The instrument fault detection and identification based on kernel principal component analysis and coupling analysis in process industry

Data-driven fault detection and identification methods are important in large-scale chemical processes. However, some traditional methods often fail to show superior performance owing to the self-limitations and the characteristics of process data, such as nonlinearity, non-Gaussian distribution, and multi-operating mode. To cope with these issues, the k-NN (k-Nearest Neighbor) fault detection method and extensions have been developed in recent years. Nevertheless, these methods are primarily used for fault detection, and few papers can be found that examine fault identification. In this paper, in order to extract effective fault information, the relationship between various faults and abnormal variables is studied, and an accurate “fault–symptom” table is presented. Then, a novel fault identification method based on k-NN variable contribution and CNN data reconstruction theories is proposed. When there is an abnormality, a variable contribution plot method based on k-NN is used to calculate the contribution index of each variable, and the feasibility of this method is verified by contribution decomposition theory, which includes a feasibility analysis of a single abnormal variable and multiple abnormal variables. Furthermore, to identify all the faulty variables, a CNN (Center-based Nearest Neighbor) data reconstruction method is proposed; the variables that have the larger contribution indices can be reconstructed using the CNN reconstruction method in turn. The proposed search strategy can guarantee that all faulty variables are found in each sample. The reliability and validity of the proposed method are verified by a numerical example and the Continuous Stirred Tank Reactor system.

Transmission Line Fault Detection and Identification in an Interconnected Power Network using Phasor Measurement Units

It is of critical importance to keep a steady operation in the blast furnace to facilitate the production of high quality hot metal. In order to monitor the state of blast furnace, this article proposes a fault detection and identification method based on the multidimensional Gated Recurrent Unit (GRU) network, which is a kind of recurrent neural network and is highly effective in handling process dynamics. Comparing to conventional recurrent neural networks, GRU has a simpler structure and involves fewer parameters. In fault detection, a moving window approach is applied and a GRU model is constructed for each process variable to generate a series of residuals, which is further monitored using the support vector data description (SVDD) method. Once a fault is detected, fault identification is performed using the contribution analysis. Application to a real blast furnace fault shows that the proposed method is effective.

Mode changes in today's sophisticated industrial processes result in unanticipated shutdowns, which could reduce the lifespan of critical machinery and result in high maintenance costs. A technique that can identify the fault of equipment operating in various modes is needed to prevent this issue. In light of this, we suggest a novel fault detection technique that makes use of the k-nearest neighbor normalization-based weight local outlier factor (WLOF). The suggested approach carries out local normalization using neighbors to take into account potential mode changes in the normal data, and WLOF is used for fault detection. In contrast to statistical methods, such as principal component analysis (PCA) and independent component analysis (ICA), the local outlier factor (LOF) uses the density of neighbors. However, conventional LOF is greatly affected by the distance between its neighbors, performance may deteriorate when faulty data is adjacent to normal data. To improve the defect detection performance of LOF, the proposed method multiplies proportionally by the distance between each neighbor. A circulating fluidized bed boiler and a multimode numerical case were used to assess the effectiveness of the suggested method. The results of the experiments demonstrate that the suggested method performs better than conventional PCA, kernel PCA (KPCA), k-nearest neighbor (kNN), and LOF. In particular, compared to conventional techniques, the suggested method increased detection accuracy by 20%. Therefore, the proposed technique is applicable to a real process operating in multiple modes.

This paper proposes a methodology for providing fault tolerance to Petri net controllers. In order to provide tolerance against faults that may compromise the functionality of the Petri net controller, we construct a redundant Petri net embedding that allows the detection and identification of place and transition faults. A place fault results in an incorrect token-load of a place, and a transition fault arises when the token-load of either the input or output place-set of a transition is not appropriately updated following the firing of a transition. The resulting Petri net controller implementations use redundant places, connections and tokens to impose invariant conditions that allow the detection and identification of faults via linear parity checks. The proposed methodology is attractive because the redundant Petri net controller makes efficient use of redundancy and allows for the systematic detection and identification of faults. More specifically, the use of d redundant places enables the detection and identification of up to d - 1 transition faults and up to [d/2] place faults.

Satellite Navigation Receiver Autonomous Integrity Monitoring (RAIM) is developed for detection and recognition of satellite faults using the redundant observation values of receiver itself. This article first makes a comparative analysis to the conventional and recently proposed RAIM fault detection and identification methods, and then points out that the conventional fault identification methods have such weakness as low fault detection probability and high false alarm probability in the situation of simultaneous multiple faulty satellites, while the recently proposed multi-satellite fault identification methods require excessive computation work though enjoy a higher detection probability. To solve these problems, a new RAIM multiple satellite fault detection and recognition method is proposed in this paper, which is characterized by high detection probability, low false alarm probability and low computation load, practicable for project implementation. Based on a simulation analysis, it turns out that this method has a higher detection probability without false alarm at all. This method requires so low computation work that it only needs 2 m times of least squares residuals fault detection and m times of fault identification in m (m > 0) faulty satellites situation, showing a very promising application value.

The day-by-day increase in digital loads draws attention towards the need for an efficient and compatible distribution network. An LVDC distribution network has the capability to fulfill such digital load demands. However, the major challenge of an LVDC distribution network is its vulnerability during a fault. The need for a high-speed fault detection method is inevitable before it can be widely adopted. This paper proposes a new fault detection method which extracts the features of the current during a fault. The proposed fault detection method uses the merits of overcurrent, the first and second derivative of current, and signal processing techniques. Three different features are extracted from a time domain current signal through a sliding window. The extracted features are based upon the root squared zero, second, and fourth order moments. The features are then set with individual thresholds to discriminate low-, high-, and very high-resistance faults. Furthermore, a fault is located through the superimposed power flow. Moreover, this study proposes a new method based on the vector sum of positive and negative pole currents to identify the faulty pole. The proposed scheme is verified by using a modified IEEE 13 node distribution network, which is implemented in Matlab/Simulink. The simulation results confirm the effectiveness of the proposed fault detection and identification method. The simulation results also confirm that a fault having a resistance of 1 m Ω is detected and interrupted within 250 μ s for the test system used in this study.

In this paper a smart remote sensing prototype for fault detection and identification of photovoltaic arrays is presented. A simple fault detection and identification algorithm has been incorporated into the designed prototype. The designed system detect automatically the fault, and then identify the origin of some investigated faults (such as open circuit, short circuit, dust accumulation and shedding effect). The prototype has been tested experimentally at the Renewable Energy Laboratory of Jijel University, Algeria. The experimental results showed the capability of the prototype to remote sensing, detecting and faults identification. The status of the system can be checked online via a website using Internet of Things (IoT) and the user could be also notified by a SMS.

Wind turbine fault detection and identification using a two-tier machine learning framework

This paper focuses on Kernel Principal Component Analysis (KPCA) in order to solve the problem of sensor fault detection and identification without linear relationship between sensors. After samples are projected into high-dimensional space, new Principal Component Analysis (PCA) model is established in the kernel principal component eigenvector space. By the contrast with SPE, Hotelling T2 is an appropriate parameter to detect sensor fault because it is more sensitive to sensor failure. The contribution of different sensor to Hotelling T2 is utilized to identify sensor fault for the faulty sensor’s contribution is large than others significantly. Finally, the proposed method is illustrated by the sensors of oil-providing system in the process of aero-engine ground testing. Experiment results show the applicability and effectiveness of the proposed method.

This paper proposes a novel fault detection algorithm in a brushless DC (BLDC) motor drive system. This proposed method is configured without the additional sensor for fault detection and identification. The fault detection and identification are achieved by a simple algorithm using the operating characteristic of the BLDC motor. The drive system after the fault identification is reconfigured by four-switch topology connecting a faulty leg to the middle point of DC-link using bidirectional switches. This proposed method can also be embedded into existing BLDC motor drive system as a subroutine without an excessive computational effort. The feasibility of a novel fault detection algorithm is validated in simulation and experiment.

Fault discriminant enhanced kernel principal component analysis incorporating prior fault information for monitoring nonlinear processes

In this paper, a novel sensor fault detection and identification technique based on kernel principal component analysis (KPCA) and its fast data reconstruction is presented. Although it has been proved that KPCA shows a better performance for sensor fault detection, the fault identification method has rarely been developed. Using the fast data reconstruction based on distance constraint, we employ the residuals of variables to identify the faulty sensor. Since the proposed method does not include iterative calculation, it has a lower calculation burden and is more suitable for online application. The simulation results show that the proposed method effectively identifies the source of typical sensor faults.

This work compares different data-driven methods for fault detection and identification of rotor failures in multicopters. The fault detection and identification methods employed in this study are based on response-only signals of the aircraft state, as the external excitation due to ambient turbulence is non-observable. Knowledge based methods using the knowledge of aircraft dynamics in the event of rotor failure is studied. A concise overview of the development of statistical time series models using the aircraft attitudes and statistical hypothesis testing to detect and classify rotor failures is presented. These methods are compared with neural networks trained on different parts of the response signals to achieve online fault detection identification of rotor failures in a hexacopter with respect to speed and accuracy of fault classification. It is shown that using a combination of statistical time series model for healthy aircraft and neural networks employed for online monitoring results in fault detection and identification in less than 0.3 s with an accuracy of 99.3%.

Fault identification and diagnosis based on KPCA and similarity clustering for nuclear power plants