Abstract: In order to monitor the changes in water level in the air chamber of a jigs machine in real time and accurately, a method for online monitoring of water level in the air chamber of a jigs machine considering multi-sensor fusion is proposed. Firstly, deploy water level monitoring sensors in the air chamber of the jigs. Secondly, by utilizing the state estimation characteristics and relevant historical information of the Kalman filter algorithm, the estimated values of the state are made closer to the true values, completing multi-sensor dynamic data fusion. Considering that serious conflicts in sensor data can cause the fusion results to deviate from the true values. Introducing D-S theory to quantify the inconsistency between data through conflict factors, using improved combination rules to redistribute the weights of conflict data, and arbitrating the preliminary fusion results of Kalman filtering at the decision-making level to achieve conflict data decision-making. Finally, the improved random forest algorithm is applied to achieve online monitoring of the water level in the air chamber of the jig. Experimental studies have shown that the proposed method can obtain more accurate online monitoring results of the water level in the air chamber of the jigs.