Quantitative assessment method for equipment health state under unsupervised condition and electronic equipment

The embodiment of the invention provides a quantitative evaluation method for the health state of equipment under an unsupervised condition and electronic equipment. The quantitative evaluation method comprises the following steps: acquiring a sensor data sequence to obtain paired comparison training samples; solving the generalized inverse of the block matrix by adopting a function; initializing a network, wherein the network comprises an input layer, a hidden layer, an enhancement layer and an output layer, wherein each layer is provided with one or more nodes; recursively solving an optimal hidden layer node number; and calculating a health state value. According to the method, an error minimization extreme learning machine algorithm based on pairwise comparison is used, and the health state of the equipment is quantitatively evaluated with a small calculated amount by using easily available sensor data under the condition that label data is not used and only common knowledge is used. 本发明实施例提供一种无监督条件下设备健康状