Parameter Self - Learning of Generalized Predictive Control Using BP Neural Network

This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.

Study of a New Improved PSO-BP Neural Network Algorithm

In order to overcome shortcomings of traditional BP neural network,such as low study efficiency, slow convergence speed,easily trapped into local optimal solution,we proposed an improved BP neural network model based on adaptive particle swarm optimization( PSO) algorithm. This algorithm adjusted the inertia weight coefficients and learning factors adaptively and therefore could be used to optimize the weights in the BP network. After establishing the improved PSO-BP( IPSO-BP) model,it was applied to solve fault diagnosis of rolling bearing. Wavelet denoising was selected to reduce the noise of the original vibration signals,and based on these vibration signals a wide set of features were used as the inputs in the neural network models. We demonstrate the effectiveness of the proposed approach by comparing with the traditional BP,PSO-BP and linear PSO-BP( LPSO-BP) algorithms. The experimental results show that IPSO-BP network outperforms other algorithms with faster convergence speed,lower errors,higher diagnostic accuracy and learning ability.

Sub-pixel mapping method based on BP neural network

A new sub-pixel mapping method based on BP neural network is proposed in order to determine the spatial distribution of class components in each mixed pixel.The network was used to train a model that describes the relationship between spatial distribution of target components in mixed pixel and its neighboring information.Then the sub-pixel scaled target could be predicted by the trained model.In order to improve the performance of BP network,BP learning algorithm with momentum was employed.The experiments were conducted both on synthetic images and on hyperspectral imagery(HSI).The results prove that this method is capable of estimating land covers fairly accurately and has a great superiority over some other sub-pixel mapping methods in terms of computational complexity.

Research on Handwritten Chinese Character Recognition Based on BP Neural Network

The application of pattern recognition technology enables us to solve various human-computer interaction problems that were difficult to solve before.Handwritten Chinese character recognition,as a hot research object in image pattern recognition,has many applications in people’s daily life,and more and more scholars are beginning to study off-line handwritten Chinese character recognition.This paper mainly studies the recognition of handwritten Chinese characters by BP(Back Propagation)neural network.Establish a handwritten Chinese character recognition model based on BP neural network,and then verify the accuracy and feasibility of the neural network through GUI(Graphical User Interface)model established by Matlab.This paper mainly includes the following aspects:Firstly,the preprocessing process of handwritten Chinese character recognition in this paper is analyzed.Among them,image preprocessing mainly includes six processes:graying,binarization,smoothing and denoising,character segmentation,histogram equalization and normalization.Secondly,through the comparative selection of feature extraction methods for handwritten Chinese characters,and through the comparative analysis of the results of three different feature extraction methods,the most suitable feature extraction method for this paper is found.Finally,it is the application of BP neural network in handwritten Chinese character recognition.The establishment,training process and parameter selection of BP neural network are described in detail.The simulation software platform chosen in this paper is Matlab,and the sample images are used to train BP neural network to verify the feasibility of Chinese character recognition.Design the GUI interface of human-computer interaction based on Matlab,show the process and results of handwritten Chinese character recognition,and analyze the experimental results.

Classification of Oil-Gas-Water Three-Phase Flow in a Pipeline Based on BP Neural Network Analysis

The flow pattern in a pipeline is a very important topic in petroleum exploitation. This paper is to classify the flow pattern of oil-gas-water flow in a pipeline by using BP neural network. The effects of different parameter combinations are investigated to find the most important ones. It is shown that BP neural network can be used in the analysis of the flow pattern of three-phase flow in pipelines. In most cases, the mean square error is large for the horizontal pipes. The optimized neuron number of the middle layer changes with conditions. So, we must changes the neuron number of the middle layer in simulation for any conditions to seek the best results. These conclusions can be taken as references for further study of the flow pattern of oil-gas-water in a pipeline.

Assessment of dairy cow feed intake based on BP neural network with polynomial decay learning rate

To overcome the shortcomings of traditional dairy cow feed intake assessment model andBP neural network, this paper proposes a method of optimizing BP neural network usingpolynomial decay learning rate, taking the cow’s body weight, lying duration, lying times,walking steps, foraging duration and concentrate-roughage ratio as input variables andtaking the actual feed intake is the output variable to establish a dairy cow feed intakeassessment model, and the model is trained and verified by experimental data collectedon site. For the sake of comparative study, feed intake is simultaneously assessed by SVRmodel, KNN logistic regression model, traditional BP neural network model, and multilayerBP neural network model. The results show that the established BP model using the polynomial decay learning rate has the highest assessment accuracy, the MSPE, RMSE, MAE,MAPE and R2 are 0.043 kg2/d and 0.208 kg/d, 0.173 kg/d, 1.37% and 0.94 respectively. Compared with SVR model and KNN mode, the RMSE value reduced by 43.9% and 26.5%, it isalso found that the model designed in this paper has many advantages in comparison withthe BP model and multilayer BP model in terms of precision and generalization. Therefore,this method is ready to be applied for accurately evaluating the dairy cow feed intake, andit can provide theoretical guidance and technical support for the precise-feeding and canalso be of high significance in the improvement of dairy precise-breeding.

Crack Fault Diagnosis and Location Method for a Dual-Disk Hollow Shaft Rotor System Based on the Radial Basis Function Network and Pattern Recognition Neural Network

The crack fault is one of the most common faults in the rotor system,and researchers have paid close attention to its fault diagnosis.However,most studies focus on discussing the dynamic response characteristics caused by the crack rather than estimating the crack depth and position based on the obtained vibration signals.In this paper,a novel crack fault diagnosis and location method for a dual-disk hollow shaft rotor system based on the Radial basis function(RBF)network and Pattern recognition neural network(PRNN)is presented.Firstly,a rotor system model with a breathing crack suitable for a short-thick hollow shaft rotor is established based on the finite element method,where the crack's periodic opening and closing pattern and different degrees of crack depth are considered.Then,the dynamic response is obtained by the harmonic balance method.By adjusting the crack parameters,the dynamic characteristics related to the crack depth and position are analyzed through the amplitude-frequency responses and waterfall plots.The analysis results show that the first critical speed,first subcritical speed,first critical speed amplitude,and super-harmonic resonance peak at the first subcritical speed can be utilized for the crack fault diagnosis.Based on this,the RBF network and PRNN are adopted to determine the depth and approximate location of the crack respectively by taking the above dynamic characteristics as input.Test results show that the proposed method has high fault diagnosis accuracy.This research proposes a crack detection method adequate for the hollow shaft rotor system,where the crack depth and position are both unknown.

A structural developmental neural network with information saturation for continual unsupervised learning

In this paper,we propose a structural developmental neural network to address the plasticity‐stability dilemma,computational inefficiency,and lack of prior knowledge in continual unsupervised learning.This model uses competitive learning rules and dynamic neurons with information saturation to achieve parameter adjustment and adaptive structure development.Dynamic neurons adjust the information saturation after winning the competition and use this parameter to modulate the neuron parameter adjustment and the division timing.By dividing to generate new neurons,the network not only keeps sensitive to novel features but also can subdivide classes learnt repeatedly.The dynamic neurons with information saturation and division mechanism can simulate the long short‐term memory of the human brain,which enables the network to continually learn new samples while maintaining the previous learning results.The parent‐child relationship between neurons arising from neuronal division enables the network to simulate the human cognitive process that gradually refines the perception of objects.By setting the clustering layer parameter,users can choose the desired degree of class subdivision.Experimental results on artificial and real‐world datasets demonstrate that the proposed model is feasible for unsupervised learning tasks in instance increment and class incre-ment scenarios and outperforms prior structural developmental neural networks.

Finite Convergence of On-line BP Neural Networks with Linearly Separable Training Patterns

In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.

基于粒子群优化BP神经网络的中空夹层钢管混凝土柱轴压承载力研究

圆中空夹层钢管混凝土(concrete filled double-skin steel tube,CFDST)柱因其独特的结构形式与优异的力学性能,已成为现代工程结构中的主要受力构件。然而外钢管、内钢管与核心混凝土之间的相互约束作用导致其受力比较复杂。为此,采用PSO-BP混合神经网络算法对圆CFDST柱的轴压承载力进行了研究。收集了167组数据建立数据库,并选取8种影响因素作为输入层参数,轴压承载力作为输出层参数,分析了传统BP神经网络模型所存在的缺陷,建立了PSO-BP神经网络模型。此外,将机器学习模型与3种规范的结果进行比较,结果表明机器学习模型的精度比3种规范的精度更高。相较于BP神经网络模型,PSO-BP神经网络模型具有更好的预测能力,更有助于预测CFDST柱的轴压承载力,对工程上研究CFDST柱的力学性能有着重要意义。

基于BP神经网络的土地利用智能分类识别与雨洪风险模拟

土地利用分类数据的精度对雨洪风险淹没模拟研究具有重要影响.土地利用分类中不同地物之间存在复杂的非线性关系,为提高土地分类数据的精度,本研究引入具有非线性映射能力的BP神经网络模型,提出了一种基于深度学习的遥感影像土地利用分类方法.选取野三坡风景名胜区GF-2遥感影像数据,对该影像进行多尺度分割.同时将能够反映土地利用信息的光谱数据和DEM数据、坡度数据,作为输入层神经元,将土地利用类型作为输出层神经元,归一化处理后进行迭代训练,构建了基于BP神经网络的土地利用分类模型.该模型的分类总体精度达到91%,Kappa系数为0.890 6.基于该模型的识别结果,利用水文模型和ArcGIS空间分析工具,模拟并分析野三坡景区百年一遇的极端降水事件造成的雨洪淹没区,并提出应对雨洪灾害的相关策略.

Novel Newton’s learning algorithm of neural networks

Newton＇s learning algorithm of NN is presented and realized. In theory, the convergence rate of learning algorithm of NN based on Newton＇s method must be faster than BP＇s and other learning algorithms, because the gradient method is linearly convergent while Newton＇s method has second order convergence rate. The fast computing algorithm of Hesse matrix of the cost function of NN is proposed and it is the theory basis of the improvement of Newton＇s learning algorithm. Simulation results show that the convergence rate of Newton＇s learning algorithm is high and apparently faster than the traditional BP method＇s, and the robustness of Newton＇s learning algorithm is also better than BP method＇ s.

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.

Adaptive learning with guaranteed stability for discrete-time recurrent neural networks

To avoid unstable learning, a stable adaptive learning algorithm was proposed for discrete-time recurrent neural networks. Unlike the dynamic gradient methods, such as the backpropagation through time and the real time recurrent learning, the weights of the recurrent neural networks were updated online in terms of Lyapunov stability theory in the proposed learning algorithm, so the learning stability was guaranteed. With the inversion of the activation function of the recurrent neural networks, the proposed learning algorithm can be easily implemented for solving varying nonlinear adaptive learning problems and fast convergence of the adaptive learning process can be achieved. Simulation experiments in pattern recognition show that only 5 iterations are needed for the storage of a 15×15 binary image pattern and only 9 iterations are needed for the perfect realization of an analog vector by an equilibrium state with the proposed learning algorithm.

基于BP-SA混合学习策略优化的舰载消磁系统在役考核评估方法

装备在役考核是验证装备服役后的作战与保障效能,促进装备迭代升级的重要手段。针对舰载消磁系统在役考核工作特点和常规考核评估方法的不足,从作战效能、适用性、可靠性、维修性以及测试性等5个方面建立了舰载消磁系统在役考核指标体系。在传统BP神经网络的基础上,引入模拟退火策略随机寻找更优解,提高了神经网络的收敛性和稳定性。评估模型经过70组舰载消磁系统数据样本的训练、测试和验证,最终得到剩余预测残差RPD为9.3093的实验结果,表明了该模型不仅克服了传统BP神经网络算法局部极小、拟合效果差等问题,且对于舰载消磁系统在役考核结果具有很好的预测与评估能力。

基于GRU-BP算法的高精度动态物流称重系统

针对动态物流秤测量精度对载重、采样频率、带速较为敏感的问题,提出了一种高精度动态物流称重系统。首先,采用三因素五水平正交试验法,结合皮尔逊相关性检验原则,使用低通巴特沃斯与卡尔曼滤波器对传感器压力信号进行了滤波降噪处理,并将加速度信号作为模型输入信号,进行了特征补偿;然后,基于深度学习算法,提出了一种改进的门控循环单元模型,在该模型采样区间内将压力与振动改写为时序化信号,并将其共同输入门控循环单元(GRU)模型;最后,对GRU模型进行了改进,对其结构输出了层堆叠误差反向传播神经网络(BP),有效加强了模型的非线性映射能力。研究结果表明:在各类传动速度及测试货物下,该模型的最大测量误差相对于同类型深度学习模型长短期记忆(LSTM)神经网络、循环神经网络(RNN)时序模型及传统数值平均模型的误差,依次降低了16.14%、27.14%、76%,可用于各类称重系统。

基于煤岩煤质多元指标的BP神经网络焦油产率预测方法研究

【目的】焦油产率是煤低温干馏利用最重要的煤质参数,决定着富油煤的清洁利用方向。但由于多方面的原因,在煤炭地质勘查阶段对煤焦油产率的测试数据十分有限,极大地制约了富油煤的精细评价和高效利用。【方法】为了提高富油煤精细评价的科学性和准确性,以陕北侏罗纪煤田以往测试1073组煤岩煤质数据为基础,并筛选出显微组分、工业分析、元素分析、灰成分分析等20项煤岩煤质参数齐全的141组数据,利用BP神经网络算法分别建立了20项煤岩煤质指标的焦油产率预测模型和以4项工业分析为基础的焦油产率预测模型,并对预测模型的准确性和合理性进行分析评价。【结果和结论】结果表明:以20项煤岩煤质指标为特征建立的预测模型最终训练均方误差为0.30,测试集数据预测结果平均绝对误差为0.65;以4项工业分析指标为特征建立的预测模型最终训练均方误差为1.07,测试集数据预测结果平均绝对误差为1.35;扩展集数据在两个模型中预测结果平均绝对误差分别为0.84和1.34,显示出20项煤岩煤质指标比4项工业分析煤质指标建立的预测模型具有更高的拟合优度和泛化性能。利用SHAP算法进一步对预测模型中20项煤岩煤质指标的重要性进行量化分析,显示出镜质组、氢元素、三氧化二铁、水分、挥发分、碳元素、壳质组、氧元素含量是焦油产率的正向影响因素,三氧化二铝、惰质组、固定碳、灰分、二氧化硅含量是焦油产率的负向影响因素,模型中煤岩煤质与焦油产率之间的内在联系很好地契合了地质上对焦油产率影响因素的基本认识,该焦油产率预测模型可以很好地应用于陕北侏罗纪煤田的焦油产率预测,为陕北地区富油煤的清洁高效利用提供支撑。

A CASCADED MODEL OF NEURAL NETWORK FOR PATTERN RECOGNITION

A cascaded model of neural network and its learning algorithm suitable for opticalimplementation are proposed.Computer simulations have shown that this model may successfullybe applied to an error-tolerance pattern recognitions of multiple 3-D targets with arbitrary spatialorientations.

Prediction of Enthalpies of Fusion for Divalent Rare Earth Halides Based on Modeling by Artificial Neural Networks and Pattern Recognition

The artificial neural network (ANN) and the pattern recognition were applied to study the correlation of enthalpies of fusion for divalent rare earth halides with their microstructural parameters,such as ionic radius and electronegativity. The model,represented by a back-propagation netal network, was trained with a 12 set of published data for divalent rare earth halides and then was used to predict the unknown ones. Also the criterion equations were ptesented to determine the enthalpies of fuSion for divalent rare earth halides using pattern recognition in mis work. The results from the model in ANN and criterion equations are in very good agreement with reference data.

2D spiral pattern recognition based on neural network covering algorithm

The main aim for a 2D spiral recognition algorithm is to learn to discriminate between data distributed on two distinct strands in the x-y plane.This problem is of critical importance since it incorporates temporal characteristics often found in real-time applications.Previous work with this benchmark has witnessed poor results with statistical methods such as discriminant analysis and tedious procedures for better results with neural networks.This paper presents a max-density covering learning algorithm based on constructive neural networks which is efficient in terms of the recognition rate and the speed of recognition.The results show that it is possible to solve the spiral problem instantaneously(up to 100% correct classification on the test set).