Multi-parameter online optimization algorithm of BP neural network algorithm in Internet of Things service

Evaluation Model of Innovation and Entrepreneurship Ability of Colleges and Universities Based on Improved BP Neural Network

Entrepreneurship education activities in colleges and universities play an important role in improving students' innovation ability. Therefore, this paper has important practical value to evaluate the innovation and entrepreneurship ability of college students. At present, most studies use qualitative research methods, which is inefficient. Even if quantitative analysis is adopted, it is mostly linear analysis, which is inconsistent with the actual situation. In order to improve the application level of genetic algorithm to the innovation and entrepreneurship ability of universities based on BP neural network, this paper studies the evaluation model of innovation and entrepreneurship ability of universities. Based on the simple analysis of the current situation of university innovation and entrepreneurship ability evaluation and the application progress of BP neural network, combined with the actual situation of university innovation and entrepreneurship, this paper constructs the innovation and entrepreneurship evaluation index, uses BP neural network to build the evaluation model, and uses genetic algorithm to optimize and improve the shortcomings of BP neural network. Then, the experimental analysis and application design are carried out. The results show that the improved algorithm is basically consistent with the predicted value, small error, and fast convergence. When it is used in the evaluation of innovation and entrepreneurship ability, quantitative analysis results can be obtained, which provides a certain reference for the development of enterprises.

Forecast the Microhardness of Ni-TiN Nanoplatings via an Artificial Neural Network Model

This study used a backward propagation (BP) model to estimate the microhardness of Ni-TiN nanoplatings prepared using pulse electrodeposition. The influence of electroplating parameters on the microhardness of Ni-TiN nanoplatings was discussed. These parameters included the concentration of the TiN particle, pulse frequency, duty cycle, and current density. The surface morphology, microstructure, and microhardness of Ni-TiN nanoplatings were examined using white-light interfering profilometry, scanning electron microscopy, Rockwell hardness testing, and high-resolution transmission emission microscopy. The Ni-TiN thin film prepared by pulse electrodeposition had a surface roughness of about 0.122 µm, and the average size of the Ni and TiN grains on this film was 61.8 and 31.3 nm, respectively. The optimal process parameters were determined based on the maximum microhardness of the deposited Ni-TiN nanoplatings, which included an 8 g/L TiN particle concentration, a 5 A/dm2 current density, an 80 Hz pulse frequency, and a 0.7 duty cycle. It could be concluded that the BP model would accurately forecast the microhardness of Ni-TiN nanoplatings, with a maximal error of about 1.04%.