a high scrap rate.A strategy based on a data-driven model was proposed to reduce casting defects and improve production efficiency,which includes the random forest(RF)classification model,the feature importance analysis,and the process parameters optimization with Monte Carlo simulation.The collected data includes four types of defects and corresponding process parameters were used to construct the RF model.Classification results show a recall rate above 90% for all categories.The Gini Index was used to assess the importance of the process parameters in the formation of various defects in the RF model.Finally,the classification model was applied to different production conditions for quality prediction.In the case of process parameters optimization for gas porosity defects,this model serves as an experimental process in the Monte Carlo method to estimate a better temperature distribution.The prediction model,when applied to the factory,greatly improved the efficiency of defect detection.Results show that the scrap rate decreased from 10.16% to 6.68%.

PEMFC Identification Based on a Fractional-Order Hammerstein State-Space Model with ADE-BH Optimization

Considering the fractional-order and nonlinear characteristics of proton exchange membrane fuel cells(PEMFC),a fractional-order subspace identification method based on the ADE-BH optimization algorithm is proposed to establish a fractional-order Hammerstein state-space model of PEMFCs.Herein,a Hammerstein model is constructed by connecting a linear module and a nonlinear module in series to precisely depict the nonlinear property of the PEMFC.During the modeling process,fractional-order theory is combined with subspace identification,and a Poisson filter is adopted to enable multi-order derivability of the data.A variable memory method is introduced to reduce computation time without losing precision.Additionally,to improve the optimization accuracy and avoid obtaining locally optimum solutions,a novel ADEBH algorithm is employed to optimize the unknown parameters in the identification method.In this algorithm,the Euclidean distance serves as the theoretical basis for updating the target vector in the absorption-generation operation of the black hole(BH)algorithm.Finally,simulations demonstrate that the proposed model has small output error and high accuracy,indicating that the model can accurately describe the electrical characteristics of the PEMFC process.

Closed-Loop System Identification Approach of the Inertial Models

The mathematical model that approximates the dynamics of the industrial process is essential for the efficient synthesis of control algorithms in industrial applications. The model of the process can be obtained according to the identification procedures in the open-loop, or in the closed-loop. In the open-loop, the identification methods are well known and offer good process approximation, which is not valid for the closed-loop identification, when the system provides the feedback output and doesn’t permit it to be identified in the open-loop. This paper offers an approach for experimental identification in the closed-loop, which supposes the approximation of the process with inertial models, with or without time delay and astatism. The coefficients are calculated based on the values of the critical transfer coefficient and period of the underdamped response of the closed-loop system with P controller, when system achieves the limit of stability. Finally, the closed-loop identification was verified by the computer simulation and the obtained results demonstrated, that the identification procedure in the closed-loop offers good results in process of estimation of the model of the process.

Identification of Mixtures of Two Types of Body Fluids Using the Multiplex Methylation System and Random Forest Models

Objective Body fluid mixtures are complex biological samples that frequently occur in crime scenes,and can provide important clues for criminal case analysis.DNA methylation assay has been applied in the identification of human body fluids,and has exhibited excellent performance in predicting single-source body fluids.The present study aims to develop a methylation SNaPshot multiplex system for body fluid identification,and accurately predict the mixture samples.In addition,the value of DNA methylation in the prediction of body fluid mixtures was further explored.Methods In the present study,420 samples of body fluid mixtures and 250 samples of single body fluids were tested using an optimized multiplex methylation system.Each kind of body fluid sample presented the specific methylation profiles of the 10 markers.Results Significant differences in methylation levels were observed between the mixtures and single body fluids.For all kinds of mixtures,the Spearman’s correlation analysis revealed a significantly strong correlation between the methylation levels and component proportions(1:20,1:10,1:5,1:1,5:1,10:1 and 20:1).Two random forest classification models were trained for the prediction of mixture types and the prediction of the mixture proportion of 2 components,based on the methylation levels of 10 markers.For the mixture prediction,Model-1 presented outstanding prediction accuracy,which reached up to 99.3%in 427 training samples,and had a remarkable accuracy of 100%in 243 independent test samples.For the mixture proportion prediction,Model-2 demonstrated an excellent accuracy of 98.8%in 252 training samples,and 98.2%in 168 independent test samples.The total prediction accuracy reached 99.3%for body fluid mixtures and 98.6%for the mixture proportions.Conclusion These results indicate the excellent capability and powerful value of the multiplex methylation system in the identification of forensic body fluid mixtures.

A Novel Method in Wood Identification Based on Anatomical Image Using Hybrid Model

Nowadays,wood identification is made by experts using hand lenses,wood atlases,and field manuals which take a lot of cost and time for the training process.The quantity and species must be strictly set up,and accurate identification of the wood species must be made during exploitation to monitor trade and enforce regulations to stop illegal logging.With the development of science,wood identification should be supported with technology to enhance the perception of fairness of trade.An automatic wood identification system and a dataset of 50 commercial wood species from Asia are established,namely,wood anatomical images collected and used to train for the proposed model.In the convolutional neural network(CNN),the last layers are usually soft-max functions with dense layers.These layers contain the most parameters that affect the speed model.To reduce the number of parameters in the last layers of the CNN model and enhance the accuracy,the structure of the model should be optimized and developed.Therefore,a hybrid of convolutional neural network and random forest model(CNN-RF model)is introduced to wood identification.The accuracy’s hybrid model is more than 98%,and the processing speed is 3 times higher than the CNN model.The highest accuracy is 1.00 in some species,and the lowest is 0.92.These results show the excellent adaptability of the hybrid model in wood identification based on anatomical images.It also facilitates further investigations of wood cells and has implications for wood science.

Interpersonal Perception in Virtual Groups: Examining Homophily, Identification and Individual Attraction Using Social Relations Model in Network

With the penetration of the Internet, virtual groups have become more and more popular. The reliability and accuracy of interpersonal perception in the virtual environment is an intriguing issue. Using the Social relations model (SRM) [1], this paper investigates interpersonal perception in virtual groups from a multilevel perspective. In particular, it examines the following three areas: homophily, identification, and individual attraction, and explores how much of these directional and dyadic relational evaluations can be attributed to the effect of the actor, the partner, and the relationship.

Comprehensive security risk factor identification for small reservoirs with heterogeneous data based on grey relational analysis model

Identification of security risk factors for small reservoirs is the basis for implementation of early warning systems.The manner of identification of the factors for small reservoirs is of practical significance when data are incomplete.The existing grey relational models have some disadvantages in measuring the correlation between categorical data sequences.To this end,this paper introduces a new grey relational model to analyze heterogeneous data.In this study,a set of security risk factors for small reservoirs was first constructed based on theoretical analysis,and heterogeneous data of these factors were recorded as sequences.The sequences were regarded as random variables,and the information entropy and conditional entropy between sequences were measured to analyze the relational degree between risk factors.Then,a new grey relational analysis model for heterogeneous data was constructed,and a comprehensive security risk factor identification method was developed.A case study of small reservoirs in Guangxi Zhuang Autonomous Region in China shows that the model constructed in this study is applicable to security risk factor identification for small reservoirs with heterogeneous and sparse data.

Identification and nonlinear model predictive control of MIMO Hammerstein system with constraints

This work is concerned with identification and nonlinear predictive control method for MIMO Hammerstein systems with constraints. Firstly, an identification method based on steady-state responses and sub-model method is introduced to MIMO Hammerstein system. A modified version of artificial bee colony algorithm is proposed to improve the prediction ability of Hammerstein model. Next, a computationally efficient nonlinear model predictive control algorithm(MGPC) is developed to deal with constrained problem of MIMO system. The identification process and performance of MGPC are shown. Numerical results about a polymerization reactor validate the effectiveness of the proposed method and the comparisons show that MGPC has a better performance than QDMC and basic GPC.

Data-driven intelligent modeling framework for the steam cracking process

Steam cracking is the dominant technology for producing light olefins,which are believed to be the foundation of the chemical industry.Predictive models of the cracking process can boost production efficiency and profit margin.Rapid advancements in machine learning research have recently enabled data-driven solutions to usher in a new era of process modeling.Meanwhile,its practical application to steam cracking is still hindered by the trade-off between prediction accuracy and computational speed.This research presents a framework for data-driven intelligent modeling of the steam cracking process.Industrial data preparation and feature engineering techniques provide computational-ready datasets for the framework,and feedstock similarities are exploited using k-means clustering.We propose LArge-Residuals-Deletion Multivariate Adaptive Regression Spline(LARD-MARS),a modeling approach that explicitly generates output formulas and eliminates potentially outlying instances.The framework is validated further by the presentation of clustering results,the explanation of variable importance,and the testing and comparison of model performance.

Shale gas production evaluation framework based on data-driven models

Increasing the production and utilization of shale gas is of great significance for building a clean and low-carbon energy system.Sharp decline of gas production has been widely observed in shale gas reservoirs.How to forecast shale gas production is still challenging due to complex fracture networks,dynamic fracture properties,frac hits,complicated multiphase flow,and multi-scale flow as well as data quality and uncertainty.This work develops an integrated framework for evaluating shale gas well production based on data-driven models.Firstly,a comprehensive dominated-factor system has been established,including geological,drilling,fracturing,and production factors.Data processing and visualization are required to ensure data quality and determine final data set.A shale gas production evaluation model is developed to evaluate shale gas production levels.Finally,the random forest algorithm is used to forecast shale gas production.The prediction accuracy of shale gas production level is higher than 95%based on the shale gas reservoirs in China.Forty-one wells are randomly selected to predict cumulative gas production using the optimal regression model.The proposed shale gas production evaluation frame-work overcomes too many assumptions of analytical or semi-analytical models and avoids huge computation cost and poor generalization for numerical modelling.

System Identification and Parameter Self-Tuning Controller on Deep-Sea Mining Vehicle

System identification is a quintessential measure for real-time analysis on kinematic characteristics for deep-sea mining vehicle, and thus to enhance the control performance and testing efficiency. In this study, the system identification algorithm, recursive least square method with instrumental variables(IV-RLS), is tailored to model ‘Pioneer I’, a deep-sea mining vehicle which recently completed a 1305-meter-deep sea trial in the Xisha area of the South China Sea in August, 2021. The algorithm operates on the sensor data collected from the trial to obtain the vehicle’s kinematic model and accordingly design the parameter self-tuning controller. The performances demonstrate the accuracy of the model, and prove its generalization capability. With this model, the optimal controller has been designed, the control parameters have been self-tuned, and the response time and robustness of the system have been optimized,which validates the high efficiency on digital modelling for precision control of deep-sea mining vehicles.

STPGTN-AMulti-Branch Parameters Identification Method Considering Spatial Constraints and Transient Measurement Data

Transmission line(TL)Parameter Identification(PI)method plays an essential role in the transmission system.The existing PI methods usually have two limitations:(1)These methods only model for single TL,and can not consider the topology connection of multiple branches for simultaneous identification.(2)Transient bad data is ignored by methods,and the random selection of terminal section data may cause the distortion of PI and have serious consequences.Therefore,a multi-task PI model considering multiple TLs’spatial constraints and massive electrical section data is proposed in this paper.The Graph Attention Network module is used to draw a single TL into a node and calculate its influence coefficient in the transmission network.Multi-Task strategy of Hard Parameter Sharing is used to identify the conductance ofmultiple branches simultaneously.Experiments show that themethod has good accuracy and robustness.Due to the consideration of spatial constraints,the method can also obtain more accurate conductance values under different training and testing conditions.

Augmented Industrial Data-Driven Modeling Under the Curse of Dimensionality

The curse of dimensionality refers to the problem o increased sparsity and computational complexity when dealing with high-dimensional data.In recent years,the types and vari ables of industrial data have increased significantly,making data driven models more challenging to develop.To address this prob lem,data augmentation technology has been introduced as an effective tool to solve the sparsity problem of high-dimensiona industrial data.This paper systematically explores and discusses the necessity,feasibility,and effectiveness of augmented indus trial data-driven modeling in the context of the curse of dimen sionality and virtual big data.Then,the process of data augmen tation modeling is analyzed,and the concept of data boosting augmentation is proposed.The data boosting augmentation involves designing the reliability weight and actual-virtual weigh functions,and developing a double weighted partial least squares model to optimize the three stages of data generation,data fusion and modeling.This approach significantly improves the inter pretability,effectiveness,and practicality of data augmentation in the industrial modeling.Finally,the proposed method is verified using practical examples of fault diagnosis systems and virtua measurement systems in the industry.The results demonstrate the effectiveness of the proposed approach in improving the accu racy and robustness of data-driven models,making them more suitable for real-world industrial applications.

PARAMETER IDENTIFICATION OF DYNAMIC MODELS USING A BAYES APPROACH

The Bayesian method of statistical analysis has been applied to the parameter identification problem. A method is presented to identify parameters of dynamic models with the Bayes estimators of measurement frequencies. This is based on the solution of an inverse generalized eigenvalue problem. The stochastic nature of test data is considered and a normal distribution is used for the measurement frequencies. An additional feature is that the engineer’s confidence in the measurement frequencies is quantified and incorporated into the identification procedure. A numerical example demonstrates the efficiency of the method.

Pattern-Moving-Based Parameter Identification of Output Error Models with Multi-Threshold Quantized Observations

This paper addresses a modified auxiliary model stochastic gradient recursive parameter identification algorithm(M-AM-SGRPIA)for a class of single input single output(SISO)linear output error models with multi-threshold quantized observations.It proves the convergence of the designed algorithm.A pattern-moving-based system dynamics description method with hybrid metrics is proposed for a kind of practical single input multiple output(SIMO)or SISO nonlinear systems,and a SISO linear output error model with multi-threshold quantized observations is adopted to approximate the unknown system.The system input design is accomplished using the measurement technology of random repeatability test,and the probabilistic characteristic of the explicit metric value is employed to estimate the implicit metric value of the pattern class variable.A modified auxiliary model stochastic gradient recursive algorithm(M-AM-SGRA)is designed to identify the model parameters,and the contraction mapping principle proves its convergence.Two numerical examples are given to demonstrate the feasibility and effectiveness of the achieved identification algorithm.

Deep learning-based activity recognition and fine motor identification using 2D skeletons of cynomolgus monkeys

Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and prediction.However,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized assessment.In this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton features.Furthermore,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in monkeys.Using the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual detection.Mon Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.

Research on Plant Species Identification Based on Improved Convolutional Neural Network

Plant species recognition is an important research area in image recognition in recent years.However,the existing plant species recognition methods have low recognition accuracy and do not meet professional requirements in terms of recognition accuracy.Therefore,ShuffleNetV2 was improved by combining the current hot concern mechanism,convolution kernel size adjustment,convolution tailoring,and CSP technology to improve the accuracy and reduce the amount of computation in this study.Six convolutional neural network models with sufficient trainable parameters were designed for differentiation learning.The SGD algorithm is used to optimize the training process to avoid overfitting or falling into the local optimum.In this paper,a conventional plant image dataset TJAU10 collected by cell phones in a natural context was constructed,containing 3000 images of 10 plant species on the campus of Tianjin Agricultural University.Finally,the improved model is compared with the baseline version of the model,which achieves better results in terms of improving accuracy and reducing the computational effort.The recognition accuracy tested on the TJAU10 dataset reaches up to 98.3%,and the recognition precision reaches up to 93.6%,which is 5.1%better than the original model and reduces the computational effort by about 31%compared with the original model.In addition,the experimental results were evaluated using metrics such as the confusion matrix,which can meet the requirements of professionals for the accurate identification of plant species.

Model identification with BPNN on restrictive ecological factors of SRB for sulfate-reduction

The model of back-propagation neural network (BPNN) was presented to demonstrate the effect of restrictive ecological factors, COD/SO 4 2- ratio, pH value, alkalinity (ALK) and SO 4 2- loading rate (Ns), on sulfate reduction of Sulfate Reducing Bacteria (SRB) in an acidogenic sulfate reducing reactor supplied with molasses as sole organic carbon source and sodium sulfate as electron acceptor. The compare of experimental results and computer simulation was also discussed. It was shown that the method of BPNN had a powerful ability to analyze the ecological characteristic of acidogenic sulfate reducing ecosystem quantitatively.