Search

A reliable braking system is an important guarantee for safe operation of mine hoist. In order to make full use of the monitoring data in the operation process of mine hoist, identify its operation status and further diagnose its fault, the deep learning method was introduced into the fault diagnosis of the hoist, and a fault diagnosis method of hoist braking system based on convolutional neural network (CNN) was proposed. First, the failure mechanism of the hoist braking system was analyzed, the monitoring parameters were determined, and the monitoring data under the normal state and fault simulation state of the hoist were collected. Then, a fault diagnosis model of the hoist braking system based on CNN was established. The monitoring data is encoded to generate a fault diagnosis data set, and the neural network is trained by the gradient descent method, and the structural parameters of the network are updated iteratively. Finally, the traditional back propagation (BP) neural network and CNN fault diagnosis model were compared and verified by test data set. The results show that the accuracy of CNN is higher than that of BP neural network, and the accuracy rate can reach 99.37%. This method can make full use of the monitoring data for diagnosis, without subjective intervention of experts, thus improving the accuracy of diagnosis.

BackgroundThe national essential public health services have been implemented since 2009 as a key initiative of the new round of China's healthcare reform. With the development of this service program, the allotted special funds and service items are increasing. Due to large number of indicators involved and wide coverage, it is imperative to explore a method that can assess the services scientifically, objectively and comprehensively.ObjectiveTo explore an appropriate method for comprehensively assessing the quality of national essential public health services, providing a basis for improving relevant policies and the quality of such services.MethodsBy use of multistage and purposive sampling, 24 community (township) health centers were selected from southern, central and northern Z Province from February to April 2019, and qualities of national essential public health services delivered by them in 2018 were comprehensively assessed using the technique for order of preference by similarity to ideal solution (TOPSIS) , rank-sum ratio (RSR) method, and fuzzy combination of TOPSIS and RSR method, respectively. With reference to the 2018 National Basic Public Health Service Project, 12 evaluation indicators were selected.ResultsAccording to the TOPSIS-based assessment, the top three community (township) health centers ranked by Ci value were A (0.917 4) , C (0.875 9) and G (0.787 9) , and the bottom three were I (0.414 2) , W (0.413 7) and N (0.407 7) . In accordance with the RSR method-based assessment, the top three community (township) health centers ranked by RSR value were A (0.890 6) , G (0.765 6) , and C (0.711 8) , and the bottom three were V (0.381 9) , W (0.362 8) , and K (0.357 6) . According to the fuzzy set theory, the top three community (township) health centers ranked by W1Ci+W2RSR values were A, C and G, and the bottom three were I, K and W in accordance with the "majority rule", which was basically consistent with the evaluation results of TOPSIS and RSR.ConclusionThe assessment results by TOPSIS, RSR, and fuzzy combination of these two and associated factors in this study are consistent with those of other studies. Either use of TOPSIS- or RSR-based quality assessment had limitations, but fuzzy combination of the two overcame these limitations, so the combination approach is worthy of promotion as an appropriate method for assessing the quality of essential public health services.