Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework

As one of the representative unsupervised data augmentation methods, generative adversarial networks (GANs) have the potential to solve the problem of insufficient samples in fault diagnosis of rotating machinery. However, the existing unsupervised GANs are usually incapable of simultaneously generating multi-mode fault samples and have some shortcomings such as mode collapse and gradient vanishing. To overcome these deficiencies, a supervised model called modified auxiliary classifier GAN (MACGAN) designed with new framework is proposed in this paper. Firstly, a new ACGAN framework is developed by adding an independent classifier to improve the compatibility between the classification and discrimination. Secondly, the Wasserstein distance is introduced in the new loss functions to overcome mode collapse and gradient vanishing. Finally, to achieve stable training, a spectral normalization is used to replace the weight clipping to constrain the weight parameters of discriminator. The proposed method is applied to fault diagnosis of bearing and gear. Compared with the existing GANs, the proposed method can more efficiently generate multi-mode fault samples with higher qualities, which can be used to assist the training of deep learning-based fault diagnosis models with high accuracy and good stability.     

Fault-tolerant control through dynamic surface triple-step approach for proton exchange membrane fuel cell air supply systems

Due to complex electrochemical and thermal phenomena, varying operations towards automotive applications, and vulnerable ancillaries in proton exchange membrane fuel cells (PEMFCs), fault diagnosis and fault-tolerant control (FTC) design have become important aspects to improve the reliability, safety and performance of PEMFC systems. This paper presents a novel FTC scheme for automotive PEMFC air supply systems via coordinated control of the air flow rate and the pressure in cathodes. A dynamic surface triple-step approach is first proposed considering nonlinear dynamics and the multi-input multi-output (MIMO) property, which combines the advantage of dynamic surface control in avoiding an “explosion of complexity” and the advantage of triple-step control in guaranteeing a simple structure and high performance. The normal case, the faulty case at the supply manifold and the faulty case in the back pressure valve are considered in the FTC design, with the stability of the overall system proved using Lyapunov methods. MATLAB/Simulink simulations with a high-fidelity PEMFC model verify the effectiveness of the proposed FTC scheme in regulating the air flow rate and oxygen excess ratio and maintaining the pressure of the cathode at a desired level even under faulty conditions.     

Study on the influence of segmented fuel cell by grooving method and its application in oxygen starvation diagnosis

The oxygen starvation in fuel cells is an important reason for the deterioration of durability. The segmented fuel cell is a method to study the gas distribution inside the fuel cell. In order to study the influence of the grooving method on segmented fuel cell and its application in oxygen starvation diagnosis, a five-serpentine-channel three-dimensional two-phase simulation model is established by FLUENT. Through steady-state simulation, the effect of grooving method on fuel cell performance is studied. The overall performance (polarization curve) of the fuel cell drops slightly, but the current density distribution on the anode graphite plate changes greatly due to the grooves. The “current concentration” phenomenon is proposed based on the current density distribution. Through dynamic simulation, the oxygen starvation under current load mode and voltage load mode is simulated, and the “starvation coefficient” is defined as an oxygen starvation diagnostic index. In the current load mode, the “starvation coefficient” never exceed 15%, because when the oxygen starvation is severe, the simulation cannot converge or even cannot maintain, which corresponds to the voltage reversal in reality. However, in the voltage load mode, the “starvation coefficient” can reach up to 100%. The conclusions have important guiding significance for the judgment of the internal reaction uniformity of the segmented fuel cell by grooving method and provide a theoretical basis for judging whether a fuel cell is out of oxygen by segmented fuel cell.     

Data-driven diagnosis of the high-pressure hydrogen leakage in fuel cell vehicles based on relevance vector machine

The hydrogen pressure inside tanks and its adjacent pipes can reach up to 70 MPa in fuel cell vehicles. This is the weak links of hydrogen leakage. The diagnosis time of mainstream hydrogen leakage diagnosis method based on hydrogen concentration sensors (HCSs) is easily affected by the number and location of installed sensors. In this study, a data-driven diagnosis method is proposed for the high-pressure hydrogen leakage. Fisher discrimination analysis and linear least squares fitting are used for data preprocessing, relevance vector machine is used for pattern recognition. When the total volume of tanks is 82 L and the hydrogen leakage flow rate is larger than 2 g/s, the diagnosis accuracy of the proposed method is higher than 95% and the diagnosis time is constant. When the leakage location is far away from HCSs, the proposed method can the diagnose hydrogen leakage in a shorter time than mainstream method.     

Machine fault diagnosis with small sample based on variational information constrained generative adversarial network

In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches.     

渤海海域辽西构造带S型走滑转换带特征及控藏作用定量表征

S型走滑转换带是走滑环境下广泛发育的一类构造。以往的研究认识多集中在对走滑转换带类型划分的探讨上，缺乏对其控藏作用的精细研究。本次研究利用渤海海域辽东湾地区连片三维地震资料，结合油气田实例，运用统计学方法分析了辽西构造带S型走滑转换带的控藏作用。辽西带新生代构造变形总体表现为NE向伸展构造系统和NNE向右旋走滑构造系统的叠加构造变形，S型走滑转换带可分为增压段和释压段两大类。按照走滑转换带演化阶段的不同，将增压段进一步细分为压扭低凸起段、平缓增压段和强烈增压段等3个亚类。将释压段同样细分为纺锤形浅凹、平缓释压段和菱形释压段等3个亚类。将走滑断裂末端发育的转换带归纳为增压型或释压型马尾扇。应用S型走滑转换带“油气富集指数”的分析方法，论证了S型走滑转换带弯曲度与走滑调节断层活动性具有正相关性，并成功应用于辽西凹陷南次洼旅大5-2北油田成藏分析工作中，为勘探决策提供了定量化依据。     

基于深度信念网络的列车故障音频诊断方法

铁路在交通运输行业有着举足轻重的地位，一旦列车发生故障将会导致严重的生命财产损失。由于列车发生故障的概率相对较低，因此难以捕获列车的故障样本。针对上述问题，提出了一种无监督学习的列车故障识别方法，通过检测列车音频信号来识别列车故障。该方法基于深度信念网络(DBN)，利用小波包分解提取检测信号的特征向量并将其作为DBN的输入，待网络充分训练后，由训练好的DBN识别当前列车的运行状况。现场监测实验结果表明，该方法能够在无监督的条件下有效识别列车故障，保障了列车的运行安全。     

基于EEMD能量熵和混合算法的电机轴承故障诊断

针对提升机电机轴承振动信号的非平稳特性和单一粒子群算法(PSO) 优化径向基函数（RBF）神经网络时存在网络收敛速度慢和适应度值易陷入局部最小的缺点，提出基于集合经验模态分解（EEMD）能量熵和模拟退火粒子群混合算法（SAPSO）优化RBF神经网络的提升机电机轴承故障诊断方法。基于EEMD求取振动信号各固有模态函数分量的能量熵，并使用相关性分析方法剔除虚假的分量，把筛选后的有效数据作为故障识别的特征向量；利用模拟退火（SA）算法具有局部概率突跳的特性，将SA算法和PSO算法相结合，在优化RBF诊断模型隐含层参数时以实现不同算法间的优劣互补。仿真结果表明，使用SAPSO算法优化后的RBF神经网络模型在提升机电机轴承故障诊断中能够加快网络收敛速度和提升故障识别精度。     

基于深度残差网络的化工过程故障诊断

本工作提出了一种基于深度残差网络(DRN)的化工过程故障诊断方法，可从大量化工过程运行数据中自动提取故障特征。模型采用快捷连接缓解传统深度神经网络训练困难的问题，且使用批归一化(BN)方法，可有效缓解梯度消失/爆炸的问题。以田纳西?伊斯曼(TE)过程为实验对象对所提方法进行诊断性能评价实验，并与以往的基于传统深度学习模型的TE过程故障诊断方法进行对比，进一步探究了模型层数、BN技术和残差结构对故障诊断率的影响，最后，通过t分布随机邻域嵌入(t-SNE)方法对网络部分层的输出进行可视化。结果表明，模型对21种工况取得了94%的平均故障诊断率和0.30%的平均假阳率，表现出更加卓越的诊断性能。输出层的二维散点图显示了清晰的聚类，表明所提出的DRN模型能够对故障进行准确诊断。