A Novel Prognostic Model of the Degradation Malfunction Combining a Dynamic Updated-ARIMA and Multivariate Isolation Forest: Application to Radar Transmitter

Abstract

In the prognosis of radar transmitter degradation malfunction, there are some restrictions, such as the fact that it is difficult to obtain fault samples and the monitoring data cannot reach the fault threshold. For these restrictions, a novel data-driven prognostic method is proposed to predict the radar transmitter degradation malfunction, in which the dynamic updated-auto-regressive integrated moving average is proposed to be used to predict the subsequent time-step of the microwave measurement historical data, and the multivariate isolation forest established without fault samples is used to detect the degradation malfunction. The validity and portability of the model are verified using two-type of degradation malfunction prognostic experiments. The experimental results show that the degradation malfunction can be predicted at least 10 time-steps (100 min) before the occurrence of a degradation malfunction. Compared with the existing radar degradation malfunction prediction methods, the proposed method needs less historical data, no fault samples, no artificial thresholds, and no extracting features. This method can complete a degradation malfunction prognosis when there are relevant restrictions.

Simplified Framework for Fault Prediction in Radar Transmitter based on Vector Autoregression Model

“…This is to allow fair comparison. It is observed that the average RMSE of the proposed method for S1 in both faults is less than that of Zhai et al (2022). However, Zhai et al (2022) shows better prediction performance in S2.…”

“…To demonstrate the performance of the proposed framework, we used the fault data from Zhai et al (2022).…”

“…In Table 1, the RMSE of the proposed framework without increasing the data size is compared to existing methods from Zhai et al (2022) and Zhai and Fang (2020). This is to allow fair comparison.…”

“…In a more recent study, Zhai, Liu, Cheng, and Fang (2022) extended the prognostic model in Zhai et al (2021) by using a multivariate isolation forest to determine the performance degradation of the radar transmitter. In addition, a modified auto-regressive integrated moving average (DU-ARIMA) with the capability to dynamically update itself, was used to predict future values of the monitored quantities before applying the multivariate isolation forest.…”

“…In addition, a modified auto-regressive integrated moving average (DU-ARIMA) with the capability to dynamically update itself, was used to predict future values of the monitored quantities before applying the multivariate isolation forest. Although, the root mean square error (RMSE) of the method in Zhai et al (2022) is less than the LSTM-based method in Zhai and Fang (2020), the superior performance may not be guaranteed when the data is large. Secondly, the prediction of the future values of the monitored quantities using univariate prediction model (DU-ARIMA) did not explore the interdependencies between the monitored quantities.…”