Intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion

Abstract

The invention relates to the technical field of intelligent monitoring, in particular to an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion, and the method comprises the steps: determining a corresponding target cold source region, obtaining multi-type data corresponding to the target cold source region, inputting the multi-type data into a pre-built multi-source heterogeneous data fusion platform for fusion, and obtaining a target cold source region; acquiring corresponding cold source monitoring data; calling a prediction identification model pre-trained for the disaster-causing organisms, inputting the cold source monitoring data into the prediction identification model, and obtaining a prediction result corresponding to the disaster-causing organisms at regular intervals; whether disaster-causing organisms will enter the target cold source area or not is judged based on the prediction result, if yes, early warning data are sent based on the monitoring platform, and the early warning data comprise the target organisms, the target time period and the corresponding target area. According to the invention, the monitoring accuracy of the cold source disaster-causing object can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent monitoring, and in particular to an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion. Background Art

[0002] With the development of coastal nuclear power plants, aquatic organisms such as shrimps and jellyfish frequently invade the cooling water system of nuclear power plants, causing a series of problems such as circulating water pump tripping, reactor automatic shutdown and even the shutdown of the entire unit. These problems not only affect the normal operation of nuclear power plants, but also pose a potential threat to public safety.

[0003] Traditional filtration systems, such as grilles and filters, have limitations in dealing with these cold source hazards, especially when dealing with sudden large-scale invasions of aquatic organisms. Although some nuclear power plants have tried to introduce autonomous cold source alarm and early warning platforms to solve this problem, existing technical means still face challenges such as insufficient monitoring data, imperfect information sharing mechanisms, and delayed early warning responses.

[0004] From the above, we can see that how to improve the monitoring accuracy of cold source disaster objects still needs to be solved. Summary of the invention

[0005] In order to improve the monitoring accuracy of cold source disaster-causing objects, the present application provides an intelligent cold source disaster-causing object monitoring method, system, storage medium and terminal based on multi-sensor fusion.

[0006] In the first aspect, the present application provides an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion, which adopts the following technical solutions:

[0007] An intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion, comprising:

[0008] Determine the corresponding target cold source area, obtain multi-type data corresponding to the target cold source area, input the multi-type data into a pre-built multi-source heterogeneous data fusion platform for fusion, and obtain the corresponding cold source monitoring data, wherein the multi-type data includes video data, image data, and environmental parameter data for the target cold source area;

[0009] Retrieving a prediction and recognition model pre-trained for disaster-causing organisms, inputting the cold source monitoring data into the prediction and recognition model, and obtaining prediction results corresponding to disaster-causing organisms on a regular basis;

[0010] Based on the prediction results, it is determined whether disaster-causing organisms will enter the target cold source area. If so, early warning data is issued based on the monitoring platform, where the early warning data includes target organisms, target time period and corresponding target area.

[0011] By adopting the above technical solution, the target cold source area is determined and multiple types of data (including video data, image data, and environmental parameter data) are obtained. These data are input into the multi-source heterogeneous data fusion platform for fusion processing to generate cold source monitoring data; then, the cold source monitoring data is analyzed using the pre-trained prediction and recognition model to obtain the prediction results of disaster-causing organisms. Based on the prediction results, it is determined whether disaster-causing organisms will enter the target cold source area. If so, early warning data containing target organisms, target time periods, and target areas is issued through the monitoring platform. Through the fusion of multi-sensor data and the prediction model, the monitoring accuracy of cold source disaster-causing objects is significantly improved, effectively preventing potential safety risks.

[0012] Optionally, the method further comprises:

[0013] Obtain historical water flow data corresponding to the target cold source area, and obtain water flow law data corresponding to the target cold source area;

[0014] Using a flow meter to obtain actual water flow data corresponding to the target cold source area, comparing the actual water flow data with the water flow law data to determine whether there is a water flow change, wherein the actual water flow data includes water flow speed and direction;

[0015] If so, obtain the actual water flow changes corresponding to the target cold source area, input the actual water flow changes into the prediction and recognition model, obtain the corresponding recognition results, and determine whether there are disaster-causing organisms located in the target cold source waters based on the recognition results.

[0016] By adopting the above technical solution, when there is a change in water flow, the actual water flow change data is obtained and input into the prediction and recognition model to obtain the recognition result, and based on the result, it is judged whether there are disaster-causing organisms in the target cold source water area. By combining water flow data and multi-sensor data, the monitoring accuracy of cold source disaster-causing objects can be further improved, and the early warning capability and reliability of the system can be enhanced.

[0017] Optionally, the method further comprises:

[0018] Retrieve the relationship mapping table between the environment and monitoring strategies corresponding to the target cold source area under different environments, where the different conditions include different seasons and different climate conditions;

[0019] Obtain current corresponding environmental data, and determine a corresponding target monitoring strategy based on the environment;

[0020] The current corresponding monitoring strategy is optimized based on the target monitoring strategy.

[0021] By adopting the above technical solution, the relationship mapping table between the environment and monitoring strategy corresponding to the target cold source area under different environmental conditions is retrieved to obtain the current environmental data, determine the corresponding target monitoring strategy, and optimize the current monitoring strategy accordingly. Through the above solution, the monitoring strategy can be dynamically adjusted according to real-time environmental changes, which can improve the pertinence and effectiveness of monitoring, thereby more accurately identifying and preventing the risks of cold source disasters.

[0022] Optionally, in the process of judging whether disaster-causing organisms will enter the target cold source area based on the prediction results, and if so, issuing early warning data based on the monitoring platform, the method further includes:

[0023] If there are disaster-causing organisms, the pre-set warning level will be called up, among which the warning level is divided into three levels: low, medium and high;

[0024] Determining a target warning level corresponding to the prediction result based on the prediction result and the warning level;

[0025] Generate corresponding warning data based on the target warning level, and the warning data also includes recommended preventive measures; send the warning data to relevant personnel through a monitoring platform or a mobile application.

[0026] By adopting the above technical solution, in the presence of disaster-causing organisms, the pre-set warning level (divided into three levels: low, medium and high) is called up, the corresponding target warning level is determined according to the prediction results, and warning data containing recommended preventive measures are generated; through graded warnings and specific preventive measures, the accuracy and effectiveness of the warnings are improved, ensuring that relevant personnel can take timely action to effectively prevent and respond to the risks of cold source disasters.

[0027] Optionally, the method further comprises:

[0028] Install an infrared sensor in the target cold source area to collect temperature distribution data corresponding to the target cold source area in real time, and identify the corresponding temperature abnormal area based on the temperature distribution data;

[0029] Retrieving abnormal temperature data corresponding to the abnormal temperature area, fusing the abnormal temperature data with the multi-type data, and generating corresponding comprehensive monitoring results;

[0030] Based on the comprehensive monitoring results, the operating status of the cold source equipment in the target cold source area is evaluated. If there is an abnormality in the cold source equipment, a corresponding emergency notification is generated and sent to the relevant responsible persons, wherein the operating status includes judging whether there is overheating or poor cooling.

[0031] By adopting the above technical solution, the abnormal temperature data is integrated with multi-type data to generate comprehensive monitoring results, and the operating status of the cold source equipment is evaluated based on the comprehensive monitoring results to determine whether there are problems such as overheating and poor cooling. If an abnormality is found in the cold source equipment, an emergency notification is generated and sent to the relevant responsible person through the monitoring platform or mobile application, which can improve the evaluation accuracy of the operating status of the cold source equipment, and can also promptly discover and deal with potential problems to ensure the stable operation of the cold source system.

[0032] Optionally, the method further comprises:

[0033] Determine the difficult-to-monitor area with weak fixed sensor signals in the target area and select the drone corresponding to the target cold source area. The drone is equipped with multiple types of sensors to ensure that the corresponding difficult-to-monitor area can be covered;

[0034] Determine a preset path corresponding to the drone based on the difficult-to-monitor area, set the inspection frequency corresponding to the drone, control the drone to navigate along the preset path and obtain multi-source monitoring data of the drone on the target cold source area;

[0035] The multi-source monitoring data is input into a prediction model, and a detailed inspection report is generated based on the prediction results of the prediction model.

[0036] By adopting the above-mentioned technical solutions, the flexible inspection and multi-source data fusion of drones can make up for the shortcomings of fixed sensors, improve the monitoring coverage and accuracy of difficult-to-monitor areas, ensure a comprehensive grasp of the real-time status of the cold source area, and promptly discover and deal with potential problems.

[0037] Optionally, the method further comprises:

[0038] Determine the key areas corresponding to the target cold source area, and install air quality sensors in the key areas, wherein the key areas include the surroundings of the equipment, vents, and air inlets;

[0039] Acquire air quality data corresponding to the key area, wherein the air quality data includes PM2.5 concentration, carbon dioxide concentration and corresponding change trends;

[0040] The air quality data is compared with a preset reference value, and if a potential risk is identified, corresponding warning data is generated.

[0041] By adopting the above technical solutions, the air quality in key areas can be monitored in real time, potential risks can be discovered and warned in a timely manner, and the monitoring accuracy and safety of the operating environment of the cold source equipment can be improved, ensuring that the equipment operates in a good environment and preventing equipment failures and safety hazards caused by air quality problems.

[0042] In the second aspect, the present application provides an intelligent cold source disaster-causing object monitoring system based on multi-sensor fusion, which adopts the following technical solutions:

[0043] An intelligent cold source disaster monitoring system based on multi-sensor fusion, comprising:

[0044] The target cold source area determination module is used to determine the corresponding target cold source area, obtain multi-type data corresponding to the target cold source area, input the multi-type data into a pre-built multi-source heterogeneous data fusion platform for fusion, and obtain the corresponding cold source monitoring data, wherein the multi-type data includes video data, image data, and environmental parameter data for the target cold source area;

[0045] A prediction result acquisition module is used to retrieve a prediction and recognition model pre-trained for disaster-causing organisms, and input the cold source monitoring data into the prediction and recognition model to obtain prediction results corresponding to disaster-causing organisms on a regular basis;

[0046] The judgment module is used to judge whether disaster-causing organisms will enter the target cold source area based on the prediction results. If so, early warning data is issued based on the monitoring platform, where the early warning data includes target organisms, target time period and corresponding target area;

[0047] A memory, used for storing a program of an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion;

[0048] The program in the processor memory can be loaded and executed by the processor to realize an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion.

[0049] In a third aspect, the present application provides a computer storage medium capable of storing a corresponding program, which has the effect of improving the monitoring accuracy of cold source disaster-causing objects, and adopts the following technical solution:

[0050] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion.

[0051] In a fourth aspect, the present application provides a circulating water pump, which adopts the following technical solution:

[0052] An intelligent terminal comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes the above-mentioned intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion.

[0053] In summary, the present application includes at least one of the following beneficial technical effects:

[0054] 1. Use the pre-trained prediction and recognition model to analyze the cold source monitoring data, obtain the prediction results of disaster-causing organisms, and timely judge and warn potential disaster-causing organisms entering the target cold source area; combine historical water flow data and actual water flow data to judge water flow changes and further improve the monitoring accuracy of cold source disaster-causing objects.

[0055] 2. Adjust the monitoring strategy according to different environmental conditions (such as season and climate) to ensure the pertinence and effectiveness of monitoring; install air quality sensors in key areas to monitor PM2.5 concentration, carbon dioxide concentration and other parameters in real time, promptly detect and warn of potential risks, and ensure that the equipment operates in a good environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 The present invention is a flow chart of a method for intelligent cold source disaster-causing object monitoring based on multi-sensor fusion according to an exemplary embodiment.

[0057] Figure 2 It is a structural block diagram of an intelligent cold source disaster-causing object monitoring system based on multi-sensor fusion according to an exemplary embodiment. DETAILED DESCRIPTION

[0058] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings.

[0059] An intelligent cold source disaster-causing object monitoring method, system, storage medium and terminal based on multi-sensor fusion, by determining the target cold source area and obtaining multi-type data, these data are input into the multi-source heterogeneous data fusion platform for fusion processing to generate cold source monitoring data; then, the cold source monitoring data is analyzed using the pre-trained prediction and recognition model to obtain the prediction results of disaster-causing organisms. Based on the prediction results, it is judged whether there will be disaster-causing organisms entering the target cold source area. If so, the monitoring platform will issue early warning data containing the target organisms, target time period and target area. Through the fusion and prediction model of multi-sensor data, the monitoring accuracy of cold source disaster-causing objects is significantly improved, and potential safety risks are effectively prevented.

[0060] Reference Figure 1 The present application embodiment discloses an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion, comprising:

[0061] S100, determine the corresponding target cold source area, obtain multi-type data corresponding to the target cold source area, input the multi-type data into a pre-built multi-source heterogeneous data fusion platform for fusion, and obtain corresponding cold source monitoring data.

[0062] Among them, first determine the specific cold source area that needs to be monitored, such as chillers, freezers, etc. as target cold source areas, and then mark the key locations of the target cold source areas, such as the surroundings, imports and exports, and vents of some equipment.

[0063] Various types of sensors are installed in the target cold source area, including cameras (for video data), image sensors, temperature sensors, humidity sensors, pressure sensors, etc., through which multiple types of data of the target cold source area are collected in real time. The multiple types of data include but are not limited to video data, image data, temperature data, humidity data, pressure data, etc. The comprehensiveness and diversity of the monitoring data are ensured by collecting multiple types of data.

[0064] Then, the various types of collected data are transmitted to the multi-source heterogeneous data fusion platform, and the multi-type data are processed comprehensively using data fusion algorithms (such as Kalman filtering, particle filtering, etc.) to generate unified cold source monitoring data. Among them, the multi-source heterogeneous data fusion platform is a system for integrating and processing data from multiple different sources and types. It generates more accurate and comprehensive monitoring results by comprehensively processing multiple types of data (such as video, images, temperature, humidity, pressure, etc.).

[0065] S110, calling a prediction and recognition model pre-trained for disaster-causing organisms, inputting cold source monitoring data into the prediction and recognition model, and obtaining prediction results corresponding to disaster-causing organisms on a regular basis.

[0066] Among them, the prediction and recognition model is trained in advance, and the training process includes the following steps: first, a large amount of sample data from the target cold source area is collected, including positive samples (the presence of disaster-causing organisms) and negative samples (the absence of disaster-causing organisms); second, these sample data are labeled and preprocessed to ensure the quality and consistency of the data; then, the initial model is trained using the labeled sample data, and the model parameters are continuously adjusted through iterative optimization algorithms (such as gradient descent) until the model reaches the predetermined accuracy standard; finally, the model is regularly updated and verified to adapt to environmental changes and new species of disaster-causing organisms, thereby ensuring the continued effectiveness and accuracy of the model.

[0067] The fused cold source monitoring data is then input into the prediction and recognition model. The prediction and recognition model generates prediction results about disaster-causing organisms based on the input data. The prediction results include information such as the type, quantity, and location of the disaster-causing organisms, so that potential disaster-causing organisms can be identified in advance. The prediction results also need to be updated regularly to ensure the real-time and effectiveness of monitoring.

[0068] S120, judging whether disaster-causing organisms will enter the target cold source area based on the prediction results, and if so, issuing early warning data based on the monitoring platform.

[0069] Among them, by analyzing the prediction results, it can be determined whether there is a risk of disaster-causing organisms entering the target cold source area. For example, when the prediction result exceeds a threshold, it is considered that there is a risk of disaster-causing organisms entering. If it is determined that there is a risk of disaster-causing organisms entering, early warning data is generated, and the early warning data includes the type of disaster-causing organisms, the expected time period of entry, and the specific target area. The early warning data can also be sent to relevant personnel through a monitoring platform or a mobile application.

[0070] Through the above steps, comprehensive, accurate and real-time monitoring of cold source disaster objects is achieved. The integration of multi-type data and the application of advanced prediction models have significantly improved the accuracy and reliability of monitoring, and effectively prevented and responded to potential safety risks.

[0071] It should be pointed out here that after determining that there are disaster-causing organisms entering the target cold source area, the following steps are also performed:

[0072] In the process of judging whether disaster-causing organisms will enter the target cold source area based on the prediction results, and if so, issuing early warning data based on the monitoring platform, the method further includes:

[0073] S1201: If there are disaster-causing organisms, the pre-set warning level is called up.

[0074] If a disaster-causing organism is detected, the pre-set warning level is called from the system. Warning levels are usually divided into three levels: low, medium, and high. Each level corresponds to a different degree of risk and response measures. These warning levels are usually set based on historical data and expert experience to ensure that different levels of warning can reflect different degrees of risk.

[0075] S1202: Determine a target warning level corresponding to the prediction result based on the prediction result and the warning level.

[0076] Among them, the potential risk level is assessed based on information such as the species, number, location, and expected entry time of the disaster-causing organisms in the prediction results, which usually involves a comprehensive assessment of multiple indicators, such as the harmfulness of the species, the number of organisms, the sensitivity of the location, etc.

[0077] The assessment results are then matched with the pre-set warning level standards to determine the corresponding target warning level. For example, if the prediction results show that there are a small number of low-hazard disaster-causing organisms, it may correspond to a low-level warning; if there are a large number of high-hazard disaster-causing organisms, it may correspond to a high-level warning.

[0078] S1203, generating corresponding warning data based on the target warning level, and sending the warning data to relevant personnel through the monitoring platform or mobile application.

[0079] Among them, detailed warning data is generated according to the determined target warning level. The warning data should include the type, quantity, location, expected entry time period and corresponding target area of ​​the disaster-causing organisms. This information should be as detailed as possible so that relevant personnel can quickly understand the specific situation. In addition, recommended preventive measures are added to the warning data. These measures should be specific and feasible, such as closing specific valves, starting cleaning procedures, increasing the frequency of inspections, notifying professionals to deal with them on site, etc. The formulation of preventive measures should be based on the warning level and specific circumstances to ensure the effectiveness and feasibility of the measures.

[0080] Similarly, you can choose the appropriate delivery channel according to the actual situation. Common delivery channels include monitoring platforms, mobile applications (such as mobile APP), text messages, emails, etc. Selecting multiple channels can ensure that the warning information can be transmitted to relevant personnel in a timely manner. And the generated warning data will be sent to relevant managers, technicians or emergency response teams through the selected channels. When sending, the integrity and accuracy of the information should be ensured to avoid missing important information.

[0081] By executing the above steps S1201 to S1203, the presence of disaster-causing organisms can be detected in a timely manner, and the appropriate warning level can be determined according to the severity of the prediction results, and detailed warning data and preventive measures can be generated; it can ensure that relevant personnel can take prompt action, thereby effectively preventing and responding to potential safety risks and ensuring the safe operation of the cold source area.

[0082] In addition, there are some areas in the target cold source area that are difficult to monitor accurately with fixed sensors. In order to accurately monitor these areas, the method also includes:

[0083] S1204, determine the difficult-to-monitor area with weak fixed sensor signals in the target area and select the drone corresponding to the target cold source area.

[0084] Among them, by regularly detecting the signal strength and data transmission quality of fixed sensors, areas with weak signals or data loss can be identified, and these areas with weak signals can be clearly marked on the map or system to ensure that subsequent drone inspections can cover these areas.

[0085] In addition, according to the geographical characteristics and environmental conditions of the difficult-to-monitor areas, choose the appropriate drone model, consider factors such as the drone's flight time, flight altitude, and load capacity, and equip the drone with various types of sensors, such as cameras (for video and image data), temperature sensors, humidity sensors, gas sensors, etc., to ensure that various types of data can be collected.

[0086] By identifying difficult-to-monitor areas and ensuring that drone inspections can cover areas that fixed sensors cannot effectively monitor, the location and characteristics of difficult-to-monitor areas can be clarified, which helps optimize the inspection routes and frequencies of drones and improve inspection efficiency. At the same time, the flexibility and maneuverability of drones enable them to cover areas that are difficult for fixed sensors to reach, ensuring that there are no blind spots in monitoring.

[0087] S1205, determining a preset path corresponding to the drone based on the difficult-to-monitor area, setting the inspection frequency corresponding to the drone, controlling the drone to navigate along the preset path and obtaining multi-source monitoring data of the drone on the target cold source area.

[0088] Among them, the inspection path of the drone is planned according to the geographical location and characteristics of the difficult-to-monitor area, and the path should cover all difficult-to-monitor areas and avoid obstacles and dangerous areas as much as possible. At the same time, the inspection frequency of the drone is set according to the actual situation and monitoring needs of the cold source area. For example, for high-risk areas, a higher inspection frequency can be set; for low-risk areas, the inspection frequency can be appropriately reduced.

[0089] In addition, before the inspection begins, the drone is started and a preliminary inspection is performed to ensure that the drone and sensors are working properly. Then, the drone is controlled to navigate along the preset path through the ground control station or automatic navigation system. During the navigation process, the status of the drone and data transmission are monitored in real time. During the flight, the drone collects various types of data in real time, including video data, image data, temperature data, humidity data, gas concentration data, etc. The collected data can be transmitted to the central monitoring platform or ground control station in real time through wireless communication technology (such as Wi-Fi, 4G / 5G, etc.).

[0090] S1206, input the multi-source monitoring data into the prediction model, and generate a detailed inspection report based on the prediction results of the prediction model.

[0091] Among them, the multi-source monitoring data collected by drones is pre-processed, including data cleaning, denoising, and standardization, to ensure the quality and consistency of the data. Then the multi-source monitoring data is fused with the data collected by fixed sensors to generate comprehensive monitoring data, which is input into the pre-trained prediction model for analysis and prediction. A detailed inspection report can be generated based on the output results of the prediction model. The report should include inspection time, inspection path, monitoring data, prediction results, potential risks, and recommended measures.

[0092] By executing the above steps from S1204 to S1206, the method can not only cover the area that is difficult to monitor with fixed sensors through drones, but also improve the comprehensiveness and accuracy of monitoring through the collection and fusion of multi-source data. The application of real-time data transmission and prediction models ensures that potential problems can be discovered and handled in a timely manner, and detailed inspection reports are generated to provide scientific decision-making support for managers and ensure the safe operation of cold source areas.

[0093] Based on the key areas mentioned in the above solution, monitor the key areas and perform the following process:

[0094] S1207, determine the key area corresponding to the target cold source area, and install air quality sensors in the key area.

[0095] Among them, by analyzing the geographical and functional layout of the target cold source area, the key areas that need to be monitored are determined. The key areas usually include the surrounding of the equipment, vents, air inlets, etc., because these areas have a greater impact on the operating status and environment of the cold source equipment. And choose the appropriate air quality sensor: According to the monitoring needs, choose the appropriate air quality sensor, which should be able to measure PM2.5 concentration, carbon dioxide concentration and other related parameters, such as temperature, humidity, etc.

[0096] Then install air quality sensors in the determined key areas. It is necessary to ensure that the installation location of the sensors is reasonable and can accurately reflect the air quality conditions in the key areas. In addition, the sensors should be installed in a location that will not be disturbed and is easy to maintain.

[0097] S1208, obtaining air quality data corresponding to the key area.

[0098] Among them, through the installed air quality sensors, air quality data of key areas are collected in real time. These data should include PM2.5 concentration, carbon dioxide concentration and other relevant parameters. The collected air quality data will be recorded in the central database in real time to ensure the integrity and traceability of the data.

[0099] The collected data needs to be preprocessed, including data cleaning, denoising, and standardization, to ensure the quality and consistency of the data. Data analysis tools can be used to perform trend analysis on air quality data to identify data change trends and periodic fluctuations.

[0100] S1209, compare the air quality data with a preset reference value, and if a potential risk is identified, generate corresponding warning data.

[0101] Among them, reference values ​​for air quality can be set in advance based on industry standards, historical data and expert experience. These reference values ​​include normal ranges and warning thresholds for PM2.5 concentration, carbon dioxide concentration, etc., and then the collected air quality data can be compared with the pre-set reference values ​​to determine whether the data exceeds the normal range.

[0102] If the data exceeds the reference value, potential risks can be identified. The identification of potential risks should be based on a comprehensive evaluation of multiple parameters, and the accuracy and reliability of the judgment must be ensured.

[0103] If a potential risk is identified, detailed warning data is generated and sent to relevant personnel through a monitoring platform or mobile application to ensure that the warning information can be delivered in a timely manner; in this embodiment of the application, the warning data should include the following:

[0104] Risk level: Determine the warning level (such as low, medium, high) based on the severity of the risk.

[0105] Risk description: Describe the existing risks in detail, including specific parameter values, change trends, etc.

[0106] Recommended Actions: Provide specific recommended actions, such as increasing ventilation, activating air purification equipment, shutting down certain equipment, etc.

[0107] By executing the above steps from S1207 to S1209, not only can the air quality in key areas within the target cold source area be accurately monitored, but potential risks can also be identified in a timely manner through data comparison and trend analysis, and detailed early warning data can be generated; this can help managers take preventive measures in a timely manner to ensure the normal operation of the cold source equipment and environmental safety, thereby improving the reliability and safety of the system.

[0108] In the data comparison process of the monitoring process, the corresponding monitoring strategies are different in different time and season, so the method also includes:

[0109] S121, retrieve a relationship mapping table between the environment and monitoring strategies corresponding to the target cold source area under different environments.

[0110] Among them, based on historical data and expert experience, a relationship mapping table is established, which records the optimal monitoring strategies corresponding to different environmental conditions (such as different seasons and different climate conditions). The relationship mapping table should include the following: Environmental conditions: different seasons (such as spring, summer, autumn, winter) and different climate conditions (such as high temperature, low temperature, high humidity, low humidity, wind speed, etc.); Monitoring strategy: recommended monitoring frequency, monitoring parameters, sensor type, etc. under each environmental condition. By establishing a relationship mapping table, it is ensured that the optimal monitoring strategy can be selected under different environmental conditions, and the scientificity and rationality of monitoring can be improved.

[0111] S122, obtaining current corresponding environmental data, and determining a corresponding target monitoring strategy based on the environmental data.

[0112] Among them, the current environmental data is collected in real time through environmental sensors installed in the target cold source area, and the collected environmental data is transmitted to the central monitoring platform through wired or wireless communication technology (such as Wi-Fi, 4G / 5G, etc.); the processed environmental data is matched with the relationship mapping table to determine the target monitoring strategy corresponding to the current environmental conditions. For example, if it is currently hot in summer, the matching table may recommend increasing the monitoring frequency, increasing the monitoring parameters of temperature and humidity, etc. By matching the relationship mapping table, it is ensured that the selected monitoring strategy is optimal to avoid insufficient or excessive monitoring due to environmental changes.

[0113] S123, optimizing the current corresponding monitoring strategy based on the target monitoring strategy.

[0114] Among them, by comparing the currently used monitoring strategy with the target monitoring strategy, the advantages and disadvantages of the current monitoring strategy are evaluated. The evaluation content includes monitoring frequency, monitoring parameters, sensor type, etc. According to the evaluation results, a specific optimization plan is formulated. The optimization plan should include the following contents:

[0115] 1. Adjust the current monitoring frequency according to the target monitoring strategy. For example, if the target monitoring strategy recommends increasing the monitoring frequency, the number of monitoring times should be increased accordingly.

[0116] 2. Increase or decrease the current monitoring parameters according to the target monitoring strategy. For example, if the target monitoring strategy recommends adding humidity monitoring, a humidity sensor should be added.

[0117] 3. Replace or supplement the current sensors according to the target monitoring strategy. For example, if the target monitoring strategy recommends adding gas sensors, the corresponding sensors should be added.

[0118] Through the above process, not only can the optimal monitoring strategy be selected according to the current environmental conditions, but also the current monitoring strategy can be optimized to ensure that the operation of the monitoring system is more efficient and accurate.

[0119] Among them, for the multi-type data mentioned above, temperature data is now used as an example, and the method also includes:

[0120] S131, installing an infrared sensor in the target cold source area, collecting temperature distribution data corresponding to the target cold source area in real time, and identifying the corresponding temperature abnormality area based on the temperature distribution data.

[0121] Among them, according to the actual situation of the target cold source area, select a suitable infrared sensor. The infrared sensor should have high resolution, high sensitivity and wide temperature measurement range, and can accurately measure the temperature distribution of the target area; then install the infrared sensor at the key position of the target cold source area, and ensure that the installation position of the sensor is reasonable and can cover important equipment and areas. For example, infrared sensors can be installed on key parts such as equipment surfaces, pipelines, cooling towers, etc.

[0122] The temperature distribution data of the target cold source area is collected in real time through the installed infrared sensor, where the temperature distribution data should include the temperature value of each monitoring point and its spatial distribution. The collected temperature distribution data is then analyzed to identify areas with abnormal temperature. For example, a temperature threshold can be set. When the temperature of an area exceeds the threshold, it is determined to be an abnormal temperature area. In addition, image processing techniques, such as edge detection and area segmentation, can be used to assist in identifying abnormal temperature areas.

[0123] S132, retrieve abnormal temperature data corresponding to the abnormal temperature area, fuse the abnormal temperature data with multiple types of data, and generate corresponding comprehensive monitoring results.

[0124] Among them, abnormal temperature data of the temperature abnormal area is extracted from the temperature distribution data, including the temperature value, location, timestamp and other information of the abnormal area, and then multiple types of data collected by other sensors in the same time period are retrieved, such as video data, image data, and environmental parameter data (temperature, humidity, pressure, etc.).

[0125] By fusing abnormal temperature data with other types of data, data fusion algorithms (such as Kalman filtering, particle filtering, deep learning, etc.) can be used to comprehensively process multi-source data to generate comprehensive monitoring results. Comprehensive monitoring results can be generated based on the fused data. The comprehensive monitoring results should include detailed information on the abnormal temperature area, changing trends of other related parameters, etc.

[0126] S133, based on the comprehensive monitoring results, the operating status of the cold source equipment in the target cold source area is evaluated. If there is an abnormality in the cold source equipment, a corresponding emergency notification is generated and sent to the relevant responsible persons.

[0127] Based on the comprehensive monitoring results, the operating status of the cold source equipment is evaluated, including whether there are problems such as overheating and poor cooling. The operating status of the equipment can be automatically determined by setting thresholds and rules. For example, if the temperature in a certain area is continuously higher than the normal range, it may indicate that the equipment has an overheating problem; if the temperature of the cooling system is lower than the normal range, it may indicate poor cooling.

[0128] If the assessment results show that there is an abnormality in the cooling source equipment, an emergency notification is generated. The emergency notification should include the following: abnormality type, clearly indicating the type of abnormality, such as overheating, poor cooling, etc.; abnormal location, detailing the specific location where the abnormality occurred; abnormal time, recording the time when the abnormality occurred; recommended measures, providing specific recommended measures, such as shutting down specific equipment, starting the cooling system, increasing the inspection frequency, etc.

[0129] Emergency notifications are sent to relevant responsible persons through monitoring platforms or mobile applications to ensure that notifications can be delivered in a timely manner. Multiple delivery channels can be used, such as SMS, email, APP push, etc., to ensure the timeliness and reliability of notifications. In addition, the system feedback mechanism can be used to confirm whether the relevant responsible person has received the emergency notification. If no confirmation reply is received, the backup channel should be used to send it again to ensure that the information is delivered in place.

[0130] Through the above process, the temperature distribution of the target cold source area can be monitored in real time through infrared sensors, and the temperature abnormality area can be identified. The comprehensive monitoring results can be generated through multi-source data fusion to scientifically evaluate the operating status of the cold source equipment. Once the equipment abnormality is found, an emergency notification can be generated and sent in time to ensure that the relevant responsible persons can take prompt action to avoid greater losses caused by equipment failure.

[0131] Finally, it can also be judged by water flow, so the method also includes:

[0132] S141, obtaining historical water flow data corresponding to the target cold source area, and obtaining water flow law data corresponding to the target cold source area.

[0133] Among them, the historical water flow data of the target cold source area is collected through historical records, databases or third-party data sources. The historical water flow data should include information such as water flow speed, direction, flow rate, etc. in different time periods; then the collected historical water flow data is analyzed to identify the regular characteristics of the water flow. For example, the changing patterns of water flow in different seasons and under different weather conditions, as well as the periodic changes of water flow in a specific time period can be analyzed. Specifically, the analysis results can be organized into water flow regularity data, including the speed range, direction change, flow rate change, etc. of the water flow. These regularity data can be used for subsequent comparison of actual water flow data.

[0134] S142, using a flow meter to obtain actual water flow data corresponding to the target cold source area, comparing the actual water flow data with the water flow law data, and determining whether there is a water flow change.

[0135] Among them, the flow meter is installed at the key position of the target cold source area to ensure that the flow meter can accurately measure the speed and direction of the water flow. The flow meter should be installed in the area where the water flow is stable to avoid external interference; the actual water flow data of the target cold source area can be collected in real time through the flow meter, including the water flow speed and direction. The data should be transmitted to the central monitoring platform in real time. And the actual water flow data collected needs to be preprocessed, including data cleaning, denoising, standardization, etc., to ensure the quality and consistency of the data.

[0136] The actual water flow data is compared with the water flow pattern data to determine whether there is a change in water flow. A threshold can be set, and when the actual water flow data exceeds the threshold range, it is determined to be a water flow change. For example, if the actual water flow speed is significantly higher or lower than the historical average, or the water flow direction changes significantly, it can be considered that there is a water flow change.

[0137] S143, if yes, obtain the actual water flow change corresponding to the target cold source area, input the actual water flow change into the prediction and recognition model, obtain the corresponding recognition result, and determine whether there are disaster-causing organisms in the target cold source water area based on the recognition result.

[0138] The data of water flow changes are extracted from the actual water flow data, including information such as the speed, direction, time and location of the changes. The extraction methods include: time series analysis, analyzing the change trend of water flow data over time; spatial analysis, analyzing the changes of water flow at different locations.

[0139] The extracted actual water flow change data is input into the pre-trained prediction and recognition model. The prediction and recognition model should be able to predict whether there are disaster-causing organisms based on the water flow change data. The model training process includes: collecting a large amount of historical water flow data and disaster-causing organism data, annotating and preprocessing them; selecting appropriate machine learning or deep learning models, such as support vector machines (SVMs), random forests, neural networks, etc.; using annotated data to train the model and optimizing model parameters through cross-validation; using an independent test set to verify the accuracy and generalization ability of the model.

[0140] The predictive recognition model generates recognition results based on the input actual water flow change data. The recognition results should include information such as whether there are disaster-causing organisms, their types, quantity, and location. Based on the recognition results of the predictive recognition model, it is determined whether there are disaster-causing organisms located in the target cold source waters. If the recognition results show that there are disaster-causing organisms, their specific location and quantity are further analyzed.

[0141] If it is determined that there are disaster-causing organisms, detailed early warning data will be generated. The early warning data should include the following: information on disaster-causing organisms, such as the type, quantity, and location of the disaster-causing organisms; risk level, which is determined based on the type and quantity of the disaster-causing organisms (such as low, medium, and high); recommended measures, which provide specific recommended measures, such as starting a cleaning procedure, increasing the frequency of inspections, and notifying professional personnel to come to the site for treatment.

[0142] Finally, the generated warning data is sent to the relevant responsible persons through the monitoring platform or mobile application. Through the above process, the actual water flow data in the target cold source area can be monitored in real time through the flow meter, the water flow changes can be identified, and the prediction recognition model can be used to determine whether the water flow changes bring the risk of disaster-causing organisms. Once a disaster-causing organism is found, warning data can be generated and sent in a timely manner to ensure that the relevant responsible persons can take prompt action to avoid equipment failures and safety hazards caused by disaster-causing organisms.

[0143] The present application embodiment discloses an intelligent cold source disaster-causing object monitoring system based on multi-sensor fusion, referring to Figure 2 , the system includes but is not limited to:

[0144] The target cold source area determination module 200 is used to determine the corresponding target cold source area, obtain multi-type data corresponding to the target cold source area, input the multi-type data into a pre-built multi-source heterogeneous data fusion platform for fusion, and obtain the corresponding cold source monitoring data, wherein the multi-type data includes video data, image data, and environmental parameter data for the target cold source area;

[0145] The prediction result acquisition module 210 retrieves the prediction and recognition model pre-trained for the disaster-causing organisms, inputs the cold source monitoring data into the prediction and recognition model, and is used to obtain the prediction results corresponding to the disaster-causing organisms on a regular basis;

[0146] The judgment module 220 is used to judge whether there will be disaster-causing organisms entering the target cold source area based on the prediction results. If so, warning data is issued based on the monitoring platform, wherein the warning data includes target organisms, target time period and corresponding target area;

[0147] A memory, used for storing a program of an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion;

[0148] The program in the processor memory can be loaded and executed by the processor to realize an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion.

[0149] The various processes and processing described above, such as a method for monitoring a cold source disaster-causing object based on multi-sensor fusion, can be executed by a CPU. For example, in some embodiments, a method for monitoring a cold source disaster-causing object based on multi-sensor fusion can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a memory. In some embodiments, part or all of the computer program can be loaded and / or installed on a computing device via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by the CPU, a method for monitoring a cold source disaster-causing object based on multi-sensor fusion or multiple actions described above can be executed.

[0150] The present disclosure relates to methods, computing devices, computer-readable storage media, and / or computer program products. The computer program product may include computer-readable program instructions for executing various aspects of the present disclosure.

[0151] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0152] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge computing devices. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0153] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0154] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions enable the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of a method for monitoring intelligent cold source disaster-causing objects based on multi-sensor fusion or multiple actions.

[0155] Computer-readable program instructions can also be loaded onto a computer, other programmable data processing device, or other equipment, so that a series of operating steps are executed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing device, or other equipment implement an intelligent cold source disaster-causing object monitoring method or multiple actions based on multi-sensor fusion.

[0156] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

[0157] Based on the same inventive concept, an embodiment of the present invention provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion.

Claims

1. An intelligent cold source disaster monitoring method based on multi-sensor fusion, characterized in that: include: Determine the corresponding target cold source area, obtain multi-type data corresponding to the target cold source area, input the multi-type data into a pre-built multi-source heterogeneous data fusion platform for fusion, and obtain the corresponding cold source monitoring data, wherein the multi-type data includes video data, image data, and environmental parameter data for the target cold source area; Retrieving a prediction and recognition model pre-trained for disaster-causing organisms, inputting the cold source monitoring data into the prediction and recognition model, and obtaining prediction results corresponding to disaster-causing organisms on a regular basis; Based on the prediction results, it is determined whether disaster-causing organisms will enter the target cold source area. If so, early warning data is issued based on the monitoring platform, where the early warning data includes target organisms, target time period and corresponding target area.

2. The intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion according to claim 1 is characterized in that: The method also includes: Obtain historical water flow data corresponding to the target cold source area, and obtain water flow law data corresponding to the target cold source area; Using a flow meter to obtain actual water flow data corresponding to the target cold source area, and comparing the actual water flow data with the water flow law data to determine whether there is a water flow change, wherein the actual water flow data includes water flow speed and direction; If so, obtain the actual water flow changes corresponding to the target cold source area, input the actual water flow changes into the prediction and recognition model, obtain the corresponding recognition results, and determine whether there are disaster-causing organisms located in the target cold source waters based on the recognition results.

3. The intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion according to claim 1 is characterized in that: The method also includes: Retrieve the relationship mapping table between the environment and monitoring strategies corresponding to the target cold source area under different environments, where the different conditions include different seasons and different climate conditions; Obtain current corresponding environmental data, and determine a corresponding target monitoring strategy based on the environment; The current corresponding monitoring strategy is optimized based on the target monitoring strategy.

4. The intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion according to claim 1 is characterized in that: In the process of judging whether disaster-causing organisms will enter the target cold source area based on the prediction results, and if so, issuing early warning data based on the monitoring platform, the method further includes: If there are disaster-causing organisms, the pre-set warning level will be called up, among which the warning level is divided into three levels: low, medium and high; Determining a target warning level corresponding to the prediction result based on the prediction result and the warning level; generating corresponding warning data based on the target warning level, the warning data also including recommended preventive measures; The warning data is sent to relevant personnel via a monitoring platform or a mobile application.

5. The intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion according to claim 4 is characterized in that: The method also includes: Install an infrared sensor in the target cold source area to collect temperature distribution data corresponding to the target cold source area in real time, and identify the corresponding temperature abnormal area based on the temperature distribution data; Retrieving abnormal temperature data corresponding to the abnormal temperature area, fusing the abnormal temperature data with the multi-type data, and generating corresponding comprehensive monitoring results; Based on the comprehensive monitoring results, the operating status of the cold source equipment in the target cold source area is evaluated. If there is an abnormality in the cold source equipment, a corresponding emergency notification is generated and sent to the relevant responsible persons, wherein the operating status includes judging whether there is overheating or poor cooling.

6. The intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion according to claim 1 is characterized in that: The method also includes: Determine the difficult-to-monitor area with weak fixed sensor signals in the target area and select the drone corresponding to the target cold source area. The drone is equipped with multiple types of sensors to ensure that the corresponding difficult-to-monitor area can be covered; Determine a preset path corresponding to the drone based on the difficult-to-monitor area, set the inspection frequency corresponding to the drone, control the drone to navigate along the preset path and obtain multi-source monitoring data of the drone on the target cold source area; The multi-source monitoring data is input into a prediction model, and a detailed inspection report is generated based on the prediction results of the prediction model.

7. The intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion according to claim 1 is characterized in that: The method also includes: Determine the key areas corresponding to the target cold source area, and install air quality sensors in the key areas, wherein the key areas include the surroundings of the equipment, vents, and air inlets; Acquire air quality data corresponding to the key area, wherein the air quality data includes PM2.5 concentration, carbon dioxide concentration and corresponding change trends; The air quality data is compared with a preset reference value, and if a potential risk is identified, corresponding warning data is generated.

8. An intelligent cold source disaster monitoring system based on multi-sensor fusion, characterized in that: include: The target cold source area determination module is used to determine the corresponding target cold source area, obtain multi-type data corresponding to the target cold source area, input the multi-type data into a pre-built multi-source heterogeneous data fusion platform for fusion, and obtain the corresponding cold source monitoring data, wherein the multi-type data includes video data, image data, and environmental parameter data for the target cold source area; A prediction result acquisition module is used to retrieve a prediction and recognition model pre-trained for disaster-causing organisms, and input the cold source monitoring data into the prediction and recognition model to obtain prediction results corresponding to disaster-causing organisms on a regular basis; The judgment module is used to judge whether disaster-causing organisms will enter the target cold source area based on the prediction results. If so, early warning data is issued based on the monitoring platform, where the early warning data includes target organisms, target time period and corresponding target area; A memory, used to store a program of an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion according to any one of claims 1 to 7; The program in the processor memory can be loaded and executed by the processor to implement an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion as described in any one of claims 1 to 7.

10. An intelligent terminal, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes an intelligent cold source disaster-causing object monitoring method based on multi-sensor fusion as described in any one of claims 1 to 7.

Images