On-site safety early warning system and method for water supply and drainage facilities

Abstract

The invention discloses a water supply and drainage facility on-site safety early warning system and method, and the system comprises the following modules: a data collection module which is used for obtaining the operation state and environmental parameter data of water plant equipment of a water supply and drainage facility; the data processing module is used for cleaning, screening and aligning the collected data; the intelligent analysis module is used for analyzing the equipment state by applying machine learning and deep learning algorithms according to the processed data; and the early warning feedback module is used for sending early warning information when the intelligent analysis module finds an abnormal condition. By combining the artificial intelligence technology, management and hidden danger early warning of production safety, personnel safety and equipment safety of water supply and drainage facilities can be achieved at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of on-site supervision of water supply and drainage facilities, and in particular to an on-site safety early warning system and method for water supply and drainage facilities. Background Art

[0002] The water supply and drainage industry is an indispensable part of urban infrastructure, and undertakes the important task of ensuring urban water supply and sewage treatment. However, with the acceleration of urbanization and the increase in the demand for refined management of water companies, traditional water plants face many challenges in safety management. Especially in large water supply plants and sewage plants, the complex industrial environment leads to frequent safety accidents.

[0003] At present, the safety management of water supply and drainage facilities mostly relies on manual inspections and single parameter monitoring, which has many defects. For example, there is insufficient supervision, weak early warning capabilities, and the inability to obtain equipment operating status and environmental parameter data in real time. Managers often find it difficult to accurately identify safety hazards in massive amounts of video data, equipment data, and operating data, which makes it impossible to identify and warn potential risks in a timely manner.

[0004] Therefore, there is an urgent need for an on-site safety early warning system for water supply and drainage facilities based on artificial intelligence technology that can solve the problems existing in the existing technology. Summary of the invention

[0005] The present invention aims to utilize artificial intelligence technology, combined with multi-source heterogeneous data collected by various sensors, and integrate multi-source data such as industrial data, video security data, and vital signs data through the front-end data acquisition layer to build an intelligent early warning system for the safe, reliable, and stable operation of water plants. At the same time, it realizes the management of personnel safety, environmental safety, equipment safety, production safety, etc. and early warning of hidden dangers, builds a comprehensive, three-dimensional, and intelligent management and control system for water plants, ensures the safe operation of water plants, and builds an efficient, accurate, and comprehensive on-site safety early warning system for water plants.

[0006] According to one aspect of the present invention, there is provided an on-site safety early warning system for water supply and drainage facilities, comprising: a data acquisition module for acquiring operating status and environmental parameter data of water plant equipment in water supply and drainage facilities; a data processing module for cleaning, screening and aligning the acquired data; an intelligent analysis module for analyzing the equipment status by applying machine learning and deep learning algorithms based on the processed data; and an early warning feedback module for sending an early warning message when the intelligent analysis module finds an abnormal situation.

[0007] Preferably, the data acquisition module collects gas concentration data of hydrogen sulfide, chlorine, ozone and methane via environmental detection sensors.

[0008] Preferably, the data acquisition module collects the indicative parameter data of the operation and maintenance personnel's body temperature, blood pressure, heart rate, and conductivity via a vital sign sensor.

[0009] Preferably, the data collection module collects real-time location data of the operation and maintenance personnel via a location sensor.

[0010] Preferably, the intelligent analysis module combines machine learning and deep learning algorithms, and uses image and behavior features in video surveillance data for training to detect abnormal behavior; the intelligent analysis module automatically generates an alarm based on the detected abnormal behavior and provides an abnormal behavior analysis report to assist security management and decision-making.

[0011] Preferably, the intelligent analysis module also predicts the probability of water plant accidents, personnel accidents and equipment failures based on the safety operation data, personnel accident data and equipment operation data of standard traditional water plants.

[0012] Preferably, the following formula is used to predict the probability of water plant accidents, personnel accidents, and equipment failures:

[0013] Among them, P(E i |F) represents event E i The probability of occurrence under a given feature F, L is the loss function, For feature x i The partial derivative of , Z is the normalization constant. Preferably, the health index HI of the equipment operation status is recalculated every time Δt using the following formula:

[0014] Among them, μ is the mean value of the device under normal operating conditions, and v(t) is the current eigenvector.

[0015] Preferably, the on-site safety warning system for water supply and drainage facilities includes: performing adaptability tests on a variety of artificial intelligence algorithm models in the artificial intelligence algorithm library, wherein the multiple artificial intelligence algorithm models include at least one of the following: decision tree, support vector machine, random forest and deep neural network; based on the test results, selecting the artificial intelligence algorithm model for algorithm combination to optimize data processing efficiency and prediction accuracy.

[0016] According to another aspect of the present invention, there is provided an on-site safety early warning method for water supply and drainage facilities, comprising: obtaining the operating status and environmental parameter data of water plant equipment of the water supply and drainage facilities; cleaning, screening and aligning the collected data; analyzing the equipment status by applying machine learning and deep learning algorithms based on the processed data; and sending early warning information when an abnormal situation is found.

[0017] The present invention discloses a water supply and drainage facility on-site safety early warning system and method, the system includes the following modules: a data acquisition module, used to obtain the water plant equipment operation status and environmental parameter data of the water supply and drainage facility; a data processing module, used to clean, filter and align the collected data; an intelligent analysis module, used to analyze the equipment status by applying machine learning and deep learning algorithms according to the processed data; and an early warning feedback module, used to send early warning information when the intelligent analysis module finds an abnormal situation. The present invention can simultaneously realize the management of production safety, personnel safety, and equipment safety of water supply and drainage facilities and early warning of hidden dangers by combining artificial intelligence technology. Specifically, the system should be able to realize comprehensive data collection and efficient abnormality detection by integrating data acquisition, processing, analysis and feedback modules. By combining advanced machine learning and deep learning algorithms, the system can comprehensively analyze and predict the equipment status, timely discover potential risks, and avoid the occurrence of safety accidents. This new early warning system will greatly improve the comprehensiveness and real-time monitoring of water supply and drainage facilities, and provide solid protection for the safe operation of water infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0019] Figure 1 is a diagram showing the composition of an on-site safety early warning system for water supply and drainage facilities according to an embodiment of the present invention;

[0020] Figure 2 is a flow chart of a field safety early warning system for water supply and drainage facilities according to an embodiment of the present invention; and

[0021] Figure 3 It is a flow chart of a method for on-site safety early warning of water supply and drainage facilities according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] Reference will now be made in detail to various embodiments of the present invention, examples of which are shown in the accompanying drawings and described below. For ease of interpretation and precise definition in the appended claims, the terms "upper", "lower", "inner" and "outer" are used to describe features of the exemplary embodiments shown in the drawings with reference to their positions.

[0024] The embodiment of the present invention provides a water supply and drainage facility on-site safety early warning system, such as Figure 1 As shown, it includes: a data acquisition module, which is used to obtain the operating status and environmental parameter data of the water plant equipment of the water supply and drainage facilities; a data processing module, which is used to clean, filter and align the collected data; an intelligent analysis module, which is used to analyze the equipment status according to the processed data by applying machine learning and deep learning algorithms; and an early warning feedback module, which is used to send early warning information when the intelligent analysis module finds an abnormal situation.

[0025] Traditional water plants use manual inspections and single parameter monitoring, which have the shortcomings of insufficient supervision and weak early warning capabilities in safety management. The on-site safety early warning system for water supply and drainage facilities in the present invention realizes comprehensive data collection and efficient anomaly detection by integrating data collection, processing, analysis and feedback modules. This system can obtain multi-source heterogeneous data in real time, including equipment operating parameters, environmental parameters, personnel health data, etc., and use advanced artificial intelligence algorithms for comprehensive analysis. This system greatly improves the comprehensiveness and real-time nature of monitoring, and can identify potential risks more quickly and avoid the occurrence of safety accidents.

[0026] According to an embodiment of the present invention, the data acquisition module collects gas concentration data of hydrogen sulfide, chlorine, ozone, and methane via environmental detection sensors.

[0027] In the embodiment of the present invention, through the integration of multiple sensors, the concentration changes of multiple harmful gases can be monitored simultaneously, ensuring that an early warning is triggered immediately when the gas concentration exceeds the standard, thereby improving detection efficiency, reducing the frequency and workload of manual inspections, and providing protection for facility operation and personnel safety.

[0028] According to an embodiment of the present invention, the data acquisition module collects the indicator parameter data of the operation and maintenance personnel's body temperature, blood pressure, heart rate, and conductivity via the vital sign sensor.

[0029] In the embodiment of the present invention, through the integration of multiple sensors, the health data of operation and maintenance personnel can be comprehensively and accurately obtained, abnormal situations can be discovered in time, and the monitoring efficiency is improved.

[0030] According to an embodiment of the present invention, the data collection module collects real-time location data of the operation and maintenance personnel via a location sensor.

[0031] In the embodiment of the present invention, through the application of the position sensor, the position information of the operation and maintenance personnel can be obtained in real time, ensuring that they can be quickly located and take corresponding measures when an emergency occurs. This improves the real-time and accuracy of monitoring and enhances the emergency response capability.

[0032] According to an embodiment of the present invention, the intelligent analysis module combines machine learning and deep learning algorithms, uses image and behavior features in video surveillance data for training, and detects abnormal behavior; the intelligent analysis module automatically generates an alarm based on the detected abnormal behavior, and provides an abnormal behavior analysis report to assist security management and decision-making.

[0033] The embodiments of the present invention realize real-time monitoring and abnormal behavior detection of operation and maintenance personnel through artificial intelligence algorithm technology, can timely discover and deal with potential security issues, and improve the accuracy and response speed of monitoring.

[0034] According to an embodiment of the present invention, the intelligent analysis module also predicts the probability of water plant accidents, personnel accidents, and equipment failures based on the safety operation data, personnel accident data, and equipment operation data of standard traditional water plants.

[0035] The intelligent analysis module in the present invention can accurately predict the probability of safety incidents in water plants by integrating a variety of historical data and real-time data, using statistical analysis and machine learning techniques. Compared with traditional static safety monitoring, the system of the present invention not only takes into account the operating status of the current equipment, but also uses historical accident data and equipment performance data for comprehensive evaluation. By using complex statistical models such as Gaussian mixture models and Bayesian networks, the system can identify potential failure modes and provide specific accident probabilities. This prediction function enables water plant managers to take preventive measures in advance and improve the foresight and effectiveness of safety management.

[0036] According to an embodiment of the present invention, the following formula is used to predict the probability of water plant accidents, personnel accidents, and equipment failures:

[0037] Among them, P(E i |F) represents event E i The probability of occurrence under a given feature F, L is the loss function, is the partial derivative of feature xi, and Z is the normalization constant.

[0038] The present invention accurately calculates and updates the probability of various safety events by combining the Bayesian network model and the loss function. Unlike the traditional experience-based fault prediction method, this system uses a rigorous mathematical model to optimize the prediction model by calculating the gradient of the loss function, which not only improves the accuracy of the prediction, but also enables the system to dynamically adjust and update the risk model to adapt to the changing operating environment and data distribution. This adaptive prediction mechanism significantly improves the flexibility and reliability of the system, enabling it to maintain efficient monitoring capabilities under different operating conditions.

[0039] According to an embodiment of the present invention, the health index HI of the equipment operation status is recalculated every time Δt using the following formula:

[0040] Among them, μ is the mean value of the device under normal operating conditions, and v(t) is the current eigenvector.

[0041] Through the health index (HI) model, the system can dynamically evaluate the operating status of the equipment. Compared with the traditional alarm system based on fixed thresholds, the HI model of the present invention takes into account the historical performance data of the equipment and judges the health status of the equipment by calculating the degree of deviation of the feature vector. This method can more accurately identify the gradual degradation or sudden failure of the equipment, avoiding the problem of missed reports or false alarms caused by setting unreasonable thresholds. The application of the HI model enables the system to provide real-time equipment health monitoring, helping managers to perform maintenance and maintenance in a timely manner, extending the service life of the equipment and improving operating efficiency.

[0042] According to an embodiment of the present invention, the on-site safety warning system for water supply and drainage facilities includes: performing adaptability tests on a variety of artificial intelligence algorithm models in an artificial intelligence algorithm library, wherein the multiple artificial intelligence algorithm models include at least one of the following: decision tree, support vector machine, random forest and deep neural network; based on the test results, selecting the artificial intelligence algorithm model for algorithm combination to optimize data processing efficiency and prediction accuracy.

[0043] In the embodiment of the present invention, through the combination and optimization of multiple algorithm models, more efficient and accurate anomaly detection and risk prediction are achieved, thereby improving the intelligence level and reliability of the system.

[0044] According to another embodiment of the present invention, a method for early warning of safety on site of water supply and drainage facilities is provided. Figure 3 As shown, it includes: obtaining the operating status and environmental parameter data of water plant equipment of water supply and drainage facilities; cleaning, screening and aligning the collected data; analyzing the equipment status by applying machine learning and deep learning algorithms based on the processed data; and sending early warning information when abnormal conditions are found.

[0045] Traditional water plants use manual inspections and single parameter monitoring, which have the disadvantages of insufficient supervision and weak early warning capabilities in safety management. The method in the embodiment of the present invention can obtain the operating status and environmental parameter data of water plant equipment of drainage facilities in real time, and use advanced artificial intelligence algorithms for comprehensive analysis, thereby greatly improving the comprehensiveness and real-time nature of monitoring, identifying potential risks more quickly, and avoiding the occurrence of safety accidents.

[0046] The present invention is further described in detail below in conjunction with specific implementation modes and accompanying drawings.

[0047] Figure 2 1 is a flow chart of a water supply and drainage facility on-site safety early warning system according to an embodiment of the present invention. Figure 2 As shown, the system mainly includes a data acquisition module, a data processing module, an intelligent analysis module and a warning feedback module.

[0048] Data collection module: Through a variety of sensors deployed at water infrastructure sites and on the bodies of operation and maintenance personnel, it collects and transmits diversified on-site data in real time, including equipment operating parameters, vital signs data, environmental parameters, video data, personnel location data, etc.

[0049] Data processing module: cleans, integrates and standardizes all types of collected data to ensure the accuracy and effectiveness of subsequent analysis.

[0050] Intelligent analysis module: Use artificial intelligence algorithms (such as machine learning, deep learning, etc.) to conduct pattern mining and behavior prediction on processed data, so as to achieve real-time assessment of the status of operation and maintenance personnel and early warning of potential risks.

[0051] Early warning feedback module: When the intelligent analysis module detects abnormal equipment operation or predicts possible problems, the system will immediately trigger an early warning signal and notify relevant managers to take countermeasures through a visual interface or mobile phone APP.

[0052] The analysis method of personnel health detection in the on-site safety early warning system is as follows:

[0053] Collect on-site vital sign data, such as body temperature, blood pressure, and heart rate, and compare them with preset values. By comparing the vital sign data with the set operation and maintenance personnel vital sign warning values, no processing will be performed if it is lower than the warning value. If the potential risk exceeds the set threshold, the safety warning system will send an abnormal signal alarm to remind the water plant central control staff on duty. When the staff on duty cannot get in touch with the on-site personnel, they need to go to the site where the personnel are located to check.

[0054] The relative positions of the on-site personnel are collected and compared with the positions and time. If there is no relative movement within a unit of time and the position does not change after a certain period of time, the potential risk exceeds the set threshold. The safety warning system sends an abnormal signal alarm to remind the water plant central control staff on duty. If the staff on duty cannot get in touch with the on-site personnel, they need to go to the site where the personnel are located to check.

[0055] The relative positions of on-site personnel are collected, and by comparing the personnel positions with the high-precision maps of the area, if the personnel are located in a confined space or a designated dangerous area, the video cameras near the personnel are linked to monitor the dynamic safety status of the personnel in real time. If the potential risk exceeds the set threshold, the safety warning system will send an abnormal signal alarm to remind the central control staff on duty at the water plant. When the staff on duty cannot get in touch with the on-site personnel, they need to go to the site where the personnel are located to check.

[0056] The conductivity of the wearable device collected by the personnel is compared with the set warning value. If it is lower than the warning value, no processing will be performed. If the potential risk exceeds the set threshold, the safety warning system will send an abnormal signal alarm to remind the water plant central control staff on duty. When the staff on duty cannot get in touch with the on-site personnel, they need to go to the site where the personnel are located to check.

[0057] The method for obtaining the analytical data of environmental detection in the on-site safety early warning system is as follows:

[0058] The data of harmful gases such as hydrogen sulfide, chlorine, ozone and methane collected on site are compared with the set warning values. If the data is lower than the warning value, no processing will be performed. If the potential risk exceeds the set threshold, the safety warning system will send out an abnormal signal alarm to remind the central control staff on duty at the water plant. The staff on duty need to take emergency measures and arrive at the site where the personnel are located to investigate the dangerous situation.

[0059] The method for obtaining the analysis data of the video information in the on-site safety early warning system is as follows:

[0060] Through video surveillance of the fenced area, AI target detection and tracking technology, and behavior recognition algorithms, abnormal behavior of operators is detected. Once an alert is triggered, if the potential risk exceeds the set threshold, the safety warning system will send out an abnormal signal alarm to alert the water plant central control staff on duty. When the staff on duty cannot get in touch with the on-site personnel, they need to go to the site where the personnel are located to check.

[0061] The method for obtaining the analytical data of the process equipment operating parameters in the on-site safety early warning system is as follows:

[0062] The electrical parameters of the main equipment on site, such as current, voltage, temperature, etc., are collected and compared with the preset values. By comparing the monitoring data with the set warning value, no processing is performed if it is lower than the warning value. If the potential risk exceeds the set threshold, the safety early warning system will send out an abnormal signal alarm to remind the central control staff on duty at the water plant. The on-site personnel will go to the site where the faulty equipment is located to investigate the dangerous situation.

[0063] Traditional water supply and drainage facilities have traditional problems such as wide distribution, difficulty in management, and inconsistent process standards. Managers are drowned in massive video data, equipment data, and operation data, making it difficult to accurately discover safety hazards. The present invention solves the problems of difficulty in on-site supervision of water supply and drainage facilities and low intelligence level through management of personnel safety, environmental safety, equipment safety, production safety, etc. and early warning of hidden dangers. The present invention implements risk assessment and early warning of various types of operation data, takes different emergency measures for different risks, and avoids safety accidents caused by inadequate emergency measures. The use of the patent of the present invention can prevent major accidents of life safety of personnel and has high safety.

[0064] The artificial intelligence-based on-site safety early warning system for water supply and drainage facilities of the present invention can provide safety protection for on-site operation and maintenance personnel of water infrastructure.

[0065] The above embodiments are only examples for clearly explaining the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications may be made based on the following description, and these various changes, modifications, substitutions and deformations derived from the principles and spirit of the present invention still fall within the scope of protection of the present invention.

Claims

1. A water supply and drainage facility on-site safety early warning system, characterized in that: include: Data acquisition module, used to obtain the operating status and environmental parameter data of water plant equipment of water supply and drainage facilities; A data processing module, used to clean, filter and align the collected data; Intelligent analysis module, which is used to analyze the equipment status by applying machine learning and deep learning algorithms based on the processed data; as well as The early warning feedback module is used to send early warning information when the intelligent analysis module finds an abnormal situation.

2. The on-site safety early warning system for water supply and drainage facilities according to claim 1 is characterized in that: The data acquisition module collects gas concentration data of hydrogen sulfide, chlorine, ozone and methane via environmental detection sensors.

3. The on-site safety early warning system for water supply and drainage facilities according to claim 1 is characterized in that: The data acquisition module collects the indicative parameter data of the operation and maintenance personnel's body temperature, blood pressure, heart rate, and conductivity via the vital sign sensor.

4. The on-site safety early warning system for water supply and drainage facilities according to claim 1 is characterized in that: The data collection module collects real-time location data of the operation and maintenance personnel via a location sensor.

5. The on-site safety early warning system for water supply and drainage facilities according to claim 1 is characterized in that: The intelligent analysis module combines machine learning and deep learning algorithms, and uses image and behavior features in video surveillance data for training to detect abnormal behavior; The intelligent analysis module automatically generates an alarm based on the detected abnormal behavior and provides an abnormal behavior analysis report to assist security management and decision-making.

6. The on-site safety early warning system for water supply and drainage facilities according to claim 5 is characterized in that: The intelligent analysis module also predicts the probability of water plant accidents, personnel accidents, and equipment failures based on the safety operation data, personnel accident data, and equipment operation data of standard traditional water plants.

7. The on-site safety early warning system for water supply and drainage facilities according to any one of claims 1 to 6, characterized in that: The following formula is used to predict the probability of water plant accidents, personnel accidents, and equipment failures: Among them, P(E i |F) represents event E i The probability of occurrence under a given feature F, L is the loss function, For feature x i The partial derivative of , Z is the normalization constant.

8. The on-site safety early warning system for water supply and drainage facilities according to claim 7 is characterized in that: Use the following formula to recalculate the health index HI of the equipment operation status every time Δt: Wherein, μ is the mean value of the device under normal operating conditions, and v(t) is the current eigenvector.

9. The on-site safety early warning system for water supply and drainage facilities according to any one of claims 1 to 6, characterized in that: include: Conducting adaptability tests on various artificial intelligence algorithm models in the artificial intelligence algorithm library, wherein the various artificial intelligence algorithm models include at least one of the following: decision tree, support vector machine, random forest, and deep neural network; Based on the test results, artificial intelligence algorithm models are selected for algorithm combination to optimize data processing efficiency and prediction accuracy.

10. A method for on-site safety early warning of water supply and drainage facilities, characterized in that: include: Obtain the operating status and environmental parameter data of water plant equipment of water supply and drainage facilities; Clean, filter and align the collected data; Analyze the equipment status by applying machine learning and deep learning algorithms based on the processed data; as well as Send warning information when abnormal conditions are detected.

Images