Peri-Net-Pro: the neural processes with quantified uncertainty for crack patterns

This paper develops a deep learning tool based on neural processes(NPs)called the Peri-Net-Pro,to predict the crack patterns in a moving disk and classifies them according to the classification modes with quantified uncertainties.In particular,image classification and regression studies are conducted by means of convolutional neural networks(CNNs)and NPs.First,the amount and quality of the data are enhanced by using peridynamics to theoretically compensate for the problems of the finite element method(FEM)in generating crack pattern images.Second,case studies are conducted with the prototype microelastic brittle(PMB),linear peridynamic solid(LPS),and viscoelastic solid(VES)models obtained by using the peridynamic theory.The case studies are performed to classify the images by using CNNs and determine the suitability of the PMB,LBS,and VES models.Finally,a regression analysis is performed on the crack pattern images with NPs to predict the crack patterns.The regression analysis results confirm that the variance decreases when the number of epochs increases by using the NPs.The training results gradually improve,and the variance ranges decrease to less than 0.035.The main finding of this study is that the NPs enable accurate predictions,even with missing or insufficient training data.The results demonstrate that if the context points are set to the 10th,100th,300th,and 784th,the training information is deliberately omitted for the context points of the 10th,100th,and 300th,and the predictions are different when the context points are significantly lower.However,the comparison of the results of the 100th and 784th context points shows that the predicted results are similar because of the Gaussian processes in the NPs.Therefore,if the NPs are employed for training,the missing information of the training data can be supplemented to predict the results.

Joint device architecture algorithm codesign of the photonic neural processing unit

The photonic neural processing unit(PNPU)demonstrates ultrahigh inference speed with low energy consumption,and it has become a promising hardware artificial intelligence(AI)accelerator.However,the nonidealities of the photonic device and the peripheral circuit make the practical application much more complex.Rather than optimizing the photonic device,the architecture,and the algorithm individually,a joint device-architecture-algorithm codesign method is proposed to improve the accuracy,efficiency and robustness of the PNPU.First,a full-flow simulator for the PNPU is developed from the back end simulator to the high-level training framework;Second,the full system architecture and the complete photonic chip design enable the simulator to closely model the real system;Third,the nonidealities of the photonic chip are evaluated for the PNPU design.The average test accuracy exceeds 98%,and the computing power exceeds 100TOPS.

Time series prediction using wavelet process neural network

In the real world, the inputs of many complicated systems are time-varying functions or processes. In order to predict the outputs of these systems with high speed and accuracy, this paper proposes a time series prediction model based on the wavelet process neural network, and develops the corresponding learning algorithm based on the expansion of the orthogonal basis functions. The effectiveness of the proposed time series prediction model and its learning algorithm is proved by the Macke-Glass time series prediction, and the comparative prediction results indicate that the proposed time series prediction model based on the wavelet process neural network seems to perform well and appears suitable for using as a good tool to predict the highly complex nonlinear time series.

Batch Process Modelling and Optimal Control Based on Neural Network Model

This paper presents several neural network based modelling, reliable optimal control, and iterative learning control methods for batch processes. In order to overcome the lack of robustness of a single neural network, bootstrap aggregated neural networks are used to build reliable data based empirical models. Apart from improving the model generalisation capability, a bootstrap aggregated neural network can also provide model prediction confidence bounds. A reliable optimal control method by incorporating model prediction confidence bounds into the optimisation objective function is presented. A neural network based iterative learning control strategy is presented to overcome the problem due to unknown disturbances and model-plant mismatches. The proposed methods are demonstrated on a simulated batch polymerisation process.

An Integrated Use of Advanced T2 Statistics and Neural Network and Genetic Algorithm in Monitoring Process Disturbance

Integrated use of statistical process control (SPC) and engineering process control (EPC) has better performance than that by solely using SPC or EPC. But integrated scheme has resulted in the problem of “Window of Opportunity” and autocorrelation. In this paper, advanced T2 statistics model and neural networks scheme are combined to solve the above problems: use T2 statistics technique to solve the problem of autocorrelation;adopt neural networks technique to solve the problem of “Window of Opportunity” and identification of disturbance causes. At the same time, regarding the shortcoming of neural network technique that its algorithm has a low speed of convergence and it is usually plunged into local optimum easily. Genetic algorithm was proposed to train samples in this paper. Results of the simulation ex-periments show that this method can detect the process disturbance quickly and accurately as well as identify the dis-turbance type.

Hybrid Neural Network Model for RH Vacuum Refining Process Control

A hybrid neural network model,in which RH process(theoretical)model is combined organically with neural network(NN)and case-base reasoning(CBR),was established.The CBR method was used to select the operation mode and the RH operational guide parameters for different steel grades according to the initial conditions of molten steel,and a three-layer BP neural network was adopted to deal with nonlinear factors for improving and compensating the limitations of technological model for RH process control and end-point prediction.It was verified that the hybrid neural network is effective for improving the precision and calculation efficiency of the model.

A Sensor Failure Detection Method Based on Artificial Neural Network and Signal Processing

This paper proposes a sensor failure detection method based on artificial neural network and signal processing,in comparison with other methods,which does not need any redundancy information among sensor outputs and divides the output of a sensor into'Signal dominant component'and'Noise dominant component'because the pattern of sensor failure often appears in the'Noise dominant component'.With an ARMA model built for'Noise dominant component'using artificial neural network,such sensor failures as bias failure,hard failure,drift failure,spike failure and cyclic failure may be detected through residual analysis,and the type of sensor failure can be indicated by an appropriate indicator.The failure detection procedure for a temperature sensor in a hovercraft engine is simulated to prove the applicability of the method proposed in this paper.

Neural regeneration after peripheral nerve injury repair is a system remodelling process of interaction between nerves and terminal effector

In China, there are approximately 20 million people suffering from peripheral nerve injury and this number is increasing at a rate of 2 million per year. These patients cannot live or work independently and are a heavy responsibility on both family and society because of extreme disability and dysfunction caused by peripheral nerve injury （PNI）. Thus, repair of PNI has become a major public health issue in China.

ANALYSIS AND DESIGN OF A NEURAL CHIP USED FOR BINARY IMAGE PROCESSING

Based on the model of a formal neuron proposed by McCulloch and Pitts,a kind ofneural circuit,which is a CMOS Variable Threshold Logic(VTL)circuit,is given in this paperconsidering the features of the binary image processing system.The theoretical analysis,andthe simulations for the building block circuits such as D/A converters,comparator and so on aregiven.The layout design of the whole circuit are also given.The binary image processing can berealized by using the VTL circuit combined with its external auxiliary circuits.

Prediction of Pitting Corrosion Mass Loss for 304 Stainless Steel by Image Processing and BP Neural Network

Image processing technique was employed to analyze pitting corrosion morphologies of 304 stainless steel exposed to FeCl3 environments. BP neural network models were developed for the prediction of pitting corrosion mass loss using the obtained data of the total and the average pit areas which were extracted from pitting binary image. The results showed that the predicted results obtained by the 2-5-1 type BP neural network model are in good agreement with the experimental data of pitting corrosion mass loss. The maximum relative error of prediction is 6.78%.

Neural Network Modeling and System Simulating for the Dynamic Process of Varied Gap Pulsed GTAW with Wire Filler

As the base of the research work on the weld shape control during pulsed gas tungsten arc welding （GTAW） with wire filler, this paper addressed the modeling of the dynamic welding process. Topside length Lt, maximum width Wt and half-length ratio Rh1 were selected to depict topside weld pool shape, and were measured on-line by vision sensing. A dynamic neural network model was constructed to predict the usually unmeasured backside width and topside height of the weld through topside shape parameters and welding parameters. The inputs of the model were the welding parameters （peak current, pulse duty ratio, welding speed, filler rate）, the joint gap, the topside pool shape parameters （Lt, Wt, and Rh1）, and their history values at two former pulse, a total of 24 numbers. The validating experiment results proved that the artificial neural network （ANN） model had high precision and could be used in process control. At last, with the developed dynamic model, steady and dynamic behavior was analyzed by simulation experiments, which discovered the variation rules of weld pool shape parameters under different welding parameters, and further knew well the characteristic of the welding process.

Artificial neural networks applied to spot welding process modeling

Artificial neural networks have been studied for applicability for modeling of spot welding process. Some basic concepts relating to neural networks are explained as well as how they can be used to model welding qualitv parameters in terms of the welding process parameter. The performance of the neural networks for modeling is presented and evaluated using actual welding data. It is concluded that neural network modeling is a good means of estimating spot welding quality on-line.

A Review: Artificial Neural Networks as Tool for Control Food Industry Process

In the last year, interest in using Artificial Neural networks as a modeling tool in food technology is increasing because they have found extensive utilization in solving many complex real world problems. Due to this and as previous step at development of some project, this paper intends to introduce the reader inside neural networks: general characteristics of the ANN, their architectures, their rules of learning, types of networks and ANN’s create process. Also this paper presents a comprehensive review of food industrial applications of artificial neural networks in the last year. ANN industrial applications are grouped and tabulated by their main functions and what they actually performed on the referenced papers with except the applications in the olive oil industry that are described with special emphasis.

Neural network modeling for dynamic pulsed GTAW process with wire filler based on MATLAB

Double-sided weld pool shapes were determined by multiple welding parameters and wire feed parameters during pulsed GTAW with wire filler. Aiming at such a system with multiple inputs and outputs, an effective modeling method, consisting of the impulse signal design, model structure and parameter identification and verification, was developed based on MATLAB software. Then, dynamic neural network models, TDNNM (Topside dynamic neural network model) and BHDNNM (Backside width and topside height dynamic neural network model), were established to predict double-sided shape parameters of the weld pool. The characteristic relationship of the welding process was simulated and analyzed with the models.

Optimization of Processing Parameters of Power Spinning for Bushing Based on Neural Network and Genetic Algorithms

A neural network model of key process parameters and forming quality is developed based on training samples which are obtained from the orthogonal experiment and the finite element numerical simulation. Optimization of the process parameters is conducted using the genetic algorithm (GA). The experimental results have shown that a surface model of the neural network can describe the nonlinear implicit relationship between the parameters of the power spinning process:the wall margin and amount of expansion. It has been found that the process of determining spinning technological parameters can be accelerated using the optimization method developed based on the BP neural network and the genetic algorithm used for the process parameters of power spinning formation. It is undoubtedly beneficial towards engineering applications.

Simulation of aging process of lead frame copper alloy by an artificial neural network

The aging hardening process makes it possible to get higher hardness and electrical conductivity of lead frame copper alloy. The process has only been studied empirically by trial-and-error method so far. The use of a supervised artificial neural network(ANN) was proposed to model the non-linear relationship between parameters of aging process with respect to hardness and conductivity properties of Cu-Cr-Zr alloy. The improved model was developed by the Levenberg-Marquardt training algorithm. A basic repository on the domain knowledge of aging process was established via sufficient data mining by the network. The results show that the ANN system is effective and successful for predicting and analyzing the properties of Cu-Cr-Zr alloy.

OPTIMIZATION OF INJECTION MOLDING PROCESS BASED ON NUMERICAL SIMULATION AND BP NEURAL NETWORKS

Plastic injection molding is a very complex process and its process planning has a direct influence on product quality and production efficiency. This paper studied the optimization of injection molding process by combining the numerical simulation with back-propagation(BP) networks. The BP networks are trained by the results of numerical simulation. The trained BP networks may:(1) shorten time for process planning;(2) optimize process parameters;(3) be employed in on-line quality control;(4) be integrated with knowledge-based system(KBS) and case-based reasoning(CBR) to make intelligent process planning of injection molding.

Expert control strategy using neural networks for electrolytic zinc process

The most important parameters which control the electrolytic process are the concentrations of zinc and sulfuric acid in the electrolyte. An expert control strategy for determining and tracking the optimal concentrations was proposed, which uses neural networks, rule models and a single loop control scheme. First, the process was described and the strategy that features an expert controller and three single loop controllers was explained. Next, neural networks and rule models were constructed based on statistical data and empirical knowledge on the process. Then, the expert controller for determining the optimal concentrations was designed through a combination of the neural networks and rule models. The three single loop controllers used the PI algorithm to track the optimal concentrations. Finally, the implementation of the proposed strategy were presented. The run results show that the strategy provides not only high purity metallic zinc, but also significant economic benefits.

Research on the controller of an arc welding process based on a PID neural network

A controller based on a PID neural network （PIDNN） is proposed for an arc welding power source whose output characteristic in responding to a given value is quickly and intelligently controlled in the welding process. The new method syncretizes the PID control strategy and neural network to control the welding process intelligently, so it has the merit of PID control rules and the trait of better information disposal ability of the neural network. The results of simulation show that the controller has the properties of quick response, low overshoot, quick convergence and good stable accuracy, which meet the requirements for control of the welding process.