Abstract: Disclosed is a customized product performance prediction method based on heterogeneous data difference compensation fusion. The method includes: on the basis of a depth auto-encoder, a neighborhood association method and a similarity difference compensation method, performing difference compensation correction on a calculation simulation data set by using a historical actual measurement data set; and training a BP neural network model by using the calculation simulation data set after the difference compensation correction to serve as a performance prediction method of a customized product.

Abstract: Disclosed is a customized product performance prediction method based on heterogeneous data difference compensation fusion. The method includes: on the basis of a depth auto-encoder, a neighborhood association method and a similarity difference compensation method, performing difference compensation correction on a calculation simulation data set by using a historical actual measurement data set; and training a BP neural network model by using the calculation simulation data set after the difference compensation correction to serve as a performance prediction method of a customized product.

Abstract: Provided is a mechanical product personalized design pattern matching method oriented to an Internet+ environment. According to the method, a user order is quantified into a feature vector, a mechanical product is decomposed into modules, a historical case library is constructed, and a design pattern scheme matched according to the user order is obtained according to the probability that a user is satisfied when different design patterns are adopted by respective modules of the mechanical product. From the perspective of probability, a personalized design pattern matching method of each design module in product customization design is researched according to the Bayesian theorem.