通过对上图进行分析发现，进行4阶差分计算后，监测数据的自相关系数与偏自

Through the analysis of the above figure, it is found that after the fourth-order difference calculation, the phenomenon that the autocorrelation coefficient and the partial autocorrelation coefficient of the monitoring data have a lagging point has been significantly improved. In order to determine the values ​​of the autoregressive term (p) and the moving average term (q) of the model, the grid search method is used to select the value range of the autoregressive term as 2≤p≤8 and the value range for the moving average term as 2≤q The data model ≤8 is searched and calculated, and there are 36 sets of data models in total, and the model parameters are optimized using Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC). When p=5 and q=4, the model's AIC value and BIC value are both the smallest (AIC=1706.01, BIC=1743.15). Therefore, the model parameters are determined to be p=5, d=4, and q=4. At this time, the residual value of the model basically presents the characteristics of white noise, as shown in Figure 10.

Through the analysis of the above figure, it is found that after the calculation of the 4th order difference, the phenomenon of the lag between the self-correlation coefficient and the partial correlation coefficient of the monitoring data has been significantly improved. In order to determine the value of the model's self-regression item (p) and sliding average item (q), the data model with the self-regression item value range of 2≤p≤8 and the sliding average item value range of 2≤q≤8 was searched and calculated by grid search method. When p is 5, q is 4, the AIC value of the model is the smallest at the same time as the BIC value (AIC is 1706.01, BIC is 1743.15), so the model parameters are determined to be p-5, d-4, q-4. At this point, the residual value of the model is basically white noise characteristics, as shown in Figure 10.

Through the analysis of the above figure, it is found that the phenomenon of lag point exists in the autocorrelation coefficient and partial autocorrelation coefficient of the monitoring data after the fourth order difference calculation, which has been significantly improved. In order to determine the values of autoregressive term (P) and moving average term (q), a grid search method was used to search and calculate the data models with the range of autoregressive term (2 ≤ P ≤ 8) and moving average term (2 ≤ Q ≤ 8). A total of 36 groups of data models were selected to optimize the model parameters by using the red pool information criterion (AIC) and Bayesian information criterion (BIC). When p = 5 and q = 4, the AIC and BIC values of the model are the minimum at the same time (AIC = 1706.01, BIC = 1743.15). Therefore, the model parameters are determined as P = 5, d = 4, q = 4. At this time, the residual value of the model basically presents the characteristics of white noise, as shown in Figure 10.<br>