An improved text mining approach to extract safety risk factors from construction accident reports

Benchmarking on railway safety performance using Bayesian inference, decision tree and petri-net techniques based on long-term accidental data sets

To clarify the risk factors and propagation characteristics affecting railway safety, we learn from historical reports to build a connected network of hazards and accidents, forming a knowledge graph (KG), and apply it to railway hazard identification and risk assessment. First, the open source-British railway accident/incident reports are selected as the data source. The text augmentation algorithm in the text mining technology is introduced and optimized to achieve data enhancement. An ensemble model is constructed based on the hidden Markov model, conditional random field (CRF) algorithm, bidirectional long short-term memory (Bi-LSTM), and Bi-LSTM-CRF deep learning network, completing the named entity recognition of the reports. Then, using the random forest algorithm, the standardized classification of entities is accomplished, and the multi-dimensional knowledge graph network is established. Finally, after defining a series of safety-related feature parameters, the obtained KG is applied to the quantitative assessment of the corresponding risk level of the hazards. The results show that this approach realizes the visualization and quantitative description of the potential relationship among hazards, faults, and accidents by exploring the topological relationship of the railway accident network, further assisting the formulation of railway risk preventive measures. 

Using text mining to establish knowledge graph from accident/incident reports in risk assessment

The prefabricated building has been proven to be an effective approach for enhancing the sustainability of the construction industry. In recent years, the Chinese government has promulgated a series of policy documents to promote the advancement of prefabricated buildings. However, in practice, there are still numerous problems related to design, production, and construction, as well as the coordination between various stages. This study aimed to fill the gap in research regarding the application of EPC (Engineering–Procurement–Construction) in prefabricated buildings in China. As most of the risks of projects are borne by general contractors in the EPC mode, the risks faced by prefabricated building projects using EPC were systematically analyzed in this study from the perspective of general contractors. After learning about the risks of assembly construction in different countries, this study conducted a questionnaire survey to establish an evaluation system, and a comprehensive evaluation method was put forward to determine the weight of each indicator. Furthermore, an evaluation model based on grey–fuzzy theory was developed in this study, which was applied to a real project in Nanjing, China. The results indicated the applicability of the established evaluation system and model and determined the risk level of the project. Additionally, in this case study, it was found that construction and design were the major factors determining the risk level of the project. This study contributes to the body of knowledge regarding the integration of EPC in prefabricated buildings, which has practical application value for general contractors when conducting risk assessments.

/pdf/a-comprehensive-risk-assessment-method-for-prefabricated-1p32rhx2.pdf

A Comprehensive Risk-Assessment Method for Prefabricated Buildings Using EPC: A Case Study from China

In view of the problems existing in the evaluation process of slope stability in cold regions, the improved entropy weight method and extension theory are used to evaluate the slope stability. Nine indexes which affect the slope stability in cold regions are selected, the matter element system of slope stability evaluation is established by extension theory, and the extension correlation degree between evaluation index and evaluation grade is calculated. The improved entropy weight method is used to calculate the entropy weight of the matter element index system, and then the stability grade of the slope matter element is determined. Based on the extension theory and improved entropy weight method, the slope stability of Beizhan open pit mine is predicted. The results show that the prediction results are consistent with the actual situation of the project, and the evaluation method can be applied to the slope stability evaluation in cold regions. By using extension theory and improved entropy weight method, the evaluation index can be changed from a single determined value to an interval value, and the influence degree of the evaluation index can be analyzed more comprehensively. This method improves the evaluation accuracy and provides a new method for the slope stability evaluation in cold regions.

Application of Extension Theory Based on Improved Entropy Weight Method to Rock Slope Analysis in Cold Regions

An improved risk assessment method based on a comprehensive weighting algorithm in railway signaling safety analysis

Traction current can to impose conductive interference on the railway signalling system, which is also known as unbalanced traction current interference. In the station turnout section, the tractio...

Optimization method of switch jumper setting based on strategies for reducing conductive interference in railway

Cab signaling apparatus is the critical equipment for ground-vehicle communication in electrified railways. With the rapid development of high-speed and heavy-haul railways, the immunity to unbalanced traction current interference for cab signaling apparatus in the onboard train control system is increasingly demanded. This paper analyzes the interference coupling mechanism of the ZPW-2000 track circuit. Based on electromagnetic field theory and the actual working parameters, a calculation model is established to complete the quantitative research of the cab signal induction process and traction current interference. Then, a finite element model is built to simulate the process. The simulation results under the signal frequency, fundamental and harmonic interference are all consistent with the theoretical calculation results. The practical measurement data verify the coupling relationship between cab signal inductive voltage and rail current. Finally, an indirect immunity test method applying this relation for the cab signals is proposed, and the voltage indexes of the disturbance sources are determined, i.e., the test limits. The results provide an accurate quantitative basis for the cab signaling research and design of the immunity test platform; besides, the proposed indirect test method can simplify the test configuration and improve test efficiency.

/pdf/quantitative-analysis-on-coupling-of-traction-current-into-32tpsoappx.pdf

Chang Liu

Papers

An improved risk assessment method based on a comprehensive weighting algorithm in railway signaling safety analysis

Optimization method of switch jumper setting based on strategies for reducing conductive interference in railway

Using text mining to establish knowledge graph from accident/incident reports in risk assessment

Quantitative analysis on coupling of traction current into cab signaling in electrified railways

An improved quantitative assessment method on hazardous interference of power lines to the signal cable in high-speed railway