Diagnosis of process faults and sensor faults in a class of nonlinear uncertain systems

This paper presents a fault diagnosis method for process faults and sensor faults in a class of nonlinear uncertain systems.The fault detection and isolation architecture consists of a fault detection estimator and a bank of adaptive isolation estimators,each corresponding to a particular fault type.Adaptive thresholds for fault detection and isolation are presented.Fault detectability conditions characterizing the class of process faults and sensor faults that are detectable by the presented method are derived.A simulation example of robotic arm is used to illustrate the effectiveness of the fault diagnosis method.

Multimode Process Fault Detection Using Local Neighborhood Similarity Analysis

Traditional data driven fault detection methods assume unimodal distribution of process data so that they often perform not well in chemical process with multiple operating modes. In order to monitor the multimode chemical process effectively, this paper presents a novel fault detection method based on local neighborhood similarity analysis(LNSA). In the proposed method, prior process knowledge is not required and only the multimode normal operation data are used to construct a reference dataset. For online monitoring of process state, LNSA applies moving window technique to obtain a current snapshot data window. Then neighborhood searching technique is used to acquire the corresponding local neighborhood data window from the reference dataset. Similarity analysis between snapshot and neighborhood data windows is performed, which includes the calculation of principal component analysis(PCA) similarity factor and distance similarity factor. The PCA similarity factor is to capture the change of data direction while the distance similarity factor is used for monitoring the shift of data center position. Based on these similarity factors, two monitoring statistics are built for multimode process fault detection. Finally a simulated continuous stirred tank system is used to demonstrate the effectiveness of the proposed method. The simulation results show that LNSA can detect multimode process changes effectively and performs better than traditional fault detection methods.

An Incremental Model Transfer Method for Complex Process Fault Diagnosis

Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of production process often lead to the changes of data distribution and the emergence of new fault classes, and the number of the new fault classes is unpredictable. The reconstruction of the fault diagnosis model and the identification of new fault classes have become core issues under the circumstances. This paper presents a fault diagnosis method based on model transfer learning and the main contributions of the paper are as follows: 1) An incremental model transfer fault diagnosis method is proposed to reconstruct the new process diagnosis model. 2) Breaking the limit of existing method that the new process can only have one more class of faults than the old process, this method can identify M faults more in the new process with the thought of incremental learning. 3) The method offers a solution to a series of problems caused by the increase of fault classes. Experiments based on Tennessee-Eastman process and ore grinding classification process demonstrate the effectiveness and the feasibility of the method.

Advancements in Photovoltaic Panel Fault Detection Techniques

This paper examines the progression and advancements in fault detection techniques for photovoltaic (PV) panels, a target for optimizing the efficiency and longevity of solar energy systems. As the adoption of PV technology grows, the need for effective fault detection strategies becomes increasingly paramount to maximize energy output and minimize operational downtimes of solar power systems. These approaches include the use of machine learning and deep learning methodologies to be able to detect the identified faults in PV technology. Here, we delve into how machine learning models, specifically kernel-based extreme learning machines and support vector machines, trained on current-voltage characteristic (I-V curve) data, provide information on fault identification. We explore deep learning approaches by taking models like EfficientNet-B0, which looks at infrared images of solar panels to detect subtle defects not visible to the human eye. We highlight the utilization of advanced image processing techniques and algorithms to exploit aerial imagery data, from Unmanned Aerial Vehicles (UAVs), for inspecting large solar installations. Some other techniques like DeepLabV3 , Feature Pyramid Networks (FPN), and U-Net will be detailed as such tools enable effective segmentation and anomaly detection in aerial panel images. Finally, we discuss implications of these technologies on labor costs, fault detection precision, and sustainability of PV installations.

The Dihedral Angle and Intersection Processes of a Conjugate Strike-Slip Fault System in the Tarim Basin, NW China

Recent studies, focused on dihedral angles and intersection processes, have increased understandings of conjugate fault mechanisms. We present new 3-D seismic data and microstructural core analysis in a case study of a large conjugate strike-slip fault system from the intracratonic Tarim Basin, NW China. Within our study area, ＂X＂ type NE and NW trending faults occur within Cambrian- Ordovician carbonates. The dihedral angles of these conjugate faults have narrow ranges, 19~ to 62~ in the Cambrian and 26~ to 51~ in the Ordovician, and their modes are 42~ and 44~ respectively. These data are significantly different from the ~60~ predicted by the Coulomb fracture criterion. It is concluded that： （1） The dihedral angles of the conjugate faults were not controlled by confining pressure, which was low and associated with shallow burial; （2） As dihedral angles were not controlled by pressure they can be used to determine the shortening direction during faulting; （3） Sequential slip may have played an important role in forming conjugate fault intersections; （4） The conjugate fault system of the Tarim basin initiated as rhombic joints; these subsequently developed into sequentially active ＂X＂ type conjugate faults; followed by preferential development of the NW-trending faults; then reactivation of the NE trending faults. This intact rhombic conjugate fault system presents new insights into mechanisms of dihedral angle development, with particular relevance to intracratonic basins.

Fault diagnosis for distillation process based on CNN–DAE

Distillation is the most widely used operation for liquid mixture separation in the chemical industry. It is of great importance to detect and diagnose faults in distillation process. Due to the strong feedback and coupling of processes in a distillation column, it is difficult to use deep auto-encoders(DAEs) alone to achieve good results in detecting and diagnosing faults, in terms of accuracy and efficiency. This paper proposes a hybrid fault-diagnosis model based on convolutional neural networks(CNNs) and DAEs, by integrating the powerful capability of CNN in feature extraction and of DAE in classification. A case study was carried out with the distillation process of depropanization. It is shown that the proposed hybrid model is of good performance compared to other models, in terms of the accuracy of fault detection in such a process. Also, with the increase of structural layers of the CNN–DAE model, the diagnostic accuracy will be improved, with an optimal accuracy of 92.2%.

Expert fault diagnosis system for leaching process in zinc hydrometallurgy

Leaching process is the first step in zinc hydrometallurgy, which involves the complex chemical reactions for dissolving zinc bearing material in dilute sulfuric acid. Ensuring the safe running of the process is a key point in the operation. An expert fault diagnosis system for the leaching process was proposed, which has been implemented in a nonferrous metals smeltery. The system architecture and the diagnosis procedure were presented, and the rule models with the certainty factor were constructed based on the empirical knowledge, empirical data and statistical results on past fault countermeasures, and an expert reasoning strategy was proposed which employs the rule models and Beyes presentation and combines forward chaining and backward chaining. [

On-line Dynamic Model Correction Based Fault Diagnosis in Chemical Processes

<Abstract>A novel fault detection and diagnosis method was proposed, using dynamic simulation to monitor chemical process and identify faults when large tracking deviations occur. It aims at parameter failures, and the parameters are updated via on-line correction. As it can predict the trend of process and determine the existence of malfunctions simultaneously, this method does not need to design problem-specific observer to estimate unmeasured state variables. Application of the proposed method is presented on one water tank and one aromatization reactor, and the results are compared with those from the traditional method.

An aligned mixture probabilistic principal component analysis for fault detection of multimode chemical processes

A novel approach named aligned mixture probabilistic principal component analysis(AMPPCA) is proposed in this study for fault detection of multimode chemical processes. In order to exploit within-mode correlations,the AMPPCA algorithm first estimates a statistical description for each operating mode by applying mixture probabilistic principal component analysis(MPPCA). As a comparison, the combined MPPCA is employed where monitoring results are softly integrated according to posterior probabilities of the test sample in each local model. For exploiting the cross-mode correlations, which may be useful but are inadvertently neglected due to separately held monitoring approaches, a global monitoring model is constructed by aligning all local models together. In this way, both within-mode and cross-mode correlations are preserved in this integrated space. Finally, the utility and feasibility of AMPPCA are demonstrated through a non-isothermal continuous stirred tank reactor and the TE benchmark process.

Data Processing of Fault Recorder in Power System

This article studies the fault recorder in power system and introduces the Comtrade format. Andituses C++ programming to read recorded fault data and adopts Fourier analysis and symmetrical component method to filter and extract fundamental waves. Finally the effectiveness of the data processing method introduced in this paper is verified by CAAP software.

Fault monitoring based on mutual information feature engineering modeling in chemical process

A large amount of information is frequently encountered when characterizing the sample model in chemical process.A fault diagnosis method based on dynamic modeling of feature engineering is proposed to effectively remove the nonlinear correlation redundancy of chemical process in this paper.From the whole process point of view,the method makes use of the characteristic of mutual information to select the optimal variable subset.It extracts the correlation among variables in the whitening process without limiting to only linear correlations.Further,PCA(Principal Component Analysis)dimension reduction is used to extract feature subset before fault diagnosis.The application results of the TE(Tennessee Eastman)simulation process show that the dynamic modeling process of MIFE(Mutual Information Feature Engineering)can accurately extract the nonlinear correlation relationship among process variables and can effectively reduce the dimension of feature detection in process monitoring.

On the Kinematic Characteristics and Dynamic Process of Boundary faults of the Nansha Ultra-crust Layer-Block

Abstract The Nansha ultra-crust layer-block is confined by ultra-crustal boundary faults of distinctive features, bordering the Kangtai-Shuangzi-Xiongnan extensional faulted zone on the north, the Baxian-Baram-Yoca-Cuyo nappe faulted zone on the south, the Wan'an-Natuna strike-slip tensional faulted zone on the west and the Mondoro-Panay strike-slip compressive faulted zone on the east. These faults take the top of the Nansha asthenosphere as their common detachmental surface. The Cenozoic dynamic process of the ultra-crust layer-block can be divided into four stages: K2-E21, during which the northern boundary faults extended, this ultra-crust layer-block was separated from the South China-Indosinian continental margin, the Palaeo-South China Sea subducted southwards and the Sibu accretion wedge was formed; E22-E31, during which the Southwest sub-sea basin extended and orogeny was active due to the collision of the Sibu accretion wedge; E32-N11, during which the central sub-sea basin extended, the Miri accretion wedge was formed and “A-type” subduction of the southern margin of the north Balawan occurred; N12-the present, during which large-scale thrusting and napping of the boundary faults in the south and mountain-building have taken place and the South China Sea stopped its extension.

SEDIMENTARY PROCESS OF THE CENOZOIC BASIN AND ITS RESPONSE TO THE SLIP-HISTORY OF THE ALTYN TAGH FAULT, NW CHINA

The NEE\|striking Altyn Tagh Fault (ATF) has been well known as one major point to know the growth history of the Tibetan plateau. Lots of investigations done since 1970’s were mostly focus on active features, particularly on determining slip, slip rate and their distribution along the fault. However, Cenozoic slip\|history of this fault remains poorly understood, and the age of initiation and total offset are controversial. Several Cenozoic sedimentary basins develop in Suo’erkulinan to Mangya regions (Fig.1). Their sedimentary processes are closely related with the ATF. The studies of the Neogene sedimentary sequences and the reconstruction of the paleo\|geography are essential to establish the displacement history of the fault during Late Cenozoic.Located at the southern side of the ATF, the Suo’erkulinan basin consists of more than 600\|meter\|thick Pliocene Shizigou Formation below and about 120\|meter\|thick Early to Middle Pleistocene Qigequan Formation above according to the 1∶200000 geological map by Xinjiang Province. An obvious erosional surface can be seen on the top of the lower sequence. Sediments in the Shizigou Formation are characterized by 400\|meter\|thick yellow to red cobble\|sized conglomerates in the bottom, up\|grading to sandstones and grey\|green mudstones. This indicated that the sedimentary facies changed from alluvial fan to fluvial fan and sediments became more and more mature. The upper sequence, the Qigequan Formation, corresponds to an alluvial facies series composed of yellow to white cobble\|sized conglomerates intercalated with lenticular sandstones. Paleo\|current indicators showed that the Shizhigou conglomeratic series were sourced from northwest. Well\|developed syn\|sedimentary faults, normal faults mostly inherited from syn\|sedimentary faults, and some striation lineations on the surface indicated transtensional tectonic environment of the strike\|slip faulting.

基于深度置信网络的多模态过程故障评估方法及应用

传统的多模态过程故障等级评估方法对模态之间的共性特征考虑较少,导致当被评估模态故障信息不充分时,评估的准确性较低.针对此问题,首先,提出一种共性–个性深度置信网络(Common and specific deep belief network,CS-DBN),该网络充分利用深度置信网络(Deep belief network,DBN)的深度分层特征提取能力,通过度量多模态数据间分布的相似性和差异性,进一步得到能够反映多模态过程共有信息的共性特征以及反映每个模态独有信息的个性特征;其次,基于CS-DBN,利用多模态过程的已知故障等级数据生成多模态共性–个性特征集,通过加权逻辑回归构建故障等级评估模型;最后,将所提方法应用于带钢热连轧生产过程的故障等级评估中.应用结果表明,随着多模态故障等级数据的增加,所提方法的评估准确率逐渐增加,当故障信息充足时,评估准确率可达98.75%;故障信息不足时,与传统方法相比,评估准确率提升近10%.

The research on the space-time coherence of Xianshuihe fault zone in the process of seismogeny

In this paper, a kind of data analysis method is used to research the space time coherence of Xianshuihe fault zone in the process of seimogeny. It is proved that, the space time coherence of Xianshuihe fault zone, in the process of seismogeny, really exists. The greater the earthquake magnitude of a fault section, the greater is its influence on the 'neighboring' sections. To a strike fault zone which bears compressive stress, the fault sections are 'series connected'. That is to say, once an earthquake happens on a fault section, the time of seismogeny in the neighboring fault sections will be shortened, therefore, this earthquake has 'an effect of hastening the occurrence of earthquakes in neighboring fault sections'. It is an inevitable rule for the Xianshuihe fault zone that the earthquake quiescent period and the earthquake active period occur alternatively. To the Xianshuihe fault zone, the slip predictable model does not tally with the actual situation, while the improved time predictable model tallies with the fact quite well. The data analysis method used here, which is used to examine the earthquake prediction models, is put forward on the basis of historical earthquake records. This kind of method and the relative conclusions have important reference value on the establishment of earthquake prediction models.

走滑断裂带三维地震特征增强处理与描述研究

走滑断裂带由于纵向断距小,超深层地震信号弱,常规叠前深度偏移地震资料难以满足超深层断裂带精细描述需求。为提高断裂带成像精度,指导走滑断裂带解释描述和评价部署,以顺北地区走滑断裂带发育区三维地震资料为例,建立了一套以提高地震资料品质的保真保幅优化处理、频谱恢复提高分辨率处理、频谱分解处理、频率域多尺度断裂检测等技术为主的走滑断裂带地震特征增强处理与描述技术,该技术组合有效拓宽了地震数据频带,提高了地震数据分辨率,使超深走滑断裂带成像精度更高,为超深走滑断裂带的精细解释、描述评价、三维雕刻提供了高品质资料基础。结合顺北地区前人研究成果,综合利用频谱恢复提高分辨率处理、频谱分解处理、频率域断裂检测数据,不同尺度断裂带特征及断储关系预测效果更好,为进一步评价断裂带和部署井位提供了技术支撑。

顺北油田分支断裂及断控储层的识别与描述研究

顺北油气田是断裂控制的断控油气田,其中不少断层发育有分支断裂。分支断裂在常规地震资料上难以发现,属于断距小或者说是比较隐蔽的断裂。因这些断裂带形态与分布不清,断控储集体特征也不清楚,从而使得储层预测与目标优选困难。如何对这类断裂开展识别和描述,进而开展储层预测和目标评价,本次研究尝试从多种方法的组合使用入手,通过反复试验发现,把时频谱蓝化提高地震分辨率处理与方向性边界保持断层增强处理组合使用,能有效提高地震资料分支断裂的识别能力;把梯度结构张量断裂检测处理与最大似然属性断裂检测处理组合使用能很好地对分支断裂进行描述与刻画;把结构张量属性分析与缝洞增强处理组合使用能很好地对洞穴型储层进行有效刻画;GST(Gradient Structural Tensor)相干属性与不连续性属性联合使用实现了对孔洞型储层的预测;体曲率+最大似然属性组合使用实现了对裂缝型储层预测与描述;在不同类型储层预测基础上,通过不同类型储层的叠合得到的总储层预测。

区域地震记录揭示的2023年甘肃积石山6.2级地震震源破裂过程

基于有限断层模型反演方法,利用区域宽频带地震波形数据,反演了2023年12月18日甘肃临夏积石山6.2级地震的震源破裂过程,获得了积石山地震破裂滑动时空分布:此次地震是逆冲兼少量走滑型地震,破裂持续时间约为9 s,主体能量在前6 s释放,地震破裂主要沿断层走向向NW方向拓展,计算得到的标量地震矩为1.39×10^(18)N·m,相当于M_(W)6.02,破裂尺度约10 km左右,最大同震滑动量为35 cm。