No abstract

Performance prediction based on candidates and screening based on predicted performance value are the core of product development. For example, the performance prediction and screening of equipment components and parts are an important guarantee for the reliability of equipment products. The prediction and screening of drug bioactivity value and performance are the keys to pharmaceutical product development. The main reasons for the failure of pharmaceutical discovery are the low bioactivity of the candidate compounds and the deficiencies in their efficacy and safety, which are related to the absorption, distribution, metabolism, excretion, and toxicity (ADMET) of the compounds. Therefore, it is very necessary to quickly and effectively perform systematic bioactivity value prediction and ADMET property evaluation for candidate compounds in the early stage of drug discovery. In this paper, a data-driven pharmaceutical products screening prediction model is proposed to screen drug candidates with higher bioactivity value and better ADMET properties. First, a quantitative prediction method for bioactivity value is proposed using the fusion regression of LGBM and neural network based on backpropagation (BP-NN). Then, the ADMET properties prediction method is proposed using XGBoost. According to the predicted bioactivity value and ADMET properties, the BVAP method is defined to screen the drug candidates. And the screening model is validated on the dataset of antagonized Erα active compounds, in which the mean square error (MSE) of fusion regression is 1.1496, the XGBoost prediction accuracy of ADMET properties are 94.0% for Caco-2, 95.7% for CYP3A4, 89.4% for HERG, 88.6% for hob, and 96.2% for Mn. Compared with the commonly used methods for ADMET properties such as SVM, RF, KNN, LDA, and NB, the XGBoost in this paper has the highest prediction accuracy and AUC value, which has better guiding significance and can help screen pharmaceutical product candidates with good bioactivity, pharmacokinetic properties, and safety.

Vehicle on-board equipment is the most important train control equipment in high-speed railways. Due to the low efficiency and accuracy of manual detection, in this paper, we propose an intellectualized fault diagnosis method based on adaptive neuro-fuzzy inference system (ANFIS) network. Firstly, we collect the fault information sheets that are recorded by electrical personnel, using frequency weighting factor and principal component analysis (PCA) to realize the data extraction and dimension reduction; Then, in order to improve the fault diagnosis rate of the model, using genetic algorithm (GA) to optimize the parameters of the ANFIS network; Finally, using the fault data of a high-speed railway line in 2019 to test the model, the optimized ANFIS model can achieve 96% fault diagnosis rate for vehicle on-board equipments, which indicating the method is effective and accurate.

Natural language processing is a research direction in many fields such as linguistics, computer science, and data fusion of study. The representation of word vector is a method to map words into the real vector space, which is the core technology of many current natural language processing tasks. This paper summarizes and studies some typical expression methods of word vector as well as research the word vectors of linguistics and mathematical principle. We first elaborate the process of mapping the words to the vector, namely, encoding natural language information to word vector according to semantics. Secondly, we analyze several typical methods such as co-occurrence matrix, Word2Vec, GloVe, ELMo on information carrying capacity. Thirdly, on the basis of analyzing the principles of these methods, this paper also uses SVD decomposition, neural network, and other methods respectively to reproduce the specific process of generating word vectors. Finally, combining word similarity calculation and text sentiment classification task, we compare the performance of word vectors trained by various methods in different tasks. Experiments verify the conclusion that different word vector generation methods have different emphases in carrying linguistic ability and perform differently in different tasks.

Spare parts are one of the important components of the equipment comprehensive support system. Spare parts management plays a decisive role in achieving the desired availability with the minimum cost. With the equipment complexity increasing, the price of spare parts has risen sharply. The traditional spare parts management makes the contradiction between fund shortage and spare parts shortage increasingly prominent. Based on the analysis of the multi-echelon and multi-indenture spare parts support model VARI-METRIC (vary multi-echelon technology for recoverable item control, VARI-METRIC), which is widely used by troops and enterprises in various countries, the model is mainly used in high system availability scenarios. However, in the case of low equipment system availability, the accuracy and cost of model inventory prediction are not ideal. This paper proposed the multi-level spare parts optimization model, which is based on the demand-supply steady-state process. It is an analytical model, which is used to solve the low accuracy problem of the VARI-METRIC model in the low equipment system availability. The analytical model is based on the multi-level spare parts support process. The article deduces methods for solving demand rate, demand–supply rate, equipment system availability, and support system availability. The marginal analysis method is used in the model to analyze the spare parts inventory allocation strategy’s current based cost and availability optimal value. Finally, a simulation model is established to evaluate and verify the model. Then, the simulation results show that, when the low availability of equipment systems are 0.4, 0.6, the relative errors of the analytical model are 3.54%, 3.86%, and its costs are 0.52, 1.795 million ¥ RMB. The experiment proves that the inventory prediction accuracy of the analytical model is significantly higher than that of the VARI-METRIC model in low equipment system availability. Finally, the conclusion and future research directions are discussed.