Self-adaptive security remote driving control method and system

Abstract

The invention discloses a self-adaptive security remote drive control method and system. The method comprises the following steps: acquiring field temperature data and image data; performing partition storage according to the area where the acquisition points are located, wherein the area is provided with a time index table, a space index table and an equipment index table; the collected temperature data are preprocessed, and whether abnormal data exist or not is judged; when abnormal data occurs, judging that the abnormal data is single-point abnormal data, multi-point abnormal data or multi-region abnormal data; matching a corresponding strategy according to the abnormal data type to analyze and confirm an abnormal condition; matching a corresponding execution strategy according to the generated abnormal condition type; monitoring the abnormal condition area in real time according to a fourth strategy, and ending the corresponding execution strategy after judging that the abnormal condition disappears; by adopting temperature and time axis matching, temperature data conditions in different environments can be reflected more accurately, so that judgment of abnormal data is more accurate, the influence of abnormity on a security and protection system is reduced, and safe and stable operation of an energy storage power station is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage power station security, and particularly relates to an adaptive security remote drive control method and system. Background Art

[0002] With the rapid development of energy storage technology, energy storage power stations are playing an increasingly important role in energy storage and management. It can not only effectively regulate energy supply and demand, improve energy utilization efficiency, but also enhance the stability and reliability of the power system, and plays an indispensable role in the large-scale access of renewable energy and the efficient utilization of distributed energy. However, the safety of energy storage power stations is a necessary factor for their stable operation and is of crucial importance. Energy storage power stations usually contain a large number of energy storage batteries, power conversion equipment, and complex electrical systems. These devices generate heat during operation. If the temperature cannot be effectively monitored and managed, it is extremely easy to trigger serious safety accidents such as thermal runaway and fires, causing huge economic losses and even casualties.

[0003] The existing method is to detect the temperature through simple sensors and give an alarm when the temperature is high. However, due to the unreasonable layout of the existing sensors, some key areas (such as the central part of the battery module, key nodes of the heat dissipation channel, etc.) cannot be effectively monitored, making it difficult to detect in a timely manner once the temperature in these areas abnormally rises. At the same time, the simple sensor detection method lacks comprehensive consideration of environmental factors. The environment inside the energy storage power station is complex and changeable, and various factors may affect the measurement results of the temperature sensor. However, the existing detection methods usually do not effectively identify environmental interference factors or other interference factors, resulting in large errors in the measured temperature data and unable to truly reflect the actual temperature of the energy storage equipment. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide an adaptive security remote drive control method and system.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] An adaptive security remote drive control method includes acquiring on-site temperature data and image data;

[0007] Partition storage is performed according to the regions where the acquisition points corresponding to the temperature data and image data are located, and each region is provided with a time index table, a space index table, and a device index table;

[0008] Preprocess the acquired temperature data to determine whether there is abnormal data;

[0009] When abnormal data appears, determine whether it is single-point abnormal data, multi-point abnormal data, or multi-region abnormal data;

[0010] When it is single-point abnormal data, further analyze the abnormal data according to the first strategy to confirm the abnormal situation;

[0011] When it is multi-point abnormal data, further analyze the abnormal data according to the second strategy to confirm the abnormal situation;

[0012] When it is multi-region abnormal data, further analyze the abnormal data according to the third strategy to confirm the abnormal situation;

[0013] Match the corresponding execution strategy according to the generated type of abnormal situation;

[0014] After sending the execution strategy to the corresponding execution unit, perform real-time monitoring on the abnormal situation area according to the fourth strategy. When it is judged that the abnormal situation has disappeared, end the corresponding execution strategy.

[0015] In the present invention, preferably, the preprocessing specifically includes: each acquisition point corresponds to an independent temperature time axis. Determine the comparison interval on the temperature time axis according to the time when the temperature data is obtained, and judge whether the temperature data is within the comparison interval. When it is within the range, it is marked as normal data. When it exceeds the range interval, the temperature data is marked as abnormal data.

[0016] In the present invention, preferably, the temperature time axis is a set of historical temperature data with a unit of year in length. Each acquisition point corresponds to a separate temperature time axis, which is arranged in sequence at intervals of days or hours, corresponding to the historical normal temperature data at each time.

[0017] In the present invention, preferably, the specific steps for determining whether it is single-point abnormal data, multi-point abnormal data or multi-region abnormal data include:

[0018] When abnormal data appears, count the number of acquisition points where the abnormal data appears and the regions where the acquisition points are located.

[0019] When there is a single acquisition point with abnormal data in the same region, it is determined as single-point abnormal data;

[0020] When there are more than 2 acquisition points with abnormal data in a single region, it is determined as multi-point abnormal data;

[0021] When there are multiple acquisition points with abnormal data in different regions at the same time, it is determined as multi-region abnormal data.

[0022] In the present invention, preferably, the first strategy is for single-point abnormal data. When single-point abnormal data appears, extract the temperature data of the past 1 hour corresponding to the acquisition point according to the time index table, calculate the temperature change rate. When the temperature change rate exceeds the preset threshold, it is determined that there is a potential risk and it is marked as a single-point abnormal situation.

[0023] In the present invention, preferably, the second strategy is directed to multi-point abnormal data in a single area. When multi-point abnormal data appears, the devices corresponding to the acquisition point positions are extracted according to the device index table, the operating status data of the corresponding devices are obtained, and the operating status data are input into the simulation model to determine whether there is a device failure and the type of the failure. When there is a failure, it is marked as a single-area device failure; when there is no device failure, an abnormal prompt message is generated.

[0024] In the present invention, preferably, the third strategy is directed to multi-area abnormal conditions. When multi-area abnormal conditions appear, other several temperature data of acquisition points at the same moment are extracted according to the time index table, and the number of acquisition points whose temperature data exceed the median value of the comparison interval is counted. When more than half of the acquisition points are higher than the median value, the current indoor temperature and outdoor temperature are synchronously obtained, and the indoor and outdoor temperature data in the same period on the historical time axis are extracted from the historical database. If the current temperature data is also higher than the historical same-period temperature and the difference exceeds a certain range, it is determined that the overheat is caused by environmental factors and is marked as an environmental abnormal condition;

[0025] If other several temperature data of acquisition points at the same moment are extracted according to the time index table and less than half of the acquisition points are higher than the median value, the corresponding devices are further determined according to the device index table, and it is judged whether the devices are in the same task list. If they are in one list, it is marked as a device abnormal condition; when they are not in the same list, the operating status data of the corresponding devices are obtained again, and the operating status data are input into the simulation model to determine whether there is a device failure and the type of the failure. When the failure and the type of the failure are output, it is determined that it is a device abnormal condition; otherwise, the corresponding acquisition points are summarized to generate an abnormal prompt message.

[0026] In the present invention, preferably, different execution strategies are matched according to the generated different abnormal condition types. When it is a single-point abnormal condition, the execution strategy is to retrieve the image data of the corresponding acquisition point for gas-liquid effluent image recognition, and at the same time, the specific position is determined according to the space index table, and a first-level maintenance instruction is generated and sent to the maintenance personnel for fixed-point maintenance to confirm local device or sensor problems; when it is a single-area device failure or a device abnormal condition, a maintenance instruction is generated according to the given specific device failure type, and at the same time, the current maintenance personnel are matched, and the maintenance instruction is sent to the maintenance personnel; when it is an environmental abnormal condition, the air-conditioning system in the corresponding area is started or the ventilation is adjusted, or the refrigeration power and ventilation volume are dynamically adjusted.

[0027] In the present invention, preferably, when generating the maintenance instruction, the current maintenance personnel are matched, the maintenance instruction is sent to the maintenance personnel, and the permissions of the corresponding area of the maintenance personnel are synchronously enabled to follow up the subsequent maintenance situation.

[0028] An adaptive security remote drive control system includes a master control platform, a collection unit, and an execution unit. The collection unit includes a temperature and humidity sensor and a video collector. The execution unit includes an air-cooling system. The execution unit is also connected to a personnel management system. The master control platform is provided with a data storage unit, a real-time data matching unit, a data processing unit, an execution strategy generation unit, and a feedback unit. The data storage unit includes a collection data storage group corresponding to each area, and each storage group is correspondingly provided with a time index table, a space index table, and a device index table. The real-time data matching unit includes several temperature time axes, and each temperature time axis corresponds to a collection point. The collected temperature data is compared with the data on the temperature time axis to determine whether there is abnormal data. When there is abnormal data, the data processing unit processes it to determine the abnormal situation. The execution strategy generation unit generates an execution strategy based on the abnormal situation and transmits it to the execution unit for execution. While executing the execution strategy, the feedback unit obtains the real-time data of the corresponding collection point and feeds it back at a high frequency, and adaptively adjusts the execution strategy or stops executing the strategy based on the feedback.

[0029] Compared with the prior art, the beneficial effects of the present invention are:

[0030] The method of the present invention can comprehensively and accurately obtain on-site data, improve the monitoring accuracy and timeliness of abnormal data by adopting precise multi-source data and optimizing the data storage indexing method; by adopting temperature time axis matching, it can more accurately reflect the temperature data situation in different environments, so as to make the determination of abnormal data more accurate and provide a reliable basis for subsequent processing; match different execution strategies according to different abnormal situations, and combine the feedback mechanism to monitor the execution situation, adaptively adjust the execution strategy based on the feedback, reduce the impact of abnormalities on the security system, and ensure the safe and stable operation of the energy storage power station. Description of the Drawings

[0031] Figure 1 It is a schematic flow chart of an adaptive security remote drive control method described in the present invention. Detailed Embodiments

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the specification of this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0034] Please refer to Figure 1 , a preferred embodiment of the present invention provides an adaptive security remote drive control method, which is mainly used for energy storage power stations to conduct daily inspections and maintenance on the equipment of energy storage power stations. By adopting accurate multi-source data and optimizing the data storage indexing method, it can comprehensively and accurately obtain on-site data, improve the monitoring accuracy and timeliness of abnormal data; by adopting temperature time-axis matching, it can more accurately reflect the temperature data situation in different environments, thereby making the determination of abnormal data more accurate and providing a reliable basis for subsequent processing; according to different abnormal situations, different execution strategies are matched, and combined with a feedback mechanism, the execution situation is monitored, and the execution strategy is adaptively adjusted based on the feedback to reduce the impact of abnormalities on the security system and ensure the safe and stable operation of the energy storage power station.

[0035] The specific steps include:

[0036] S1. Obtain on-site temperature data and image data:

[0037] Temperature and humidity sensors, camera collectors, gas sensors, sound sensors and other various sensors are installed at multiple collection points in the energy storage power station to achieve comprehensive monitoring of the equipment of the energy storage power station. Among them, there are many cases of false alarms or misreports of data anomalies caused by temperature. Therefore, only the temperature data collected by the temperature sensors is improved in combination with the image data processing method.

[0038] S2. Store the data in partitions according to the regions where the collection points corresponding to the temperature data and image data are located. Each region is provided with a time index table, a space index table and a device index table.

[0039] Specifically, due to the large overall scale of the energy storage power station, it is managed in partitions. The collected temperature data and image data are stored in partitions. While storing the data, a time index table is established. In the time index table, the temperature data collected by each collection point corresponds to the time point. At the same time, a space index table is also set. In the space index table, each collection point is associated with its specific location, and the specific location is represented by a corresponding code; a device index table is also set. In the device index table, each collection point is associated with the corresponding device it collects, and the specific device is also represented by a corresponding device code. By establishing the index table, it is convenient to extract and analyze the collected data later and improve the data processing efficiency.

[0040] S3. Preprocess the collected temperature data and determine whether there is abnormal data.

[0041] Specifically, the preprocessing specifically includes: Each collection point corresponds to an independent temperature time axis. Determine the comparison interval on the temperature time axis according to the time when the temperature data is obtained. Judge whether the temperature data is within the comparison interval. When it is within the range, it is marked as normal data. When it exceeds the range interval, the temperature data is marked as abnormal data.

[0042] The temperature time axis is a set of historical temperature data with a length of 1 unit year. Each collection point corresponds to a separate temperature time axis. Each time point within the temperature time axis is arranged sequentially at intervals of days or hours. Each time point corresponds to a set of historical temperature data. The set of historical temperature data includes the temperature values collected at the same collection point in previous years. The historical temperature interval is formed based on the maximum and minimum values of the historical temperature values. That is, each time point on the temperature time axis corresponds to a historical temperature interval, where the historical temperature values do not include abnormal data. Match the time of the collected data to the same or the closest time point on the temperature time axis, and obtain the corresponding historical temperature interval at this time point. This historical temperature interval is the comparison interval. Judge whether the temperature data is within this comparison interval. When it is within the interval, it is normal data. When it exceeds the range, it is marked as abnormal data. By adopting the temperature time axis comparison method, it can better adapt to environmental changes. At the same time, the latest normal data is incorporated into the corresponding set of historical temperature data every week or month.

[0043] S4. When abnormal data appears, determine whether it is single-point abnormal data, multi-point abnormal data, or multi-region abnormal data;

[0044] When it is single-point abnormal data, further analyze and confirm the abnormal situation according to the first strategy;

[0045] When it is multi-point abnormal data, further analyze and confirm the abnormal situation according to the second strategy;

[0046] When it is multi-region abnormal data, further analyze and confirm the abnormal situation according to the third strategy;

[0047] Match the corresponding execution strategy according to the generated type of abnormal situation;

[0048] After sending the execution strategy to the corresponding execution unit, perform real-time monitoring on the abnormal situation area according to the fourth strategy. When it is judged that the abnormal situation has disappeared, end the corresponding execution strategy.

[0049] Specifically, the specific steps for determining whether it is single-point abnormal data, multi-point abnormal data, or multi-region abnormal data include:

[0050] When abnormal data appears, count the number of collection points where the abnormal data appears and the areas where the collection points are located.

[0051] When a single abnormal data collection point appears in the same area, it is judged as single-point abnormal data; if the collection point has frequent abnormalities in the past period of time (such as more than 3 times in a week), the attention level of its abnormal situation is increased, marked as "high-frequency single-point abnormality", and given priority for analysis.

[0052] When there are more than two abnormal data collection points in a single area, it is judged as multi-point abnormal data;

[0053] When multiple abnormal data collection points appear in different areas at the same time, it is determined to be multi-area abnormal data.

[0054] In this embodiment, the first strategy targets single-point abnormal data. When single-point abnormal data occurs, the temperature data of the past hour corresponding to the collection point is extracted according to the time index table, and the temperature change rate is calculated using methods such as linear regression. When the temperature change rate exceeds a preset threshold (such as a rise of 5°C per minute), it is determined that there is a potential risk and is marked as a single-point abnormal situation. The single-point abnormal situation may be a sensor problem or a problem in a part of the corresponding location equipment area.

[0055] In this embodiment, the second strategy targets multi-point abnormal data in a single area. When multi-point abnormal data occurs, the corresponding equipment of the collection point location is extracted according to the equipment index table, and the operating status data of the corresponding equipment is obtained. The operating status data is input into the simulation model to model the multi-parameter data of the equipment, and it is determined whether the equipment has a fault and the type of fault). When a fault exists, it is marked as a single-area equipment fault; when there is no equipment fault, an abnormal prompt message is generated. The simulation model uses a machine learning algorithm, which is obtained through preliminary training and can quickly determine whether the equipment has a fault and the type of fault.

[0056] In this embodiment, the third strategy is for multi-region abnormal situations. When multi-region abnormal situations occur, the temperature data of several other collection points at the same time are extracted according to the time index table, and the number of collection points whose temperature data exceeds the middle value of the comparison interval is counted. When more than half of the collection points are higher than the middle value, the current indoor temperature and outdoor temperature are synchronously obtained, and the indoor and outdoor temperature data of the same period on the historical time axis are extracted from the historical database. If the current temperature data is also higher than the historical temperature of the same period, and the difference exceeds a certain range (such as 5°C), it is determined to be overheating caused by environmental factors and marked as an environmental abnormal situation;

[0057] Extract the temperature data of several other collection points at the same moment according to the time index table. If less than half of the collection points are higher than the median value, further determine the corresponding device according to the device index table, and judge whether the devices are in the same task list. If they are in the same list, mark it as an abnormal device situation; when they are not in the same list, obtain the operation status data of the corresponding device, and input the operation status data into the simulation model (using machine learning algorithms (such as decision trees, support vector machines, etc.) to model the multi-parameter data of the device to judge whether there is a fault in the device and the type of the fault), judge whether there is a fault in the device and the type of the fault. When the fault and the type of the fault are output, it is determined as an abnormal device situation. Otherwise, summarize the corresponding collection points to generate an abnormal prompt message.

[0058] In this embodiment, the second strategy and the third strategy also extract the temperature data of the corresponding past 1 hour of each collection point according to the time index table, calculate the temperature change rate by using methods such as linear regression, and judge whether the change rates are similar. When the change rates are the same, it can be determined that the abnormal situation is caused by the same factor. Then, obtain the operation status data of some corresponding devices to determine the specific device fault and the type of the fault; when the change rates are different or partially the same, use the original strategy for analysis and judgment.

[0059] S5. In this embodiment, different execution strategies are matched according to the generated different types of abnormal situations. When it is a single-point abnormal situation, the execution strategy is to retrieve the image data of the corresponding collection point for gas-liquid effluent image recognition, and at the same time determine the specific location according to the space index table, generate a first-level maintenance instruction and send it to the maintenance personnel for fixed-point maintenance to confirm local equipment or sensor problems. When it is a single-region device fault or device abnormal situation, generate a maintenance instruction according to the given specific device fault type. The maintenance instruction includes the specific device number and the type of the fault. When generating the maintenance instruction, match the current maintenance personnel. The current maintenance personnel are based on the current maintenance personnel list provided by the personnel management system and the maintenance area corresponding to the personnel. According to the device number of the maintenance instruction, it corresponds to the maintenance area, so as to match the current maintenance personnel in this area, send the maintenance instruction to the maintenance personnel, and simultaneously open the permissions of the area corresponding to the maintenance personnel to follow up the subsequent maintenance situation.

[0060] In the event of environmental anomalies, activate the air conditioning system in the corresponding area, adjust ventilation, or dynamically adjust the cooling power and ventilation volume. When an abnormal prompt message appears, a warning message needs to be generated in a timely manner and sent to all maintenance personnel for manual inspection and troubleshooting in a timely manner. At the same time, activate the image data in the corresponding area and give priority to sending it to the visualization unit for display. The visualization display unit processes the image data in the corresponding area to determine whether there is personnel movement. When it is determined that there is no personnel movement within the set time, that is, no personnel arrive at the area for maintenance, a warning message is generated for this area again; when it is determined that there is personnel movement, the warning message in the corresponding area is suspended and waiting for the personnel to feedback maintenance information.

[0061] For equipment failure anomalies, in addition to notifying the maintenance personnel, the equipment can also be remotely controlled to enter the safe mode, or the equipment operating power can be reduced, the operation can be suspended, etc. to prevent the failure from expanding further.

[0062] In this embodiment, the fourth strategy is to establish a real-time feedback mechanism. The execution unit feeds back the execution status of the execution strategy, such as whether the air conditioner is started normally, whether the equipment enters the safe mode, etc., and the on-site real-time data to the master control platform at a high frequency (such as once per second). The master control platform dynamically adjusts the current execution strategy according to the feedback information, and uses the RBF-VSG adaptive control algorithm to optimize the operation status of the energy storage system; when it is found that the temperature drops slowly after starting the air conditioner, the master control platform automatically increases the cooling power of the air conditioner. When the fourth strategy determines that the abnormal situation has disappeared, in addition to ending the corresponding execution strategy, a detailed record and analysis of this abnormal situation are also carried out, and the abnormal situation knowledge base is updated to provide a reference for subsequent abnormal handling.

[0063] Another preferred embodiment of the present invention provides an adaptive security remote drive control system, including a master control platform, a collection unit, and an execution unit. The collection unit includes a temperature and humidity sensor and a video collector. The execution unit includes an air-cooled system. The execution unit is also connected to a personnel management system. The master control platform is provided with a data storage unit, a real-time data matching unit, a data processing unit, an execution strategy generation unit, and a feedback unit. The data storage unit includes a collection data storage group corresponding to each area, and each storage group is correspondingly provided with a time index table, a space index table, and an equipment index table. The real-time data matching unit includes a number of temperature time axes, each temperature time axis corresponding to a collection point. The collected temperature data is compared with the data on the temperature time axis to determine whether there is abnormal data. When there is abnormal data, the data processing unit processes it to determine the abnormal situation. The execution strategy generation unit generates an execution strategy based on the abnormal situation and transmits it to the execution unit for execution. The feedback unit, while executing the execution strategy, obtains the real-time data of the corresponding collection point and feeds it back at a high frequency, and dynamically adjusts the execution strategy or stops executing the strategy according to the feedback.

[0064] In some other preferred embodiments of the present invention, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, causes the processor to execute the steps of the method as described in the above embodiments.

[0065] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0066] The above description is a detailed description of the preferred and feasible embodiments of the present invention, but the embodiments are not intended to limit the scope of the patent application of the present invention. All equivalent changes or modifications made under the technical spirit disclosed by the present invention shall fall within the scope of the patent covered by the present invention.

Claims

1. An adaptive security remote drive control method, characterized in that: Obtain on-site temperature data and image data; The temperature data and image data are stored in partitions according to the areas where the acquisition points corresponding to the temperature data and image data are located. Each area is provided with a time index table, a space index table and a device index table. Pre-process the collected temperature data to determine whether there is abnormal data; When abnormal data appears, it is determined whether it is single-point abnormal data, multi-point abnormal data or multi-region abnormal data; When it is single-point abnormal data, analyze the abnormal data according to the first strategy to confirm the abnormal situation; When there are multiple points of abnormal data, the abnormal data is analyzed and confirmed according to the second strategy; When there are abnormal data in multiple regions, the abnormal data is analyzed and confirmed according to the third strategy; Match the corresponding execution strategy according to the generated exception type; After the execution strategy is sent to the corresponding execution unit, the abnormal situation area is monitored in real time according to the fourth strategy, and when it is determined that the abnormal situation disappears, the corresponding execution strategy is terminated.

2. The adaptive security remote drive control method according to claim 1, characterized in that: The preprocessing specifically includes: each collection point corresponds to an independent temperature-time axis, the comparison interval on the temperature-time axis is determined according to the time when the temperature data is acquired, and it is judged whether the temperature data is within the comparison interval. When it is within the range, it is marked as normal data, and when it exceeds the range, the temperature data is marked as abnormal data.

3. The adaptive security remote drive control method according to claim 2, characterized in that: The temperature time axis is a historical temperature data set with a length of unit year. Each collection point is matched with a separate temperature time axis, which is arranged in sequence at intervals of days or hours, corresponding to the historical conventional temperature data at each time.

4. The adaptive security remote drive control method according to claim 1, characterized in that: The specific steps for determining whether it is single-point abnormal data, multi-point abnormal data or multi-region abnormal data include: When abnormal data appears, count the number of collection points where the abnormal data appears and the areas where the collection points are located. When a single abnormal data collection point appears in the same area, it is determined as single-point abnormal data; When there are more than two abnormal data collection points in a single area, it is judged as multi-point abnormal data; When multiple abnormal data collection points appear in different areas at the same time, it is determined to be multi-area abnormal data.

5. The adaptive security remote drive control method according to claim 1, characterized in that: The first strategy targets single-point abnormal data. When single-point abnormal data occurs, the temperature data of the past hour corresponding to the collection point is extracted according to the time index table, and the temperature change rate is calculated. When the temperature change rate exceeds the preset threshold, it is determined that there is a potential risk and marked as a single-point abnormal situation.

6. The adaptive security remote drive control method according to claim 1, characterized in that: The second strategy targets multi-point abnormal data in a single area. When multi-point abnormal data occurs, the device corresponding to the collection point location is extracted according to the device index table, and the operating status data of the corresponding device is obtained. The operating status data is input into the simulation model to determine whether the equipment has a fault and the type of fault. When a fault exists, it is marked as a single-area equipment fault; when there is no equipment fault, an abnormal prompt message is generated.

7. The adaptive security remote drive control method according to claim 1, characterized in that: The third strategy is aimed at multi-region abnormal situations. When multi-region abnormal situations occur, the temperature data of several other collection points at the same time are extracted according to the time index table, and the number of collection points whose temperature data exceeds the middle value of the comparison interval is counted. When more than half of the collection points are higher than the middle value, the current indoor temperature and outdoor temperature are obtained synchronously, and the indoor and outdoor temperature data of the same period on the historical time axis are extracted from the historical database. If the current temperature data is also higher than the historical temperature of the same period, and the difference exceeds a certain range, it is determined to be overheating caused by environmental factors and marked as an environmental abnormal situation; Extract the temperature data of several other collection points at the same time according to the time index table. If no more than half of the collection points are higher than the median value, further determine the corresponding device according to the device index table to determine whether the device is in the same task list. If so, mark it as an abnormal device situation. If they are not in the same list, the operating status data of the corresponding equipment is obtained and input into the simulation model to determine whether the equipment has a fault and the type of fault. When the fault and the type of fault are output, it is determined to be an equipment abnormality. Otherwise, the corresponding collection points are summarized to generate abnormal prompt information.

8. The adaptive security remote drive control method according to claim 1, characterized in that: Different execution strategies are matched according to the different types of abnormal situations generated. When it is a single-point abnormal situation, the execution strategy is to retrieve the image data of the corresponding collection point for gas-liquid leakage image recognition, and at the same time determine the specific location based on the spatial index table, generate a first-level maintenance instruction and send it to the maintenance personnel to perform fixed-point maintenance and confirm local equipment or sensor problems; when it is a single-area equipment failure or equipment abnormality, a maintenance instruction is generated based on the specific equipment failure type given, and the current maintenance personnel are matched while the maintenance instruction is generated, and the maintenance instruction is sent to the maintenance personnel; when it is an environmental abnormality, the air-conditioning system in the corresponding area is started or the ventilation is adjusted, or the cooling power and ventilation volume are dynamically adjusted.

9. The adaptive security remote drive control method according to claim 8, characterized in that: When generating maintenance instructions, match the current maintenance personnel, send the maintenance instructions to the maintenance personnel, and simultaneously enable the permissions of the maintenance personnel in the corresponding area to follow up on subsequent maintenance situations.

10. An adaptive security remote drive control system, used to implement an adaptive security remote drive control method according to any one of claims 1 to 9, characterized in that: It includes a master control platform, a collection unit and an execution unit. The collection unit includes a temperature and humidity sensor and a video collector. The execution unit includes an air cooling system. The execution unit is also connected to a personnel management system. The master control platform is provided with a data storage unit, a real-time data matching unit, a data processing unit, an execution strategy generation unit and a feedback unit. The data storage unit includes a collection data storage group corresponding to each area. Each storage group is provided with a time index table, a space index table and a device index table. The real-time data matching unit includes several temperature time axes, each temperature time axis corresponds to a collection point. The collected temperature data is compared with the temperature time axis data to determine whether there is abnormal data. When there is abnormal data, the abnormal situation is determined by the data processing unit. The execution strategy generation unit generates an execution strategy according to the abnormal situation and transmits it to the execution unit for execution. While executing the execution strategy, the feedback unit obtains the real-time data of the corresponding collection point to feedback at a high frequency, and dynamically adjusts the execution strategy or stops the execution strategy according to the feedback.

Images