基于人工智能巡检系统的化工材料安全生产风险溯源研究

化工材料生产是一个复杂的过程，涉及到各种危险物质的加工和储存，突发火灾或化学品泄漏等事故常造成巨大的人力物力损失。这些事故的发生往往是由 于在检查过程中被忽视或没有及时发现的细节。因此，加强化工材料安全生产巡 检工作，及时发现安全隐患至关重要。本文提出了一种化工材料生产风险智能巡 检策略，实现了火灾风险的及时发现溯源、对于高风险地区重点关注和多次巡检 后实现全区域覆盖等功能。 对于一个智能巡检系统，风险溯源和路径规划是必不可少的环节。本文以火 灾为例，对目标检测算法 YOLOv5 进行改进，实现了对火焰更高精度的识别，将 召回率提升 37.4%，平均精度均值提升 6.7%。同时提出一种多目标巡检路径规划 方法，考虑了环境地形的影响，使巡检顺序的确定更加符合实际情况, 对于路径的优化采用信息子集优化方法，进一步提高了优化效率，并通过实验证明了此方法的优势。将这种多目标巡检路径规划方法和火灾识别技术应用在智能巡检策略上，引入风险热力地图的概念，使巡检策略更加完善，为智能巡检策略的实现提供了 支撑。结合上述内容，提出了一种智能巡检策略，实现对高风险地区的多次巡检 和全区域覆盖的目的，通过实验证明了其有效性和可行性，为化工材料安全生产巡检提供了一种新的解决方案。

Chemical material production is a complex operation that involves handling and storing a variety of hazardous compounds. Mishaps like chemical spills or unexpected fires frequently cause significant losses in both human and material resources. These mishaps frequently occur due to small oversights that are overlooked or not detected in a timely manner during patrols. As a result, it is crucial to increase the patrol work of chemical material safety production and promptly identify potential safety concerns. This project proposes an intelligent patrol strategy for chemical material production risks, which enables timely discovery and tracing of fire risks, focusing on high-risk areas, and realizes the whole area coverage after multiple patrols. Risk tracing and path planning are crucial for an intelligent patrol system. Taking fire as an example, this project enhances the target detection algorithm YOLOv5, boosting the recall rate by 37.4% and the average precision by 6.7%. In the meantime, a multi-objective patrol path planning method that takes into account the impact of the surrounding topography is offered, bringing the selection of the patrol order closer to the reality of the situation. The informed subset optimization method is used for path optimization, further improving optimization efficiency. And the advantages of this method are proved by experiments. This multi-target patrol path planning method and fire identification technology are applied to the intelligent patrol strategy, introducing the concept of a risk heat map to make the patrol strategy more comprehensive and to provide support for the implementation of the intelligent patrol strategy. An intelligent patrol strategy is suggested in conjunction with the previously mentioned material to accomplish the goals of multiple patrols of high-risk regions and comprehensive coverage of the entire area. Experiments have proven its viability and effectiveness, providing a fresh solution for the patrol of chemical materials safety production.

[1] SHOU Y, CHEN J, GUO X, et al. A dynamic individual risk management method considering spatial and temporal synergistic effect of toxic substance leakage and fire accidents[J]. Process Safety and Environmental Protection, 2023, 169: 238-251.
[2] WANG J, FU G, YAN M. Comparative analysis of two catastrophic hazardous chemical accidents in China[J]. Process Safety Progress, 2020, 39(1).
[3] CHAO C Y, ZHANG H, HAMMER M, et al. Integrating Fixed Monitoring Systems with LowCost Sensors to Create High-Resolution Air Quality Maps for the Northern China Plain Region[J]. ACS Earth and Space Chemistry, 2021, 5(11): 3022-3035.
[4] QIU S, CHEN B, WANG R, et al. Estimating contaminant source in chemical industry park using UAV-based monitoring platform, artificial neural network and atmospheric dispersion simulation[J]. RSC Advances, 2017, 7(63): 39726-39738.
[5] RAHBAR F, MARJOVI A, MARTINOLI A. An algorithm for odor source localization based on source term estimation[C]//2019 International Conference on Robotics and Automation (ICRA).2019: 973-979.
[6] RHODES C, LIU C, CHEN W H. Informative path planning for gas distribution mapping in cluttered environments[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; RSJ, 2020: 6726-6732.
[7] RICCI F, SCARPONI G E, PASTOR E, et al. Safety distances for storage tanks to prevent fire damage in Wildland-Industrial Interface[J]. Process Safety and Environmental Protection, 2021, 147: 693-702.
[8] HUANG P, CHEN M, CHEN K, et al. A combined real-time intelligent fire detection and forecasting approach through cameras based on computer vision method[J]. Process Safety and Environmental Protection, 2022, 164: 629-638.
[9] DIWATE R B, PATIL L V, KHODASKAR M R, et al. Lower Complex CNN Model for Fire Detection in Surveillance Videos[C]//2021 International Conference on Emerging Smart Computing and Informatics (ESCI). IEEE, 2021: 380-384.
[10] HUANG L, LIU G, WANG Y, et al. Fire detection in video surveillances using convolutional neural networks and wavelet transform[J]. Engineering Applications of Artificial Intelligence,2022, 110: 104737.
[11] SAPONARA S, ELHANASHI A, GAGLIARDI A. Exploiting R-CNN for video smoke/fire sensing in antifire surveillance indoor and outdoor systems for smart cities[C]//2020 IEEE International Conference on Smart Computing (SMARTCOMP). IEEE; IEEE Comp Soc, 2020: 392-397.
[12] CHAOXIA C, SHANG W, ZHANG F. Information-guided flame detection based on faster RCNN[J]. IEEE Access, 2020, 8: 58923-58932.
[13] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016: 779-788.
[14] NGUYEN A, NGUYEN H, TRAN V, et al. A visual real-time fire detection using single shot multibox detector for uav-based fire surveillance[C]//2020 IEEE Eighth International Conference on Communications and Electronics (ICCE). 2021: 338-343.
[15] QIN Y Y, CAO J T, JI X F. Fire detection method based on depthwise separable convolution and yolov3[J]. International Journal of Automation and Computing, 2021, 18: 300-310.
[16] ZHAO L, ZHI L, ZHAO C, et al. Fire-YOLO: A small target object detection method for fire inspection[J]. Sustainability, 2022, 14(9): 4930.
[17] POIKONEN S, GOLDEN B, WASIL E A. A branch-and-bound approach to the traveling salesman problem with a drone[J]. INFORMS Journal on Computing, 2019, 31(2): 335-346.
[18] İLHAN İ, GÖKMEN G. A list-based simulated annealing algorithm with crossover operator for the traveling salesman problem[J]. Neural Computing and Applications, 2022, 34(10): 1-26.
[19] BEHMANESH R, RAHIMI I, GANDOMI A H. Evolutionary many-objective algorithms for combinatorial optimization problems: a comparative study[J]. Archives of Computational Methods in Engineering, 2021, 28(2): 673-688.
[20] HALIM A H, ISMAIL I. Combinatorial optimization: comparison of heuristic algorithms in travelling salesman problem[J]. Archives of Computational Methods in Engineering, 2019, 26 (2): 367-380.
[21] CHAUHAN C, GUPTA R, PATHAK K. Survey of methods of solving tsp along with its implementation using dynamic programming approach[J]. International Journal of Computer Applications, 2012, 52(4).
[22] ZHOU Y, XU W, FU Z H, et al. Multi-neighborhood simulated annealing-based iterated local search for colored traveling salesman problems[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(9): 16072-16082.
[23] LIU J, LI W. Greedy permuting method for genetic algorithm on traveling salesman problem[C]//2018 8th International Conference on Electronics Information and Emergency Communication (ICEIEC). IEEE, 2018: 47-51.
[24] DU P, LIU N, ZHANG H, et al. An improved ant colony optimization based on an adaptive heuristic factor for the traveling salesman problem[J]. Journal of Advanced Transportation,2021, 2021: 1-16.
[25] MAVROVOUNIOTIS M, YANG S, VAN M, et al. Ant colony optimization algorithms for dynamic optimization: A case study of the dynamic travelling salesperson problem [research frontier][J]. IEEE Computational Intelligence Magazine, 2020, 15(1): 52-63.
[26] COLORNI A, DORIGO M, MANIEZZO V, et al. Distributed optimization by ant colonies[C]//Proceedings of the First European Conference on Artificial Life: volume 142. 1991: 134-142.
[27] DORIGO M, MANIEZZO V, COLORNI A. Ant system: optimization by a colony of cooperating agents[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics),1996, 26(1): 29-41.
[28] STUTZLE T, HOOS H. MAX-MIN ant system and local search for the traveling salesman problem[C]//Proceedings of 1997 IEEE International Conference on Evolutionary Computation(ICEC’97). IEEE, 1997: 309-314.
[29] BULLNHEIMER B. A new rank based version of the ant system: A computational study[J]. Central European Journal of Operations Research, 1999, 7: 25-38.
[30] ASCHEUER N, FISCHETTI M, GRÖTSCHEL M. A polyhedral study of the asymmetric traveling salesman problem with time windows[J]. Networks: An International Journal, 2000,36(2): 69-79.
[31] COHEN I, EPSTEIN C, ISAIAH P, et al. Discretization-based and look-ahead algorithms for the dubins traveling salesperson problem[J]. IEEE Transactions on Automation Science and Engineering, 2016, 14(1): 383-390.
[32] TUANI A F, KEEDWELL E, COLLETT M. Heterogenous adaptive ant colony optimization with 3-opt local search for the travelling salesman problem[J]. Applied Soft Computing, 2020, 97(B): 106720.
[33] WANG J, MENG M Q H. Real-time decision making and path planning for robotic autonomous luggage trolley collection at airports[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 52(4): 2174-2183.
[34] WANG J, MENG M Q H. Optimal path planning using generalized voronoi graph and multiple potential functions[J]. IEEE Transactions on Industrial Electronics, 2020, 67(12): 10621-10630.
[35] ZHANG J, WU J, SHEN X, et al. Autonomous land vehicle path planning algorithm based on improved heuristic function of A-Star[J]. International Journal of Advanced Robotic Systems, 2021, 18(5): 17298814211042730.
[36] LIU L S, LIN J F, YAO J X, et al. Path Planning for Smart Car Based on Dijkstra Algorithm and Dynamic Window Approach[J]. Wireless Communications and Mobile Computing, 2021,2021: 1-12.
[37] CHEN G, LUO N, LIU D, et al. Path planning for manipulators based on an improved probabilistic roadmap method[J]. Robotics and Computer-Integrated Manufacturing, 2021, 72: 102196.
[38] ALARABI S, LUO C, SANTORA M. A PRM Approach to Path Planning with Obstacle Avoidance of an Autonomous Robot[C]//2022 8th International Conference on Automation, Robotics and Applications (ICARA 2022). IEEE; IEEE Robot & Automat Soc; Czech Univ Life Sci Prague, 2022: 76-80.
[39] LAVALLE S M, et al. Rapidly-exploring random trees: A new tool for path planning. 1998[J]. URL http://citeseerx. ist. psu. edu/viewdoc/summary, 1998.
[40] KARAMAN S, FRAZZOLI E. Sampling-based algorithms for optimal motion planning[J]. The International Journal of Robotics Research, 2011, 30(7): 846-894.
[41] GAMMELL J D, SRINIVASA S S, BARFOOT T D. Informed RRT*: Optimal Sampling-based Path Planning Focused via Direct Sampling of an Admissible Ellipsoidal Heuristic[C]//2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014). IEEE; Robot Soc Japan; RA; SICE; IES; New Technol Fdn, 2014: 2997-3004.
[42] WANG J, CHI W, SHAO M, et al. Finding a high-quality initial solution for the RRTs algorithms in 2D environments[J]. Robotica, 2019, 37(10): 1677-1694.
[43] TAN C S, MOHD-MOKHTAR R, ARSHAD M R. A comprehensive review of coverage path planning in robotics using classical and heuristic algorithms[J]. IEEE Access, 2021, 9: 119310-119342.
[44] VAN DER HOEK W, KONRADSEN F, AMERASINGHE P H, et al. Towards a risk map of malaria for Sri Lanka: the importance of house location relative to vector breeding sites[J]. International Journal of Epidemiology, 2003, 32(2): 280-285.
[45] ANDREEV I, HITTENBERGER M, HOFER P, et al. Risks due to beyond design base accidents of nuclear power plants in Europe—the methodology of riskmap[J]. Journal of Hazardous Materials, 1998, 61(1-3): 257-262.
[46] DEY P K. Managing project risk using combined analytic hierarchy process and risk map[J]. Applied Soft Computing, 2010, 10(4): 990-1000.
[47] PRIMATESTA S, RIZZO A, LA COUR-HARBO A. Ground risk map for unmanned aircraft in urban environments[J]. Journal of Intelligent & Robotic Systems, 2020, 97(3-4): 489-509.
[48] HOLLINGER G A, SUKHATME G S. Sampling-based Motion Planning for Robotic Information Gathering.[C]//Robotics: Science and Systems: volume 3. 2013: 1-8.
[49] WANG C, CHENG J, CHI W, et al. Semantic-aware informative path planning for efficient object search using mobile robot[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 51(8): 5230-5243.
[50] LIU Y, LU W, WANG H, et al. Improved impact assessment of odorous compounds from landfills using Monte Carlo simulation[J]. Science of the Total Environment, 2019, 648: 805- 810.
[51] 周旺. 基于移动监测系统的化工园区大气污染溯源研究[D]. 浙江大学, 2022.
[52] 温凯, 王伟, 谢宜峰, 等. 基于气体扩散模型的天然气泄漏场景下无人机自主飞行控制算 法研究[J]. 石油科学通报, 2021, 6(4): 12.
[53] GAMMELL J D, BARFOOT T D, SRINIVASA S S. Informed sampling for asymptotically optimal path planning[J]. IEEE Transactions on Robotics, 2018, 34(4): 966-984.
[54] YU Z, SHEN Y, SHEN C. A real-time detection approach for bridge cracks based on YOLOv4- FPM[J]. Automation in Construction, 2021, 122.
[55] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: A New Backbone that can Enhance Learning Capability of CNN[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2020). IEEE; CVF; IEEE Comp Soc, 2020: 1571-1580.
[56] LI X, LAI T, WANG S, et al. Weighted Feature Pyramid Networks for Object Detection[C]//2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom). 2019: 1500-1504.
[57] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; CVF; IEEE Comp Soc, 2018: 8759-8768.
[58] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.
[59] 王浩. 基于化工园区火灾风险等级安全巡检机器人路径优化[D]. 北京: 北京石油化工学院, 2021.
[60] LAURI M, RITALA R. Planning for robotic exploration based on forward simulation[J]. Robotics and Autonomous Systems, 2016, 83: 15-31.