Study and Application of Fault Prediction Methods with Improved Reservoir Neural Networks

Time-series prediction is one of themajor methodologies used for fault prediction. Themethods based on recurrent neural networks have been widely used in time-series prediction for their remarkable non-liner mapping ability. As a new recurrent neural network, reservoir neural network can effectively process the time-series prediction. However, the ill-posedness problemof reservoir neural networks has seriously restricted the generalization performance. In this paper, a fault prediction algorithm based on time-series is proposed using improved reservoir neural networks. The basic idea is taking structure risk into consideration, that is, the cost function involves not only the experience risk factor but also the structure risk factor. Thus a regulation coefficient is introduced to calculate the outputweight of the reservoir neural network. As a result, the amplitude of outputweight is effectively controlled and the ill-posedness problemis solved. Because the training speed of ordinary reservoir networks is naturally fast, the improved reservoir networks for time-series prediction are good in speed and generalization ability. Experiments on Mackey-Glass and sunspot time series prediction prove the effectiveness of the algorithm. The proposed algorithm is applied to TE process fault prediction. We first forecast some timeseries obtained from TE and then predict the fault type adopting the static reservoirs with the predicted data. The final prediction correct rate reaches 81%.     

一种生化反应器智能自适应学习和预测神经元网络系统

The adaptive learning and prediction of a highly nonlinear and time-varying bioreactor benchmark process is studied using Neur-On-Line, a graphical tool kit for developing and deploying neural networks in the G2 real time intelligent environment,and a new modified Broyden, Fletcher, Goldfarb, and Shanno （BFGS） quasi-Newton algorithm. The modified BFGS algorithm for the adaptive learning of back propagation （BP） neural networks is developed and embedded into NeurOn-Line by introducing a new search method of learning rate to the full memory BFGS algorithm. Simulation results show that the adaptive learning and prediction neural network system can quicklv track the time-varving and nonlinear behavior of the bioreactor.     

基于神经网络与遗传算法结合的硝化细菌发酵培养基优化(英文)

Two artificial intelligence techniques, artificial neural network and genetic algorithm, were applied to optimize the fermentation medium for improving the nitrite oxidization rate of nitrite oxidizing bacteria. Experiments were conducted with the composition of medium components obtained by genetic algorithm, and the experimental data were used to build a BP (back propagation) neural network model. The concentrations of six medium components were used as input vectors, and the nitrite oxidization rate was used as output vector of the model. The BP neural network model was used as the objective function of genetic algorithm to find the optimum medium composition for the maximum nitrite oxidization rate. The maximum nitrite oxidization rate was 0.952 g 2 NO-2-N·(g MLSS)-1·d-1 , obtained at the genetic algorithm optimized concentration of medium components (g·L-1 ): NaCl 0.58, MgSO 4 ·7H 2 O 0.14, FeSO 4 ·7H 2 O 0.141, KH 2 PO 4 0.8485, NaNO 2 2.52, and NaHCO 3 3.613. Validation experiments suggest that the experimental results are consistent with the best result predicted by the model. A scale-up experiment shows that the nitrite degraded completely after 34 h when cultured in the optimum medium, which is 10 h less than that cultured in the initial medium.     

基于邻域保留空间中模糊C聚类的多模态过程监控(英文)

For complex industrial processes with multiple operational conditions, it is important to develop effective monitoring algorithms to ensure the safety of production processes. This paper proposes a novel monitoring strategy based on fuzzy C-means. The high dimensional historical data are transferred to a low dimensional subspace spanned by locality preserving projection. Then the scores in the novel subspace are classified into several overlapped clusters, each representing an operational mode. The distance statistics of each cluster are integrated though the membership values into a novel BID (Bayesian inference distance) monitoring index. The efficiency and effectiveness of the proposed method are validated though the Tennessee Eastman benchmark process.     

改进的自适应免疫算法及其在对二甲苯氧化燃烧副反应优化中的应用(英文)

In recent years, immune genetic algorithm (IGA) is gaining popularity for finding the optimal solution for non-linear optimization problems in many engineering applications. However, IGA with deterministic mutation factor suffers from the problem of premature convergence. In this study, a modified self-adaptive immune genetic algorithm (MSIGA) with two memory bases, in which immune concepts are applied to determine the mutation parameters, is proposed to improve the searching ability of the algorithm and maintain population diversity. Performance comparisons with other well-known population-based iterative algorithms show that the proposed method converges quickly to the global optimum and overcomes premature problem. This algorithm is applied to optimize a feed forward neural network to measure the content of products in the combustion side reaction of p-xylene oxidation, and satisfactory results are obtained.     

复杂故障判定的基于结构化残差的多层次分析法

In industrial processes,there exist faults that have complex effect on process variables.Complex and simple faults are defined according to their effect dimensions.The conventional approaches based on structured residuals cannot isolate complex faults.This paper presents a multi-level strategy for complex fault isolation.An extraction procedure is employed to reduce the complex faults to simple ones and assign them to several levels.On each level,faults are isolated by their different responses in the structured residuals.Each residual is obtained insensitive to one fault but more sensitive to others.The faults on different levels are verified to have different residual responses and will not be confused.An entire incidence matrix containing residual response characteristics of all faults is obtained,based on which faults can be isolated.The proposed method is applied in the Tennessee Eastman process example,and the effectiveness and advantage are demonstrated.     

基于自适应学习速率的模糊神经网络控制器

针对模糊神经网络控制器中很难确定一个最佳学习速率的问题,将带有动量因子的自适应学习速率BP算法引入模糊神经网络控制器中。采用模糊推理自适应调节学习速率,同时引入动量因子,提高系统的收敛速度,并基于Lyapunov定理给出了系统稳定的证明过程。针对同一数学模型,用Matlab编程仿真3种方法的实验结果表明:优化后的模糊神经网络控制器较普通模糊神经网络控制器和模糊控制器具有更优越的控制性能。     

一种改进的混合遗传算法及在化工过程动态优化中的应用(英文)

The solutions of dynamic optimization problems are usually very difficult due to their highly nonlinear and multidimensional nature. Genetic algorithm (GA) has been proved to be a feasible method when the gradient is difficult to calculate. Its advantage is that the control profiles at all time stages are optimized simultaneously, but its convergence is very slow in the later period of evolution and it is easily trapped in the local optimum. In this study, a hybrid improved genetic algorithm (HIGA) for solving dynamic optimization problems is proposed to overcome these defects. Simplex method (SM) is used to perform the local search in the neighborhood of the optimal solution. By using SM, the ideal searching direction of global optimal solution could be found as soon as possible and the convergence speed of the algorithm is improved. The hybrid algorithm presents some improvements, such as protecting the best individual, accepting immigrations, as well as employing adaptive crossover and Gaussian mutation operators. The efficiency of the proposed algorithm is demonstrated by solving several dynamic optimization problems. At last, HIGA is applied to the optimal production of secreted protein in a fed batch reactor and the optimal feed-rate found by HIGA is effective and relatively stable.     

基于半闭环框架的软测量设计(英文)

Soft-sensing is widely used in industrial applications. The traditional soft-sensing structure is open-loop without correction mechanism. If the working condition is changed or there is unknown disturbance, the forecast result of soft-sensing model may be incorrect. In order to obtain accurate values, it is necessary to carry out online correction. In this paper, a semiclosed-loop framework (SLF) is proposed to establish a soft-sensing approach, which estimates the input variables in the next moment by a prediction model and calibrates the output variables by a compensation model. The experimental results show that the proposed method has better prediction accuracy and robustness than other open-loop models.     

基于线性时变扰动模型的间歇过程最优迭代学习控制

A batch-to-batch optimal iterative learning control (ILC) strategy for the tracking control of product quality in batch processes is presented. The linear time-varying perturbation (LTVP) model is built for product quality around the nominal trajectories. To address problems of model-plant mismatches, model prediction errors in the previous batch run are added to the model predictions for the current batch run. Then tracking error transition models can be built, and the ILC law with direct error feedback is explicitly obtained. A rigorous theorem is proposed, to prove the convergence of tracking error under ILC. The proposed methodology is illustrated on a typical batch reactor and the results show that the performance of trajectory tracking is gradually improved by the ILC.     

一种分布式模糊神经网络在熔融指数软测量中的应用

采用Mamdani模型作为模糊分类器 ,利用神经网络建立非线性模型 ,构造一种分布式神经网络。采用多组样本数据建模 ,根据各输入模糊子集和隶属度函数 ,将输入样本空间模糊分割成多个子空间 ,对每个子空间用一个神经网络模型建立映射关系。对每一组输入向量在确定归属类后 ,自动切换至对应的子网络作为输入 ,该子网络的输出值则作为分布式网络的输出。仿真结果表明 ,该方法与用单个神经元网络相比 ,明显提高了模型的精度和泛化能力。     

Prediction of Timber Kiln Drying Rates by Neural Networks

The purpose of this exploratory work was to apply artificial neural network (ANN) modeling to the prediction of timber kiln drying rates based on species and basic density information for the hem-fir mix that grows along the local coastal areas. The ANN models with three inputs (initial moisture content, basic density, and drying time) were developed to predict one output, namely, average final moisture content. The back-propagation algorithm, the most common neural network learning method, was implemented for testing, training, and validation. Optimal configuration of the network model was obtained by varying its main parameters, such as transfer function, learning rule, number of neurons and layers, and learning runs. Accurate prediction of the experimental drying rate data by the ANN model was achieved with a mean absolute relative error less than 2%, thus supporting the powerful predictive capacity of this modeling method.     

Prediction of Timber Kiln Drying Rates by Neural Networks

The purpose of this exploratory work was to apply artificial neural network (ANN) modeling to the prediction of timber kiln drying rates based on species and basic density information for the hem-fir mix that grows along the local coastal areas. The ANN models with three inputs (initial moisture content, basic density, and drying time) were developed to predict one output, namely, average final moisture content. The back-propagation algorithm, the most common neural network learning method, was implemented for testing, training, and validation. Optimal configuration of the network model was obtained by varying its main parameters, such as transfer function, learning rule, number of neurons and layers, and learning runs. Accurate prediction of the experimental drying rate data by the ANN model was achieved with a mean absolute relative error less than 2%, thus supporting the powerful predictive capacity of this modeling method.     

PollenDetect: An Open-Source Pollen Viability Status Recognition System Based on Deep Learning Neural Networks

Pollen grains, the male gametophytes for reproduction in higher plants, are vulnerable to various stresses that lead to loss of viability and eventually crop yield. A conventional method for assessing pollen viability is manual counting after staining, which is laborious and hinders high-throughput screening. We developed an automatic detection tool (PollenDetect) to distinguish viable and nonviable pollen based on the YOLOv5 neural network, which is adjusted to adapt to the small target detection task. Compared with manual work, PollenDetect significantly reduced detection time (from approximately 3 min to 1 s for each image). Meanwhile, PollenDetect can maintain high detection accuracy. When PollenDetect was tested on cotton pollen viability, 99% accuracy was achieved. Furthermore, the results obtained using PollenDetect show that high temperature weakened cotton pollen viability, which is highly similar to the pollen viability results obtained using 2,3,5-triphenyltetrazolium formazan quantification. PollenDetect is an open-source software that can be further trained to count different types of pollen for research purposes. Thus, PollenDetect is a rapid and accurate system for recognizing pollen viability status, and is important for screening stress-resistant crop varieties for the identification of pollen viability and stress resistance genes during genetic breeding research.     

煤直接液化间歇反应器性能的人工神经网络模拟

鉴于煤直接液化反应的复杂性和机理模型难以建立、计算量大等,结合人工神经网络建模方法,建立了煤直接液化间歇反应器的BP神经网络模型,并利用统计极差分析方法考察了影响反应器煤转化率、油收率及综合评价3个指标的8个关键因素的敏感程度。结果表明,训练完成的BP神经网络模型不仅能很好地拟合已知实验结果,而且具有良好的预测能力,预测结果的平均相对误差为3.75%;当煤为烟煤或亚烟煤、溶剂分别为萘满(1,2,3,4-四氢化萘)或循环溶剂时,综合评价给出的影响因素的敏感性顺序为:温度>反应时间>剂煤比>煤粒度>氢分压和填充程度>煤类型>溶剂类型。     

用神经网络技术预测库存发射药安全寿命的可行性

在对发射药贮存寿命终点判据和发射药能量示数、贮存环境温度、湿度等影响贮存安定性的因素进行分析的基础上，以BP人工神经网络作为预测手段，对发射药的安全贮存寿命进行了预测。     

HLGNN-MDA: Heuristic Learning Based on Graph Neural Networks for miRNA–Disease Association Prediction

Identifying disease-related miRNAs can improve the understanding of complex diseases. However, experimentally finding the association between miRNAs and diseases is expensive in terms of time and resources. The computational screening of reliable miRNA–disease associations has thus become a necessary tool to guide biological experiments. “Similar miRNAs will be associated with the same disease” is the assumption on which most current miRNA–disease association prediction methods rely; however, biased prior knowledge, and incomplete and inaccurate miRNA similarity data and disease similarity data limit the performance of the model. Here, we propose heuristic learning based on graph neural networks to predict microRNA–disease associations (HLGNN-MDA). We learn the local graph topology features of the predicted miRNA–disease node pairs using graph neural networks. In particular, our improvements to the graph convolution layer of the graph neural network enable it to learn information among homogeneous nodes and among heterogeneous nodes. We illustrate the performance of HLGNN-MDA by performing tenfold cross-validation against excellent baseline models. The results show that we have promising performance in multiple metrics. We also focus on the role of the improvements to the graph convolution layer in the model. The case studies are supported by evidence on breast cancer, hepatocellular carcinoma and renal cell carcinoma. Given the above, the experiments demonstrate that HLGNN-MDA can serve as a reliable method to identify novel miRNA–disease associations.     

"人工神经网络"方法用于超临界流体萃取模拟

在15－30MPa和303－323K条件下，用超临界CO2流体萃取沙棘籽油，结果表明，最高沙棘油收率（30MPa,308K)可达到90％以上，对过程进行动力学模拟，建立了超临界萃取过程的人工神经网络（ANN）模型，以MATLAB软件为平台，编制了SFE－ANN模拟程序系统，采用3层BP网络结构，以压力，温度、萃取时间为输入，以萃取出油量为输出对网络进行训练，由此得到的网络可以对萃取速率和单位时间床高方向的萃取出油量进行准确的模拟和预测，与实验结果比较证明，训练样本集误差为0．2％，测试样本集误差为0．5％，模拟误差小于6％。