Prediction Model for Occupational Incidents in Chemical and Gas Industries
Ganapathy Subramaniam Balasubramanian1, Ramaprabha Thangamani2
1Ganapathy Subramaniam Balasubramanian*, Research Scholar, PG and Research Department of Computer Science and Applications, Vivekanandha College of Arts and Science, TN, India.
2Dr. T. Ramaprabha, PG and Research Department of Computer Sciences and Applications, Vivekanandha College of Arts and Science, Tiruchengode, TN, India.
Manuscript received on November 10, 2019. | Revised Manuscript received on November 17, 2019. | Manuscript published on 30 November, 2019. | PP: 3836-3840 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8212118419/2019©BEIESP | DOI: 10.35940/ijrte.D8212.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Understanding occupational incidents is one of the important measures in workplace safety strategy. Analyzing the trends of the occupational incident data helps to identify the potential pain points and helps to reduce the loss. Optimizing the Machine Learning algorithms is a relatively new trend to fit the prediction model and algorithms in the right place to support human beneficial factors. The aim of this research is to build a prediction model to identify the occupational incidents in chemical and gas industries. This paper describes the architecture and approach of building and implementing the prediction model to predict the cause of the incident which can be used as a key index for achieving industrial safety in specific to chemical and gas industries. The implementation of the scoring algorithm coupled with prediction model should bring unbiased data to obtain logical conclusion. The prediction model has been trained against FACTS (Failure and Accidents Technical information system) is an incidents database which have 25,700 chemical industrial incidents with accident descriptions for the years span from 2004 to 2014. Inspection data and sensor logs should be fed on top of the trained dataset to verify and validate the implementation. The outcome of the implementation provides insight towards the understanding of the patterns, classifications, and also contributes to an enhanced understanding of quantitative and qualitative analytics. Cutting edge cloud-based technology opens up the gate to process the continuous in-streaming data, process it and output the desired result in real-time. The primary technology stack used in this architecture is Apache Kafka, Apache Spark Streaming, KSQL, Data frames, and AWS Lambda functions. Lambda functions are used to implement the scoring algorithm and prediction algorithm to write out the results back to AWS S3 buckets. Proof of concept implementation of the prediction model helps the industries to see through the incidents and will layout the base platform for the various safety-related implementations which always benefits the workplace’s reputation, growth, and have less attrition in human resources.
Keywords: Occupational incidents, Prediction Model, Machine Learning, Real-time processing.
Scope of the Article: Machine Learning.