由于水压试验机是一个复杂的高压系统,该类系统发生事故不仅会影响生产的可靠运行而且会造成人员和财产的巨大损失。因此,研究切实可行的水压试验机故障预测方法,对保证生产安全可靠运行具有重要意义。针对一些液压元件故障具有批次间渐变的特点,提出了基于多元统计技术与时间序列结合的缓变故障预测方法。该方法通过建立T^2及Q统计量的自回归模型,预测下一批次统计量值,将所求值与控制限对比进而实现渐变故障的预测。采用水压试验机实际生产过程数据对该方法进行仿真研究,仿真结果验证了该方法的有效性。
As a complex high-pressure system, the failure of hydraulic tube tester will not only seriously affect the safety of process operation, but also result in huge loss of personnel and wealth. Therefore, it is significant to study feasible fault prediction methods, which will guarantee the safe reliability of the production. According to the gradual property of hydraulic component faults over batches, a fault prediction method is developed based on multivariate statistical technique and time series analysis. The statistical values of the next batch are estimated by building the autoregressive models of T^2 and Q statistics, and then compared with the control limits, so that the gradual faults can be predicted. The effectiveness of the proposed method is emulated by applying it in process data.