The automobile industries and the manufacturing revolution leads to a large extend of risk and hazards to automobile workers. The modern automobile industries are complicated because of various breakthroughs in technological innovations and based on the nature of operation with hazards of assorted degrees at every stage. This paper aims in identifying the hazards to evaluate and compare the rate of risk. The proposed framework comprises three diverse levels such as the data collection phase, data processing phase and riskprediction phase. In the data collection phase, the data gathered from the automobile manufacturing industry located in Tamil Nadu region is taken for investigation. In the data processing phase, raw data obtained from cameras and sensors are processed and the features are then extracted and selected for prediction purposes. In the risk prediction phase, the risk is predicted and classified into four levels namely level 1 (Extreme risk level), level 2 (High risk level), level 3 (Medium risk level), and level 4 (Low risk level) using deep convolutional neural network-hybrid Aquila optimizer (DCNN-HAO) approach. Regarding the evaluation of the proposed model, few performance measures namely area of under curve (AUC), area under receiving operation characteristics (ROC), false positive rate (FPR) and true positive rate (TPR) are evaluated. The experimental investigations are performed and graphical evaluation revealed that the proposed technique achieves better performances than other techniques. This confirms that the superiority and feasibility of the proposed DCNNHAO approach that accurately predicts the risk.