Figure 5
A scatter plot titled SHAP Summary Plot illustrating the contribution of individual features to anomaly prediction. The plot features multiple data points, each representing a feature's impact on the model output. The x-axis represents SHAP values, indicating the impact on model output, ranging from negative to positive values. The y-axis lists various features, including xmarms_mean, zmarms_max, S_Axis_Load_mean, xmarms_max, smarms_std, smarms_mean, zmarms_mean, ymarms_max, xmarms_std, ymarms_std, watt_max, S_Axis_Load_std, N, energy_mean, ymarms_mean, UDI, energy_std, watt_mean, smarms_max, and watt_std. Data points are color-coded from blue to red, indicating low to high feature values. Vibration-related variables such as xmarms_mean, zmarms_max, and S_Axis_Load_mean exhibit the greatest influence on model output, suggesting that machining anomalies are primarily governed by dynamic machine behavior.SHAP summary plot illustrating the contribution of individual features to anomaly prediction. Vibration-related variables, including xmarms_mean, zmarms_max, S_Axis_Load_mean, and smarms_std, exhibit the greatest influence on model output, confirming that machining anomalies are primarily governed by dynamic machine behaviour rather than nominal cutting parameters