Fault prediction for nonlinear stochastic system with incipient faults based on particle filter and nonlinear regression

Ding, Bo; Fang, Huajing

doi:10.1016/j.isatra.2017.03.018

Cited by 34 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structure and principle of the 3‐tank system can be shown in our previous work . The discrete state equations of the 3‐tank system is described as

({, \begin{matrix} array h_{1, k + 1} = h_{1, k} + T / A (Q_{1} - Q_{13}) + w_{1, k} \\ array h_{2, k + 1} = h_{2, k} + T / A (Q_{2} + Q_{32} - Q_{20}) + w_{2, k} \\ array h_{3, k + 1} = h_{3, k} + T / A (Q_{13} - Q_{32}) + w_{3, k}, \end{matrix})

where T is the sampling interval of the system; A is the cross‐sectional area of tanks; h i ( i =1,2,3) are the water level of each tank; Q 1 and Q 2 are incoming mass flow; w k is a vector of process noise having 3 components and a covariance of Q k ; Q i j is the mass flow from the i th tank to the j th tank, and given as

({, \begin{matrix} array Q_{13} = a z_{1} s sgn (h_{1} - h_{3}) \sqrt{2 g |h_{1} - h_{3}|} \\ array Q_{32} = a z_{3} s sgn (h_{3} - h_{2}) \sqrt{2 g |h_{3} - h_{2}|} \\ array Q_{20} = a z_{2} s \sqrt{2 g h_{2}}, \end{matrix})

where s is the cross‐sectional area of pipe; a z i ( i =1,2,3) are the flow coefficients of each pipe; and g represents the acceleration of gravity.…”

Section: Simulationsmentioning

confidence: 99%

See 1 more Smart Citation

Fault estimation and prediction for nonlinear stochastic system with intermittent observations

Ding

Fang

2017

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

Summary This paper is concerned with the fault estimation and prediction problems for a class of nonlinear stochastic systems with intermittent observations. Based on the extended Kalman filter and Kalman filter, the fault and state are simultaneously estimated, and then, it is extended to the case of intermittent observations. Meanwhile, the boundedness of the estimation error is also discussed. Once the fault is detected, the parameters of each fault are identified by the linear regression method. Then, the future fault signal can be predicted by the parameters of the fault. The effectiveness of the proposed algorithm is verified by the simulation of the 3‐tank system.

show abstract

“…The structure and principle of the 3‐tank system can be shown in our previous work . The discrete state equations of the 3‐tank system is described as

({, \begin{matrix} array h_{1, k + 1} = h_{1, k} + T / A (Q_{1} - Q_{13}) + w_{1, k} \\ array h_{2, k + 1} = h_{2, k} + T / A (Q_{2} + Q_{32} - Q_{20}) + w_{2, k} \\ array h_{3, k + 1} = h_{3, k} + T / A (Q_{13} - Q_{32}) + w_{3, k}, \end{matrix})

({, \begin{matrix} array Q_{13} = a z_{1} s sgn (h_{1} - h_{3}) \sqrt{2 g |h_{1} - h_{3}|} \\ array Q_{32} = a z_{3} s sgn (h_{3} - h_{2}) \sqrt{2 g |h_{3} - h_{2}|} \\ array Q_{20} = a z_{2} s \sqrt{2 g h_{2}}, \end{matrix})

where s is the cross‐sectional area of pipe; a z i ( i =1,2,3) are the flow coefficients of each pipe; and g represents the acceleration of gravity.…”

Section: Simulationsmentioning

confidence: 99%

“…The structure and principle of the 3-tank system can be shown in our previous work. 38 The discrete state equations of the 3-tank system is described as…”

Section: Plant Descriptionmentioning

confidence: 99%

Fault estimation and prediction for nonlinear stochastic system with intermittent observations

Ding

Fang

2017

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

show abstract

“…The literature [12] deeply analyzed the causes of failures and analyzed the relationship between the causes of failures and environmental attributes, then evaluated the impact of failure prediction on overall performance prediction, finally, established a failure prediction model. According to the literature [13][14][15][16][17][18][19], these methods do not need a thorough examination of the mechanism of equipment fault and fall within the black box concept. When the number of samples is insufficient, it is difficult to establish an accurate fault prediction model.…”

Section: Introductionmentioning

confidence: 99%

Fault Critical Point Prediction Method of Nuclear Gate Valve with Small Samples Based on Characteristic Analysis of Operation

Liu

et al. 2022

Materials

View full text Add to dashboard Cite

The number of fault samples for the new nuclear valve is commonly rare; thus, the machine learning algorithm is not suitable for the fault prediction of this kind of equipment. In order to overcome this difficulty, this paper proposes a novel method for the fault critical point prediction of the gate valve based on the characteristic analysis of the operation process variables. The operation process of gate valve switch often contains various fault characteristics and information, and this method first adopts the Shannon entropy to describe the power spectrum of vibration signal relevant to the operation process of gate valve switch, and then employs the mean value of the power spectrum entropy as an indirect process variable and further investigates the differences between the indirect process variable under the healthy state and the fault state with a different fault degree. In addition, the power signal of the gate valve is also employed as the direct process variable and the features of the direct process variable under the healthy state and the fault state with different fault degrees are also investigated. Based on the previous indirect process variable and direct process variable, the prediction approach for the critical point of the gate valve fault is established by analyzing the change in the indirect process variable and direct process variable before and after faults. Finally, the data of a nuclear gate valve experiment are employed to demonstrate the feasibility of the proposed method and the results show that the proposed method can effectively predict the fault critical point of the mentioned nuclear gate valve. If the diagnostic threshold is set properly, the critical point prediction of a nuclear gate valve fault can be realized as 100% or close to 100%. Furthermore, the proposed method can be directly applied to the nuclear gate valve in a nuclear power plant to improve the operation reliability of the valve. At the same time, the method can be applied to the fault diagnosis and prediction of valves in other fields, such as the chemical industry.

show abstract

“…To reduce the errors caused by task scheduling, Ji and Wang [8] designed a fault prediction method for workshop scheduling by big large data analysis. Ding and Fang [9] proposed a fault estimation algorithm based on a particle filter, through the study of the fault prediction of nonlinear stochastic systems with initial faults. Yue et al [10] proposed a fault prediction method based on kernel function, which is used to evaluate the network performance of Ribbon WSN.…”

Section: Introductionmentioning

confidence: 99%

“…The observational data of the system state is analyzed. Combined with the system identification and optimization theory, the fault prediction model is established, such as Bayesian [5], [6], neural network [11], particle filter [9], time series [7], and deep learning [12]. The methods do not need to understand the internal mechanisms of the system before modeling, and the accuracy of the model is improved by training samples.…”

Section: Introductionmentioning

confidence: 99%

Fault Prediction Method for Wireless Sensor Network Based on Evidential Reasoning and Belief-Rule-Base

Chen

Zhou

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Wireless sensor network (WSN) is a distributed intelligent network, which can independently achieve the information collection task of monitoring targets. However, the WSN is susceptible to faults due to various factors, such as sensor resources, network bandwidth, and work environment. The WSN fault prediction technology can estimate the fault trend of the WSN, which can provide the basis for the formulation and implementation of emergency strategies. In this paper, a new WSN fault prediction method is proposed based on evidential reasoning (ER) and belief rule base (BRB). First, the process of the WSN fault prediction is described, which mainly includes the fault assessment of the current WSN and the fault prediction of future WSN. Second, the WSN fault prediction model is constructed, including the ER-based fault assessment model and BRB-based fault prediction model. The projection covariance matrix adaptation evolutionary strategies (P-CMA-ESs) are used to optimize model parameters. Finally, a case study is constructed to verify the validity of the WSN fault prediction model. The experimental results show that the model can adequately estimate the fault state of the current WSN and then predict the fault status of future WSN. INDEX TERMS Fault prediction, belief rule base (BRB), fault assessment, evidential reasoning (ER) wireless sensor network (WSN).

show abstract

Fault prediction for nonlinear stochastic system with incipient faults based on particle filter and nonlinear regression

Cited by 34 publications

References 21 publications

Fault estimation and prediction for nonlinear stochastic system with intermittent observations

Fault estimation and prediction for nonlinear stochastic system with intermittent observations

Fault Critical Point Prediction Method of Nuclear Gate Valve with Small Samples Based on Characteristic Analysis of Operation

Fault Prediction Method for Wireless Sensor Network Based on Evidential Reasoning and Belief-Rule-Base

Contact Info

Product

Resources

About