Fault Identification Unit Research Articles

ECOC-based integrated learning method for fault diagnosis in nuclear power plants

Abstract The fault diagnosis system of nuclear power plants plays an important role in ensuring the safety and economy of nuclear power plant operations. This paper first analyzes typical faults of nuclear power plants and their phenomena, and fault samples are obtained. A comprehensive study of the structure of the nuclear power plant system, its working mode and the association between each subsystem is carried out to analyze the monitoring parameters and fault characteristics and establish the fault data set. Secondly, an IFWA (Improved Fireworks Algorithm - Integrated Learning) algorithm is proposed to assess the severity of faults in the first circuit of a nuclear power plant. Finally, the fault diagnosis module is divided into three units according to the functional logic, i.e., condition monitoring unit, fault identification unit, and fault severity assessment unit. The results show that the diagnostic accuracy of the IFWA algorithm is 94.25% for SGTR in the single-fault diagnosis experiment and 96.25% for SGTR-LOCA in the multiple-fault diagnosis experiment. It shows that the IFWA algorithm proposed in this paper has the optimal performance capability when applied to nuclear power plant fault diagnosis and effectively assists managers in diagnosing faults and giving maintenance recommendations.

Convolutional Neural networks based on parallel multi-scale pooling branch: A transfer diagnosis method for mechanical vibrational signal with less computational cost

Traditional fault diagnosis models based on machine learning technology are difficult to apply to data samples under different working conditions. In a working environment that can only provide less computational resources, the parameter scale of algorithms is restricted, and the difficulty of transfer diagnosis is further increased. To this end, this paper proposes a transfer diagnosis method based on PMSPB-CNN (Convolutional Neural Networks Based on Parallel Multi-scale Pooling Branch) to solve the mechanical vibrational signal fault diagnosis problem under multiple working conditions with less computational cost. PMSPB-CNN introduces a parallel multi-scale pooling branch (PMSPB) structure to replace the basic convolution module used in traditional 1D-CNN. The multiple parallel paths in PMSPB structure contain the pooling layers with different scales and pooling methods to mine high-level features with different granularities. There are no network parameters that need to be trained in this structure, which greatly saves computational resources and reduces the risk of overfitting. Based on the transfer learning strategy of freezing the pretrained feature mining unit and fine-tuning the parameters of the fault identification unit, PMSPB-CNN can perform high-accuracy fault diagnosis on similar fault samples under multiple working conditions. The experimental results show that the parameter number of PMSPB-CNN is 774, and the number of parameters that need to be re-optimized for transfer diagnose is only 360. However, compared with the existing methods, even if the pre-trained network is directly used to diagnose faults under the other working conditions, the accuracy of PMSPB-CNN still maintain a high level on the two verification datasets, reaching 73.2% and 97.8% respectively. After fine-tuning the fault identification unit, PMSPB-CNN can achieve the 100% transfer diagnosis accuracy. In addition, the mechanism analysis experimental results show that when dealing with the data under different working conditions, the pooling layer in PMSPB structure with the best classification performance is not exactly the same. Furthermore, the output features of the frozen feature mining unit already highly recognizable before fine-tuning the fault identification unit. These conclusions proved that PMSPB structure provides sufficient fault tolerance and flexibility for the network, thereby improving the generalization of PMSPB-CNN.

A traveling-wave-based protection scheme for the bipolar voltage source converter based high voltage direct current (VSC-HVDC) transmission lines in renewable energy integration

The voltage source converter based high voltage direct current (VSC-HVDC) technology is a feasible solution to realize wide-area complementarity and flexible consumption of the renewable clean energy resources but DC line faults are crucial problems. The traditional traveling wave protection for HVDC transmission lines are easily affected by the fault resistance and signal noise. Besides, it cannot detect the double-pole-to-ground fault. To overcome these problems, a single-ended protection scheme based on the phase-mode transformation and wavelet transform modulus maximum (WTMM) theories for DC lines in the VSC-HVDC transmission system is proposed in this paper. The protection scheme includes the protection startup unit, the internal fault identification unit, and the faulty pole detection unit. Extensive simulation tests carried out in PSCAD/EMTDC verify that the protection scheme has high selectivity in the high fault resistance faults, remote faults, and close-by faults with different fault types. And it does not rely too much on data synchronization. Furthermore, sensitivity analysis and comparisons with other methods indicate that the protection is insensitive to signal noise and suitable for different operational modes. And the effectiveness of the protection is independent of the high sampling frequency. Moreover, it can identify the double-pole-to-ground fault correctly.

Robust fault diagnosis for switched systems based on sliding mode observer

In this paper, the robust fault diagnosis for switched systems is studied based on sliding mode observers, taking the DC–DC power electronic converter as an example. According to the switched system mode, a sliding mode observer is designed through linear matrix inequalities to detect the fault. The fault identification unit not only locates the faulty component, but also realizes the identification of the faulty component parameter. For different components of the system, a series of adaptive sliding mode observers are designed to determine the location of fault. At the same time, an appropriate adaptive law is selected to estimate the parameters of the components. Finally, the proposed method is proved to be effective by an example of power electronic DC-DC boost converter.