Citation:

Mr. S. Manoj Kumar, S. Thanumalaya Perumal, Mr. S. Raksesh, 2026. "Industrial Fire Accident Predictions using Machine Language", ESP Journal of Engineering & Technology Advancements  6(1): 161-166.

Abstract:

Industrial fire accidents pose a significant threat to human safety, infrastructure, and economic stability, particularly in high-risk environments such as manufacturing plants, oil refineries, and power stations. This project presents an intelligent fire accident prediction system using machine learning techniques, specifically Artificial Neural Networks (ANN), to analyze critical environmental and operational parameters such as temperature, humidity, smoke levels, and flame detection. A structured dataset representing multiple scenarios—including Normal conditions, Cooking/Steam, Electrical Short, and Active Fire—is used to train and evaluate the model. The proposed system focuses not only on detecting active fire incidents but also on identifying early warning signs, such as electrical faults and abnormal thermal variations, enabling proactive prevention. By leveraging the nonlinear learning capability of ANN, the model effectively distinguishes between safe and hazardous conditions, significantly reducing false alarms while improving detection accuracy. The system is designed for real-time monitoring and can be integrated with IoT-based sensor networks for continuous data acquisition and automated alert generation. Experimental results demonstrate that the model achieves high classification performance, making it suitable for deployment in industrial safety applications. This approach enhances early response mechanisms, minimizes damage, and contributes to the development of smart, reliable, and predictive fire safety systems.

References:

[1] A. Kumar and S. Singh, “Intelligent Fire Detection System Using Machine Learning Techniques,” IEEE Access, vol. 10, pp. 45678–45689, 2022.

[2] R. Patel, M. Shah, and K. Joshi, “IoT-Based Smart Fire Monitoring System Using Neural Networks,” IEEE Internet of Things Journal, vol. 9, no. 5, pp. 3456–3465, Mar. 2022.

[3] L. Wang and H. Zhao, “Deep Learning for Fire and Smoke Detection: A Survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 8, pp. 3201–3215, Aug. 2022.

[4] S. Verma and P. Gupta, “ANN-Based Fire Detection in Smart Buildings,” in Proc. IEEE Int. Conf. Smart Cities, 2022, pp. 112–118.

[5] T. Nguyen and J. Lee, “Real-Time Fire Detection Using Edge AI and Sensor Fusion,” IEEE Sensors Journal, vol. 22, no. 10, pp. 9876–9885, 2022.

[6] M. Ali, F. Khan, and R. Ahmed, “Early Fire Prediction Using Artificial Neural Networks,” IEEE Access, vol. 11, pp. 23456–23467, 2023.

[7] P. Sharma and D. Mehta, “Smart Fire Alarm System Using IoT and Machine Learning,” in Proc. IEEE Int. Conf. Emerging Technologies, 2023, pp. 221–226.

[8] Y. Chen, X. Liu, and Z. Wu, “Multisensor Data Fusion for Fire Detection Using Deep Neural Networks,” IEEE Transactions on Industrial Informatics, vol. 19, no. 4, pp. 5678–5687, Apr. 2023.

[9] K. Reddy and V. Rao, “Adaptive Fire Detection System Using ANN and IoT Sensors,” IEEE Sensors Letters, vol. 7, no. 6, pp. 1–4, 2023.

[10] J. Park and S. Kim, “Low-Power AI-Based Fire Detection System for Smart Homes,” IEEE Consumer Electronics Magazine, vol. 12, no. 2, pp. 45–52, Mar. 2023.

[11] D. Roy, S. Banerjee, and A. Ghosh, “Fire Detection in Smart Cities Using Deep Learning and IoT,” IEEE Access, vol. 12, pp. 11234–11245, 2024.

[12] H. Li and Q. Zhang, “Hybrid ANN Model for Fire Risk Prediction in Industrial Systems,” IEEE Transactions on Industrial Electronics, vol. 71, no. 3, pp. 2345–2353, Mar. 2024.

[13] V. Kumar and R. Iyer, “Real-Time Smoke and Flame Detection Using AI-Based Embedded Systems,” in Proc. IEEE Int. Conf. Embedded Systems, 2024, pp. 98–103.

[14] M. Hassan and T. Ali, “AI-Driven Fire Detection and Prevention System Using Sensor Networks,” IEEE Internet of Things Journal, vol. 11, no. 1, pp. 1234–1245, Jan. 2024.

[15] S. Das and P. Roy, “Efficient Fire Detection Using Deep Neural Networks and Edge Computing,” IEEE Access, vol. 12, pp. 56789–56800, 2024.

[16] B. Singh and A. Kaur, “Intelligent Fire Monitoring System Using ANN and Cloud Integration,” IEEE Cloud Computing, vol. 11, no. 2, pp. 67–75, 2025.

[17] Y. Tanaka and K. Suzuki, “AI-Based Fire Detection System for Industrial Safety Applications,” IEEE Transactions on Automation Science and Engineering, vol. 22, no. 1, pp. 89–98, Jan. 2025.

[18] R. Gupta and N. Verma, “Deep Learning-Based Fire and Smoke Detection in Real-Time Video Streams,” IEEE Access, vol. 13, pp. 12345–12358, 2025.

[19] E. Martin and J. Clark, “Next-Generation Smart Fire Detection Using AI and IoT,” in Proc. IEEE Global Communications Conf. (GLOBECOM), 2025, pp. 456–461.

[20] S. Iqbal and M. Rahman, “Advanced Neural Network Models for Early Fire Prediction Systems,” IEEE Transactions on Artificial Intelligence, vol. 7, no. 2, pp. 210–220, Feb. 2026.

Keywords:

Fire Prediction, Machine Learning, ANN, Industrial Safety, IoT Monitoring.