Search results

Safety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a challenge. This paper aims to develop a knowledge extraction model to automatically and efficiently extract domain knowledge from unstructured texts.

Bidirectional encoder representations from transformers (BERT)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method based on a pre-training language model was applied to carry out knowledge entity recognition in the field of coal mine construction safety in this paper. Firstly, 80 safety standards for coal mine construction were collected, sorted out and marked as a descriptive corpus. Then, the BERT pre-training language model was used to obtain dynamic word vectors. Finally, the BiLSTM-CRF model concluded the entity’s optimal tag sequence.

Accordingly, 11,933 entities and 2,051 relationships in the standard specifications texts of this paper were identified and a language model suitable for coal mine construction safety management was proposed. The experiments showed that F1 values were all above 60% in nine types of entities such as security management. F1 value of this model was more than 60% for entity extraction. The model identified and extracted entities more accurately than conventional methods.

This work completed the domain knowledge query and built a Q&A platform via entities and relationships identified by the standard specifications suitable for coal mines. This paper proposed a systematic framework for texts in coal mine construction safety to improve efficiency and accuracy of domain-specific entity extraction. In addition, the pretraining language model was also introduced into the coal mine construction safety to realize dynamic entity recognition, which provides technical support and theoretical reference for the optimization of safety management platforms.

This study aims to develop a finite element method based co-simulation platform for the numerical analysis of motor drive system. With the rising requirement of industry, the comprehensive design of motor drive systems has attracted increasing attentions. An accurate model, which considers the coupling between motor and its drive system, is vital for the analysis and design of motor drive system.

Considering the coupling relationship between motor and its drive system, a flexible and extensible co-simulation platform of motor drive system is developed with the C++ language and finite element machine model to carry out the comprehensive analysis of motor drive system. The control system simulation program developed with C++ language adopts the same discrete form as the single-chip microcomputer and can simulate the interrupt mechanism, making the simulation closer to the actual control system. With the finite element analysis results of current step, the winding input voltage of next step is calculated by the executable program of control system and is fed into the finite element analysis, forming the two-way coupling analysis of drive system.

Preliminary studies, such as calculation of machine core losses fed by inverters, and control parameters optimization, are conducted with this platform, which shows the flexibility and expansibility of this platform.

The power inverter circuit along with the controller is modeled using the C++ language, and embedded into the finite element machine model to achieve more realistic motor drive system simulation and complex functions.

Defining and validating a map of related technologies is critical for managers, investors and inventors. Because of the increase in the applications of and demand for semiconductor lasers, analyzing the technological position of developers has become increasingly critical. Therefore, the purpose of this study is to adopt the technological position analysis to identify mainstream technologies and developments relevant to semiconductor lasers.

Correspondence analysis and k-means cluster analysis, which are data mining techniques, are used to reveal strategic groups of major competitors in the semiconductor laser market according to their Patent Cooperation Treaty (PCT) patent applications.

The results of this study reveal that PCT patent applications are generally obtained for masers, optical elements, semiconductor devices and methods for measuring and that technology developers have varying technological positions.

Through position analysis, this study identifies the technological focuses of different manufacturers to obtain information that can guide the allocation of research and development resources.