FIGURE 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Hazardous chemicals are inflammable, explosive, and/or toxic and are prone to accidental leakage, fire, and explosion during production, storage, and transportation. It is time-consuming and laborious to study the properties of hazardous chemicals individually for systematic accident prevention because of the wide variety of hazardous chemicals and...
Contexts in source publication
Context 1
... clustering analysis of incident information has four main components: 1) construction of hazardous chemical incident database; 2) clustering analysis based on incident database; 3) use of word frequency statistics and analysis of accident information by category; 4) development of accident prevention information system. A flowchart is shown in Fig. ...
Context 2
... Statistical analysis of failure mode By combining the statistics of the two factors with the highest word frequency in the failure mode information for the 30 categories, we obtained a total of seven failure modes and took them as the key factors of concern. Fig. 10 shows the frequency of occurrence of these factors in the 60 selected data items. The most common failure modes in all categories are leaking, puncture, and crushing. Fig. 11 shows the frequency of the three most common failure modes in the 30 categories. The line chart shows the frequency of leaking, and the points represent the ...
Context 3
... the highest word frequency in the failure mode information for the 30 categories, we obtained a total of seven failure modes and took them as the key factors of concern. Fig. 10 shows the frequency of occurrence of these factors in the 60 selected data items. The most common failure modes in all categories are leaking, puncture, and crushing. Fig. 11 shows the frequency of the three most common failure modes in the 30 categories. The line chart shows the frequency of leaking, and the points represent the frequencies of other failure modes. These frequencies can be regarded as the probability of occurrence in each category. By comparing the probabilities of the failure modes, the ...
Context 4
... Statistical analysis of cause of failure By combining the statistics of the two factors with the highest word frequency in the cause of failure in the 30 categories, we obtained a total of 13 causes of failure and took them as the key factors of concern. Fig. 12 shows the frequency of occurrence of these factors in the 60 selected data items. The most common causes of failure in all the categories are loose closure (component or device), forklift accident, and human error. Fig. 13 shows the frequencies of the three most common causes of failure in the 30 categories. The line chart shows the ...
Context 5
... of failure in the 30 categories, we obtained a total of 13 causes of failure and took them as the key factors of concern. Fig. 12 shows the frequency of occurrence of these factors in the 60 selected data items. The most common causes of failure in all the categories are loose closure (component or device), forklift accident, and human error. Fig. 13 shows the frequencies of the three most common causes of failure in the 30 categories. The line chart shows the frequency of ''loose closure (component or device),'' and the points represent the frequencies of other causes of failure. The frequencies of the causes of failure can be regarded as the probability of occurrence in each ...
Context 6
... cause, process, and consequences of each type of incident reveals a causal linkage between the factors contributing to the accident. Consequently, an accident analysis diagram can be drawn for each type of incident. We take Class 23, which has the largest number of consequences, as an example to illustrate the accident analysis. The diagram in Fig. 14 shows the two items with the highest frequency in the incident process description; failed component, failure mode, and cause of failure information; and consequences, along with the corresponding ...
Citations
... Using machine learning techniques, researchers are now exploring these vast knowledge sources to extract key risk factors (Santos, Dias, & Amado, 2022;Li, 2021). As previously stated, the vast majority of accident data in the industry is unstructured and unannotated (Deng, Gu, Zeng, Zhang, & Wang, 2020). There are only a few unsupervised machine learning methods that can effectively handle unstructured data. ...
... K-means clustering is relatively simple to implement, guarantees convergence, and easily adapts to new examples. Due to these advantages, Deng et al. (2020) used K-means clustering to classify information about accidents with hazardous chemicals, and Liu et al. (2021) used K-means clustering combined with TF-IDF to classify accident causality factors from pipeline accident reports. Deciding the K value in K-means clustering is an iterative process; in the first step, each data point in the dataset is randomly assigned to its closest centroid. ...
Introduction: Workplace accidents in the petroleum industry can cause catastrophic damage to people, property, and the environment. Earlier studies in this domain indicate that the majority of the accident report information is available in unstructured text format. Conventional techniques for the analysis of accident data are time-consuming and heavily dependent on experts' subject knowledge, experience, and judgment. There is a need to develop a machine learning-based decision support system to analyze the vast amounts of unstructured text data that are frequently overlooked due to a lack of appropriate methodology. Method: To address this gap in the literature, we propose a hybrid methodology that uses improved text-mining techniques combined with an un-bias group decision-making framework to combine the output of objective weights (based on text mining) and subjective weights (based on expert opinion) of risk factors to prioritize them. Based on the contextual word embedding models and term frequencies, we extracted five important clusters of risk factors comprising more than 32 risk sub-factors. A heterogeneous group of experts and employees in the petroleum industry were contacted to obtain their opinions on the extracted risk factors, and the best-worst method was used to convert their opinions to weights. Conclusions and Practical Applications: The applicability of our proposed framework was tested on the data compiled from the accident data released by the petroleum industries in India. Our framework can be extended to accident data from any industry, to reduce analysis time and improve the accuracy in classifying and prioritizing risk factors.
... Sci. 2024, 14, 1352 9 of 23 statistically cluster high-dimensional datasets, as evidenced by its successful application in numerous studies related to accident clustering [9,15,[39][40][41]. The Euclidean distance (d) in n-dimensional space is a measure of the true straight-line distance between two points (p, q) in Euclidean space within the context of K-means clustering. ...
The highway construction industry carries substantial safety risks for workers, necessitating thorough accident analyses to implement effective preventive measures. Current research lacks comprehensive investigations into safety incidents, relying heavily on conventional statistical methods and overlooking valuable textual information in publicly available databases. This study leverages a state-of-the-art large language model (LLM), specifically OpenAI’s GPT-3.5 model. The primary focus is to enhance text-based incident analysis that is sourced from OSHA’s Severe Injury Reports (SIR) database. By incorporating novel natural language processing (NLP) techniques, dimensionality reduction, clustering algorithms, and LLM prompting of incident narratives, the study aims to develop an approach to the analysis of major accident causes in highway construction. The resulting cluster analysis, coupled with LLM summarization and cause identification, reveals the major accident types, such as heat-related and struck-by injuries, as well as commonalities between incidents. This research showcases the potential of artificial intelligence (AI) and LLM technology in data-driven analysis. By efficiently processing textual data and providing insightful analysis, the study fosters practical implications for safety professionals and the development of more effective accident prevention and intervention strategies within the industry.
... AlRukaibi et al. [7] conducts risk analysis on the surrounding environment and crowd safety of the hazardous materials transport route, designs an event simulation scene, and inserts it into GPS for risk analysis. Deng et al. [31] used K-means clustering to classify hazardous material transportation accidents, and proposed corresponding solutions to the classification results. Hu et al. [24] considered cost, risk and emergency response capability, and used compromise weight model and evolutionary algorithm to solve the multi-objective hazardous material transportation problem. ...
Hazardous material transport accidents are events with low probability and high consequence risk. With the increase in the proportion of hazardous materials transported on domestic roads, increasing number of scholars have begun to study this field. In this study, a multi-objective hazardous materials transport route planning model considering road traffic resilience and low carbon, which considers the uncertainty of demand and time and is under the limit of the time window. It transports many types of hazardous materials from multiple suppliers to multiple retails with the three goals (transportation cost, risk and carbon emission). This model fills the gap in the research on hazardous materials transportation in the field of low carbon, and this is the first time that road traffic resilience is considered in the transport of hazardous materials as one of the weight factors of risk calculation. We designed a improved ant colony optimization algorithm (ACO) to obtain the pareto optimal solution set. We compare the improved ACO with genetic algorithm and simulated annealing algorithm. The results show that the improved ACO has better solution quality and solution space, which verifies the validity and reliability of the improved ACO.
... Penelitian yang berjudul Short-term Forecasting of Individual Residential Load Based on Deep Learning and K-Means clustering [5], mempelajari tentang metode peramalan beban hunian individu jangka pendek berdasarkan kombinasi deep learning dan K-Means clustering, yang mampu mengekstraksi kesamaan beban hunian secara efektif dan melakukan peramalan beban hunian secara akurat di tingkat individu. Hasil dari penelitian ini menunjukkan metode yang digunakan dapat mencapai akurasi prediksi yang jauh lebih tinggi, dibandingkan dengan metode benchmark.Penelitian lainnya dengan judul Hazardous Chemical Accident Prevention Based on K-Means clustering Analysis of Incident Information mengusulkan metode generik pencegahan kecelakaan bahan kimia berbahaya berdasarkan analisis pengelompokan K-Means dari informasi insiden untuk menggambarkan bagaimana memecahkan masalah [6]. Hasil dari penelitian menunjukkan bahwa metode yang diusulkan untuk pencegahan kecelakaan bahan kimia berbahaya dapat digunakan untuk meningkatkan klasifikasi kecelakaan. ...
The rapid development of technology has an impact on how data is collected. A high level of data productivity will be in vain if it is not followed by the ability to process data that can produce information that helps the development of the organization. This study aims to help the Promotion Section of UNKRISWINA SUMBA in mapping the characteristics of the target schools and then provide alternative promotion strategies as input in formulating forms of institutional promotion. The data used is in the form of student data who have registered at UNKRISWINA SUMBA since 2016 – 2020. Data processing uses the concept of data mining by applying the K-Means algorithm. K-Means algorithm is used for clustering promotion target schools as many as 4 clusters. Cluster determination is carried out using the elbow method to determine the optimal value of k to perform calculations. Based on the results of processing based on the K-Means algorithm, it is known that as many as 8 schools in cluster 0 are the schools with the most students enrolling in UNKRISWINA SUMBA, 76 schools in cluster 1 are schools with the fewest students enrolling in UNKRISWINA SUMBA, 21 schools those in cluster 2 are schools with quite a lot of students enrolling in UNKRISWINA SUMBA, and 1 school in cluster 3 is a school with quite a number of students enrolling in UNKRISWINA SUMBA but focusing on the Economic Development and Management study program.
... Based on the principal characteristics of hazardous chemicals, accidents were divided into five categories: leakage accident, fire accident, explosion accident, poisoning accident and other accident [24]. The statistics of accidents are shown in Figure 2. As shown in Figure 2, explosion accidents were the main type of hazardous chemical accident, occupying 43.4% of the total number of accidents, and was the main form of accident consequences. ...
... In this study, we mainly considered professional qualification and field experience. Finally, we obtained the expert weight by referring to reference [24]. The results are shown in Table 1. ...
Refining and chemical integration is the major trend in the development of the world petrochemical industry, showing intensive and large-scale development. The accident risks caused by this integration are complex and diverse, and pose new challenges to petrochemical industry safety. In order to clarify the characteristics of the accident and the risk root contained in the production process of the enterprise, avoid the risk reasonably and improve the overall safety level of the petrochemical industry, in this paper, 159 accident cases of dangerous chemicals in China from 2017–2021 were statistically analyzed. A Bayesian network (BN)-based risk analysis model was proposed to clarify the characteristics and root causes of accident risks in large refining enterprises. The prior probability parameter in the Bayesian network was replaced by the comprehensive weight, which combined subjective and objective weights. A hybrid method of fuzzy set theory and a noisy-OR gate model was employed to eliminate the problem of the conditional probability parameters being difficult to obtain and the evaluation results not being accurate in traditional BN networks. Finally, the feasibility of the methods was verified by a case study of a petrochemical enterprise in Zhoushan. The results indicated that leakage, fire and explosion were the main types of accidents in petrochemical enterprises. The human factor was the main influencing factors of the top six most critical risk root causes in the enterprise. The coupling risk has a relatively large impact on enterprise security. The research results are in line with reality and can provide a reference for the safety risk management and control of petrochemical enterprises.
... However, unfortunately, in recent years the problem of the socalled "human factor" [10][11][12] has become increasingly apparent. This is associated not only with expectations of catastrophic consequences of the displacement of humans by robots and artificial intelligence, but also with the increase in tension of operators' work, stress, increase in the number of errors leading to catastrophic consequences, increase in cases of injuries and even deaths of people [13][14][15]. ...
The article considers the problem of human factor in complex polyergatic systems with a flow of applications for functions (problem solving) arising at random moments of time. The structure of a decision support system for the operator-manager, including subsystems of monitoring, forecasting and decision-making, is justified. The system of criteria relevant to solving the tasks of functions distribution was substantiated and its multi-criteria nature was shown. The technology of multi-criteria evaluation and choice of alternatives based on the methodology of hierarchical system analysis of problems and the method of analysis of hierarchies Thomas Saaty has been proposed. The decision-making system, which has been tested in the operation of control systems of various complex technical and production objects, has been implemented. The proposed method differs from the known approaches in that this method is aimed at prompt decision-making, as well as in that it uses a multi-criteria approach and both pragmatic and ergonomic criteria are used as criteria.
... The K-Means algorithm is integrated into the minimum spanning tree algorithm, and a fast minimum spanning tree algorithm based on the N-point complete graph is proposed, which reduces the theoretical time complexity from OðN 2 Þ to OðN 1:5 Þ and overcomes the deficiency that the traditional minimum spanning tree algorithm cannot be applied to large datasets due to time complexity. K-Means clustering can also be used to develop image compression methods on low-power embedded devices, that is, using the similarity of pixel colors to group pixels and compress the original image, so as to reduce the power of wireless imaging sensor networks [19,20]. ...
In order to solve the problem of how to explore potential information in massive data and make effective use of it, this paper mainly studies news text clustering and proposes a news clustering algorithm based on improved K -Means. Then, the MapReduce programming model is used to parallelize the TIM- K -Means algorithm, so that it can run on the Hadoop platform. The accuracy and error are used as measurement indicators, and the collected datasets are used for experiments to verify the correctness and effectiveness of the TI value and TIM- K -Means algorithm. In addition, the Alibaba cloud server is used to build the Hadoop cluster, and the feasibility of parallelization transformation of TIM- K -Means algorithm is verified by accelerated comparison. The results show that the parallelized TIM- K -Means has a good acceleration ratio, can save about 30% of the time under the same conditions, and can meet the actual needs of processing massive data in the context of big data. In multidocument automatic summarization, news clustering algorithm can gather the news with the same topic and provide cleaner and accurate data for visual automatic summarization, which is of great significance in the fields of public opinion supervision, hot topic discovery, emergency real-time tracking, and so on.
... Specialised hazardous chemical storage tanks and containers should be used for transportation; towing tractors should be used for transportation. Vehicles need to be cleaned and disinfected every time they return to the logistics company after serving customers to prevent residual hazardous chemicals from causing potential risks 24 . Therefore, when the company formulates integrated decision-making of vehicle combined strategy and route optimisation based on customer demand, the company needs to consider customer demand and proper vehicle scheduling. ...
... If the numbers are displayed, it represents the transportation distance. 24 . According to the current subsidy policy for purchasing environmental vehicles in Shandong Province, the present value of the subsidy for purchasing environmental vehicles C s is 50,000 yuan. 5. ...
With the optimal operating cost and optimal carbon emission target of the chemical logistics companies, a low-carbon routing optimisation with a multi-energy type vehicle combined problem is proposed by considering the concept of the logistics companies’ low-carbon behaviour. An integrated decision-making of multi-energy type vehicles combined strategy and route optimisation based on customer demand is presented, and an improved genetic algorithm is designed. A case study is then applied based on the data collected from the case research. The effectiveness of the improved genetic algorithm is tested. The two joint objectives of operating cost and carbon emission are examined through the cost analysis of environmental energy vehicles and traditional energy vehicles in different combination scenarios. The case analysis shows that a rational multi-energy type vehicle combination with route optimisation has a significant correlation with the operating cost and carbon emissions, while the environmental vehicle purchasing cost reduction and subsidy policy affect the operating cost.
