Search

Commercial grain elevators are hazardous agro-manufacturing work environments where workers are prone to serious and life-threatening injuries. The aim of this study is to give insight into safety risks in grain handling facilities through information processing of workers’ compensation data on agro-manufacturing occupational incidents within commercial grain elevators in the Midwest region of the United States between 2008 and 2016. The severity of occupational incidents is determined by total dollar amount incurred on medical, indemnity, and other expenses in workers’ compensation claims. The most important factors that affect the cost escalation of occupational incidents are extracted using bootstrap partitioning method, and are applied as input for constructing two machine learning models: random forests decision trees, and naive Bayes. Both models show high accuracy (87.64% and 92.78% respectively) in predicting that a future claim is classified as either low or medium, severity. The models contribute to identifying high injury risk groups, and prevalent incident causes, allowing a more research-based focused intervention effort in grain handling workplaces. In addition, the results are applicable in forecasting cost severity of future claims, and identifying factors that contribute to the escalation of claims costs.

Although machine learning methods have been used as an outcome prediction tool in many fields, their utilization in predicting incident outcome in occupational safety is relatively new. This study tests the performance of machine learning techniques in modeling and predicting occupational incidents severity with respect to accessible information of injured workers in agribusiness industries using workers’ compensation claims. More than 33,000 incidents within agribusiness industries in the Midwest of the United States for 2008–2016 were analyzed. The total cost of incidents was extracted and classified from workers’ compensation claims. Supervised machine learning algorithms for classification (support vector machines with linear, quadratic, and RBF kernels, Boosted Trees, and Naive Bayes) were applied. The models can predict injury severity classification based on injured body part, body group, nature of injury, nature group, cause of injury, cause group, and age and tenure of injured workers with the accuracy rate of 92–98%. The results emphasize the significance of quantitative analysis of empirical injury data in safety science, and contribute to enhanced understanding of injury patterns using predictive modeling along with safety experts’ perspectives with regulatory or managerial viewpoints. The predictive models obtained from this study can be used to augment the experience of safety professionals in agribusiness industries to improve safety intervention efforts.

Current maintenance intervals of mechanical systems are scheduled a priori based on the life of the system, resulting in expensive maintenance scheduling, and often undermining the safety of passengers. Going forward, the actual usage of a vehicle will be used to predict stresses in its structure, and therefore, to define a specific maintenance scheduling. Machine learning (ML) algorithms can be used to map a reduced set of data coming from real-time measurements of a structure into a detailed/high-fidelity finite element analysis (FEA) model of the same system. As a result, the FEA-based ML approach will directly estimate the stress distribution over the entire system during operations, thus improving the ability to define ad-hoc, safe, and efficient maintenance procedures. The paper initially presents a review of the current state-of-the-art of ML methods applied to finite elements. A surrogate finite element approach based on ML algorithms is also proposed to estimate the time-varying response of a one-dimensional beam. Several ML regression models, such as decision trees and artificial neural networks, have been developed, and their performance is compared for direct estimation of the stress distribution over a beam structure. The surrogate finite element models based on ML algorithms are able to estimate the response of the beam accurately, with artificial neural networks providing more accurate results.

The grain handling industry plays a significant role in U.S. agriculture by storing, distributing, and processing a variety of agricultural commodities. Commercial grain elevators are hazardous agro-manufacturing work environments where workers are prone to severe injuries, due to the nature of the activities and workplace. One of the leading causes of occupational incidents in all industries, including grain elevators, is slip, trip, and fall (STF). Therefore, prediction of STF incidents prior to occurrence is significant in occupational safety analysis. Despite high frequency of STF incidents at work, exploring their dominant factors via machine learning algorithms in agro-manufacturing environments is relatively new or unaddressed. Safety professionals may utilize the prediction and analysis of determinant factors of occupational incidents for actionable prevention and safety mitigation planning and practices. The objective of this research is to describe the slip-trip-fall (STF) injuries and trends in a population of agribusiness operations workers within commercial grain elevators in the Midwest of the United States, identify risk factors for STF injuries, and develop prevention strategies for STF hazards.

Mining is known to be one of the most hazardous occupations in the world. Many serious accidents have occurred worldwide over the years in mining. Although there have been efforts to create a safer work environment for miners, the number of accidents occurring at the mining sites is still significant. Machine learning techniques and predictive analytics are becoming one of the leading resources to create safer work environments in the manufacturing and construction industries. These techniques are leveraged to generate actionable insights to improve decision-making. A large amount of mining safety-related data are available, and machine learning algorithms can be used to analyze the data. The use of machine learning techniques can significantly benefit the mining industry. Decision tree, random forest, and artificial neural networks were implemented to analyze the outcomes of mining accidents. These machine learning models were also used to predict days away from work. An accidents dataset provided by the Mine Safety and Health Administration was used to train the models. The models were trained separately on tabular data and narratives. The use of a synthetic data augmentation technique using word embedding was also investigated to tackle the data imbalance problem. Performance of all the models was compared with the performance of the traditional logistic regression model. The results show that models trained on narratives performed better than the models trained on structured/tabular data in predicting the outcome of the accident. The higher predictive power of the models trained on narratives led to the conclusion that the narratives have additional information relevant to the outcome of injury compared to the tabular entries. The models trained on tabular data had a lower mean squared error compared to the models trained on narratives while predicting the days away from work. The results highlight the importance of predictors, like shift start time, accident time, and mining experience in predicting the days away from work. It was found that the F1 score of all the underrepresented classes except one improved after the use of the data augmentation technique. This approach gave greater insight into the factors influencing the outcome of the accident and days away from work.

Due to the high frequency and costs of occupational incidents in agro-manufacturing operations, as well as substantial impact of occupational injuries on labor-market outcomes, predicting the post-incident state of an injury and identifying its contributory factors is vital to protect workers, improve workplace safety, and reduce overall costs of injuries. This study evaluates the performance of machine learning algorithms in classifying post-incident outcomes of occupational injuries in agro-manufacturing operations. Injury factors extracted from 14,000 workers’ compensation claims recorded between 2008 and 2016 in the Midwest region of the United States were used to develop machine learning models. The models predicted incident outcomes based on injury details with an overall accuracy rate of 78%, and high accuracy rate for medical post-incident state (97–98%). The results emphasize the significance of quantitative analysis of empirical injury data in safety science, and contributes to enhanced understanding of occupational incidents root causes using predictive modeling along with safety experts’ perspective.