An environment-adaptive intelligent monitoring system and method for power distribution cabinets

Abstract

This invention relates to the field of power distribution cabinet technology and provides an intelligent monitoring system and method for environmentally adaptive power distribution cabinets. The system includes: S1, integrating several environmental sensors within the cabinet to collect environmental data during a collection period; S2, pre-setting an environmental state recognition model to obtain an environmental state pattern; S3, using the environmental state pattern as a judgment condition and external environmental data as a constraint condition, inputting them into a pre-set environmental decision rule to obtain a set of decision actions; S4, prioritizing the decision actions within the decision action set to obtain the optimal set of decision actions; S5, executing the decision actions and recording the decision results; and S6, performing backtracking analysis on the historical database according to a backtracking period to optimize the decision threshold. This invention achieves adaptive adjustment of the power distribution cabinet to the environment through a pre-set environmental state recognition model and environmental decision rules, and realizes adaptive optimization of the decision threshold through backtracking analysis of the historical database during the backtracking period.

Description

Technical Field

[0001] This invention relates to the field of power distribution cabinet technology, and more specifically, to an intelligent monitoring system and method for an environment-adaptive power distribution cabinet. Background Technology

[0002] A power distribution cabinet is a complete set of devices in a power system used to centrally install switching equipment, measuring instruments, protective electrical appliances, auxiliary equipment, and other components to realize the reception, distribution, control, protection, and monitoring of electrical energy. Power distribution cabinets are often installed in high-temperature, high-humidity, or dusty environments, and their environmental adaptability directly affects operational safety and lifespan. With the increasing growth of power loads and the increasing complexity of power consumption environments, higher requirements are placed on the environmental adaptability of power distribution cabinets. Ensuring the long-term stable operation of power distribution cabinets in complex and changing environments is a key task in power system design and operation and maintenance.

[0003] However, existing power distribution cabinets have significant shortcomings in environmental adaptability. On the one hand, when constructing environmental decision-making mechanisms, existing power distribution cabinets only consider the internal environmental conditions, neglecting the external environmental conditions. They have not established a collaborative decision-making mechanism based on internal needs and external constraints, which easily leads to the introduction of new problems from outside the cabinet after solving old problems inside. On the other hand, existing power distribution cabinets lack the ability to learn and optimize autonomously in terms of environmental self-adaptation. Their environmental adaptation strategies rely on fixed manual settings, while power distribution cabinets cannot dynamically evolve in complex environments, such as equipment aging. Therefore, the original environmental adaptation strategies set by the power distribution cabinets are difficult to maintain accuracy and effectiveness in the long term. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide an intelligent monitoring system and method for environmentally adaptive power distribution cabinets.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent monitoring method for an environment-adaptive power distribution cabinet, comprising the following steps: S1. Several environmental acquisition sensors are integrated inside the cabinet. The several environmental acquisition sensors have a preset acquisition period and acquire environmental data within the acquisition period. The environmental data includes environmental data inside the cabinet and environmental data outside the cabinet. S2. Preset an environmental state recognition model, and match the environmental state recognition model with the environmental data inside the cabinet to obtain an environmental state pattern; S3. Using the environmental state mode as the judgment condition and the external environmental data as the constraint condition, input them into the preset environmental decision rules to obtain a set of decision actions; S4. Evaluate the priority of each decision action in the decision action set, sort the priority of each decision action in the decision action set, and obtain the optimal decision action set; S5. Further execute decision actions based on the optimal decision action set, and record the decision results; S6. Establish a historical database to record each decision event, preset a backtracking period, perform backtracking analysis on the historical database according to the backtracking period, and optimize the decision threshold.

[0006] The present invention is further configured such that: the cabinet interior environmental data in S1 includes cabinet interior humidity. Cabinet temperature Concentration of particulate matter in the air inside the cabinet and condensation signal The external environmental data includes the external humidity. External temperature of cabinet Concentration of particulate matter in the air outside the cabinet , where i is a positive integer, representing the i-th acquisition cycle; The cabinet interior environment data vector for the i-th acquisition cycle is labeled as follows: The external environment data vector of the i-th acquisition cycle is labeled as .

[0007] The present invention is further configured such that the environmental state recognition model in S2 is specifically: Using the cabinet interior environment data vector To determine the conditions, a state mapping function for the cabinet is established. The cabinet internal state mapping function Specifically: ; in, , , , , These represent the mapping functions based on the preset cabinet state in the i-th cycle. The corresponding five environmental state modes, the Indicates an abnormal humidity state, the Indicating an abnormal temperature state, the Indicates the internal contamination status, the Indicates the critical state of condensation, the Indicates a normal environmental state; The Indicates the humidity threshold range inside the cabinet, the This indicates the temperature threshold range inside the cabinet. This indicates the threshold concentration of particulate matter inside the cabinet. This indicates that the cabinet is in a critical state of condensation during the i-th collection cycle. This indicates that there is no risk of condensation inside the cabinet during the i-th collection cycle; The cabinet interior environment data vector Input the cabinet internal state mapping function The judgment condition set for the i-th period is obtained. The set of judgment conditions Includes at least one environmental state mode.

[0008] The present invention is further configured such that: the environmental decision rule in S3 uses external environmental data as a constraint condition, specifically as follows: Using the external environment data vector of the cabinet Establish constraint mapping functions. The constraint mapping function Specifically: ; in, , These represent the mapping functions for the i-th period based on preset constraints. The corresponding two constraints, the This indicates that ventilation is permitted. This indicates that ventilation is prohibited; The Indicates the outdoor humidity threshold range, the Indicates the temperature threshold range outside the cabinet, the Indicates the threshold concentration of particulate matter outside the cabinet; The external environment data vector Input the constraint mapping function The external constraints of the cabinet in the i-th period are obtained. The external constraints of the cabinet for and One of them.

[0009] The present invention is further configured such that the environmental decision rule further includes: Set up environmental adjustment action set The set of environmental adjustment actions It includes at least energy-saving standby mode, exhaust operation, cooling operation, heating operation, and internal circulation filtration operation; Establish environmental decision-making rules ,in, Let represent the set of judgment conditions for the i-th period. Let represent the external constraints of the cabinet in the i-th cycle. This represents the set of decision actions for the i-th cycle, and the environmental decision rule. The exit conditions are for The environmental decision rules Specifically: When the for When, match In power-saving standby mode; When the Not included ,and for When, prioritize matching This is for ventilation. When the Not included ,and for When, match It is at least one of the following: refrigeration, heating, and internal circulation filtration.

[0010] The present invention is further configured such that S4 specifically comprises: S41. Evaluate the severity of the environmental state pattern corresponding to each decision action. The severity of the state is determined by the degree of deviation and the risk weight. Calculate the degree of deviation for each environmental state pattern. The This indicates the degree of deviation from environmental state mode j, specifically, when the decision data corresponding to environmental state mode j exceeds the boundary of its decision threshold, the excess amount is divided by the value of the boundary exceeded. The decision data is the cabinet state mapping function. The mapping data corresponding to the environmental state mode j mentioned above, and the decision threshold is the state mapping function inside the cabinet. The judgment threshold corresponding to the decision data mentioned above; S42. Assign a risk weight to each environmental state mode and calculate the severity of the state corresponding to each environmental state mode. , wherein This indicates the degree of deviation of the environmental state mode j. This represents the risk weight of the environmental state pattern j; S43. Preset a baseline rate of change for each decision data point. Calculate the rate of change for each decision data point based on the deviation between the current acquisition period and the previous acquisition period. Divide the rate of change by the preset baseline rate of change to obtain the state occurrence rate of the environmental state mode. ; S44. Calculate the urgency score for each of the environmental state modes. ,in The urgency weight indicates the severity of the situation. The urgency weight indicates the rate at which a state occurs; S45. Sort each environmental state mode from highest to lowest according to the urgency score, and sort the decision actions corresponding to the environmental state modes from front to back according to the sorting of the environmental state modes. That is, the higher the urgency of the environmental state mode, the higher the priority of its corresponding decision action, and obtain the optimal decision action set.

[0011] The present invention is further configured such that: the decision event includes environmental data, decision action, and decision result, wherein the decision result includes at least the time length from the start to the end of the decision action, i.e., the execution time; The backtracking analysis includes clustering the environmental data in the decision events and statistically analyzing the decision actions and results of the decision events under each environmental state mode.

[0012] The present invention is further configured such that the optimization of the decision threshold specifically involves: The decision threshold refers to the cabinet's internal state mapping function. Mapping function with constraints The decision thresholds include the humidity threshold range inside the cabinet. The temperature threshold range inside the cabinet The threshold for particulate matter concentration inside the cabinet The aforementioned external humidity threshold range The aforementioned external temperature threshold range and the threshold concentration of particulate matter outside the cabinet Analyze decision-making events based on the same environmental state pattern: If the decision events are intensive and the execution time of the decision results is short under the environmental state mode, then the decision threshold is relaxed based on the environmental data; If decision events are sparse and the execution time of decision results is long under the environmental state mode, then the decision threshold is tightened based on the environmental data.

[0013] An intelligent monitoring system for an environment-adaptive power distribution cabinet, used to implement the intelligent monitoring method for an environment-adaptive power distribution cabinet as described above, includes a data acquisition module, an environmental state identification module, a decision acquisition module, a priority ranking module, a decision execution module, and a backtracking optimization module, wherein... The data acquisition module is used to integrate several environmental acquisition sensors inside the cabinet and collect environmental data during the acquisition period. The environmental data includes environmental data inside the cabinet and environmental data outside the cabinet. The environmental status recognition module is used to match the environmental status recognition model based on the external environment data of the cabinet to obtain the environmental status pattern. The decision acquisition module is used to obtain a set of decision actions by inputting the environmental state mode as the judgment condition and the external environmental data as the constraint condition into the preset environmental decision rules. The priority sorting module is used to sort the decision actions within the decision action set by priority to obtain the optimal decision action set. The decision execution module is used to execute decision actions according to the optimal decision action set and record the decision results; The backtracking optimization module is used to establish a historical database, record each decision event, preset a backtracking period, perform backtracking analysis on the historical database according to the backtracking period, and optimize the decision threshold.

[0014] The present invention is further configured such that the decision execution module is connected to an exhaust device, a dehumidification device, a refrigeration device, a heating device, and an internal circulation filtration device.

[0015] In summary, this application includes at least one of the following beneficial technical effects of an environmentally adaptive intelligent monitoring system and method for distribution cabinets: 1. By introducing a two-layer decision-making rule that coordinates the judgment of the internal environment and external constraints, precise matching of environmental regulation is achieved, avoiding erroneous actions caused by only considering the internal environment without considering the external weather.

[0016] 2. By using a preset environmental state recognition model and environmental decision rules, the power distribution cabinet can adaptively adjust to the environment without the need for manual operation by staff, making it more efficient and intelligent.

[0017] 3. By prioritizing decision-making actions, conflicting decisions are prevented. At the same time, actions with high urgency are performed first. This ensures that when multiple environmental anomalies occur simultaneously, the power distribution cabinet can prioritize the most urgent protection actions, reducing the risk of equipment damage and safety accidents.

[0018] 4. By establishing a historical database and setting a backtracking period, the historical database is backtracked and analyzed within the backtracking period, which realizes adaptive optimization of decision thresholds. Distribution cabinets in different regions and at different altitudes can automatically optimize and adapt to their environment as operating data accumulates during use, overcoming the shortcomings of traditional distribution cabinets that cannot adapt to dynamic changes such as seasons, regions and equipment aging due to fixed thresholds. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system modules of the present invention. Detailed Implementation

[0020] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] It should be noted that, unless otherwise specified, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0022] Please see Figures 1 to 2 The present invention provides the following technical solutions: Example 1, see Figure 1 An intelligent monitoring method for an environment-adaptive power distribution cabinet includes the following steps: S1. The cabinet integrates several environmental acquisition sensors, which are preset with an acquisition period. During the acquisition period, environmental data is collected. The environmental data includes indoor environmental data and outdoor environmental data. Specifically, the several environmental acquisition sensors include indoor humidity sensor, indoor temperature sensor, indoor air particulate matter detection sensor, condensation sensor, outdoor humidity sensor, outdoor temperature sensor, and outdoor air particulate matter detection sensor. S2. Preset environmental status recognition model, match the environmental status recognition model with the environmental data inside the cabinet to obtain the environmental status pattern; S3. Using the environmental state mode as the judgment condition and the external environmental data as the constraint condition, input them into the preset environmental decision rules to obtain the decision action set; S4. Evaluate the priority of each decision action in the decision action set, sort the priority of each decision action in the decision action set, and obtain the optimal decision action set. S5. Execute further decision actions based on the optimal decision action set, and record the decision results; S6. Establish a historical database to record each decision event, preset the backtracking period, perform backtracking analysis on the historical database according to the backtracking period, and optimize the decision threshold.

[0023] Furthermore, the cabinet interior environmental data in S1 includes cabinet humidity. Cabinet temperature Concentration of particulate matter in the air inside the cabinet and condensation signal External environmental data includes external humidity. External temperature of cabinet Concentration of particulate matter in the air outside the cabinet Where i is a positive integer, representing the i-th acquisition cycle, condensation signal. include and , This indicates that the cabinet is in a critical state of condensation during the i-th collection cycle. This indicates that there is no risk of condensation inside the cabinet during the i-th collection cycle.

[0024] The cabinet interior environment data vector for the i-th acquisition cycle is labeled as follows. The external environment data vector of the i-th acquisition cycle is labeled as .

[0025] Furthermore, the environmental state recognition model in S2 is specifically as follows: Using cabinet interior environmental data vectors To determine the conditions, a state mapping function for the cabinet is established. Cabinet internal state mapping function Specifically: ; in, , , , , These represent the mapping functions based on the preset cabinet state in the i-th cycle. The corresponding five environmental state modes, This indicates an abnormal humidity level. Indicates an abnormal temperature condition. Indicates the internal pollution status. This indicates the critical state of condensation. Indicates a normal environmental state; This indicates the temperature threshold range inside the cabinet. This indicates the threshold concentration of particulate matter inside the cabinet. This indicates that the cabinet is in a critical state of condensation during the i-th collection cycle. This indicates that there is no risk of condensation inside the cabinet during the i-th collection cycle; Vector the environmental data inside the cabinet Input cabinet internal state mapping function The judgment condition set for the i-th period is obtained. , condition set This includes at least one environmental state mode. Apart from the normal environmental state, these environmental state modes are independent of each other and can coexist simultaneously. For example, before a summer thunderstorm, high humidity, high temperature, and condensation critical conditions may occur simultaneously. (40%, 70%) (15℃, 35℃) for , obtain , , , The mapping yields the set of judgment conditions as follows: .

[0026] Furthermore, the environmental decision rules in S3 use external environmental data as constraints, specifically as follows: External environmental data vector Establish constraint mapping functions. constraint mapping function Specifically: ; in, , These represent the mapping functions for the i-th period based on preset constraints. The corresponding two types of constraints, This indicates that ventilation is permitted. This indicates that ventilation is prohibited. Indicates the humidity threshold range outside the cabinet. Indicates the temperature threshold range outside the cabinet. The threshold for the concentration of particulate matter outside the cabinet is indicated. The ventilation is activated based on the humidity, temperature and particulate matter concentration outside the cabinet. This invention can identify the environmental conditions outside the cabinet and avoid bringing in moisture or pollutants when introducing external air through ventilation, thus improving the safety and effectiveness of the environmental adaptive function of this invention. Vector data of the external environment of the cabinet Input constraint mapping function The external constraints of the cabinet in the i-th period are obtained. External constraints of the cabinet for and One of them, for example, before summer thunderstorms, is known (30%, 80%) (10℃, 40℃). , obtain , , The determination is that ventilation is not allowed, meaning the external constraints of the cabinet are... Or, during a sandstorm, to obtain , , The determination is that ventilation is not allowed, meaning the external constraints of the cabinet are... .

[0027] Furthermore, environmental decision-making rules further include: Set up environmental adjustment action set Environmental adjustment action set It includes at least energy-saving standby mode, exhaust operation, cooling operation, heating operation, and internal circulation filtration operation; Establish environmental decision-making rules ,in, Let represent the set of judgment conditions for the i-th period. Let represent the external constraints of the cabinet in the i-th cycle. This represents the set of decision actions in the i-th cycle, and the environmental decision rule. The exit conditions are for Environmental decision-making rules Specifically: when for When, match In power-saving standby mode; when Not included ,and for When, prioritize matching This is for ventilation. when Not included ,and for When, match It is at least one of the following: dehumidification, cooling, heating, and internal circulation filtration.

[0028] For example, as shown in Table 1, set the environmental decision rules:

[0029] By employing a dual-layer decision-making rule system that considers both the internal environmental state mode and external constraints, the system can intelligently select between exhaust ventilation and internal closed-loop regulation based on the external environment. This avoids secondary pollution caused by blind ventilation in harsh weather conditions such as rain, snow, and sandstorms, which is common in traditional power distribution cabinets. Simultaneously, an energy-saving standby mode is set up under normal environmental conditions to reduce energy consumption, achieving a balance between environmental adaptability and low energy consumption. Through a preset environmental state recognition model and environmental decision-making rules, the power distribution cabinet can adaptively adjust to the environment without requiring manual operation by staff, making it more efficient and intelligent.

[0030] Furthermore, S4 specifically refers to: S41. Evaluate the severity of the environmental state pattern corresponding to each decision action. The severity of the state is determined by the degree of deviation and the risk weight. Calculate the degree of deviation for each environmental state pattern. , This indicates the degree of deviation of environmental state mode j, specifically, when the decision data corresponding to environmental state mode j exceeds the boundary of its decision threshold, the excess amount is divided by the value of the boundary exceeded. The decision data is the cabinet state mapping function. The mapping data corresponding to the environmental state mode j, and the decision threshold is the cabinet state mapping function. The judgment threshold corresponding to the decision data in the middle; S42. Assign risk weights to each environmental state pattern and calculate the severity of the corresponding environmental state pattern. ,in This indicates the degree of deviation of the environmental state pattern j. This represents the risk weight of environmental state pattern j; S43. Preset a baseline rate of change for each decision data point. Calculate the rate of change for each decision data point based on the deviation between the current and previous acquisition cycles. Divide the rate of change by the preset baseline rate of change to obtain the rate of occurrence of the environmental state mode. ; S44. Calculate the urgency score for each environmental state mode. ,in The urgency weight indicates the severity of the situation. The urgency weight indicates the rate at which a state occurs; S45. Sort each environmental state mode from highest to lowest according to the urgency score. Sort the decision actions corresponding to the environmental state modes from front to back according to the sorting of the environmental state modes. That is, the higher the urgency of the environmental state mode, the higher the priority of its corresponding decision action, and obtain the optimal decision action set.

[0031] By prioritizing decision-making actions, conflicts can be prevented, and actions with high urgency can be performed first. This ensures that when multiple environmental anomalies occur simultaneously, the power distribution cabinet can prioritize the most urgent protective actions, reducing the risk of equipment damage and safety accidents.

[0032] Furthermore, the decision event includes environmental data, decision actions, and decision results, wherein the decision results include at least the length of time from the start to the end of the decision action, i.e., the execution time; Retrospective analysis includes clustering based on environmental data in decision events and statistically analyzing the decision actions and results of decision events under each environmental state pattern.

[0033] Furthermore, the optimization of the decision threshold is specifically as follows: Decision threshold refers to the state mapping function within the cabinet. Mapping function with constraints The decision thresholds include the humidity threshold range inside the cabinet. Cabinet internal temperature threshold range Particulate matter concentration threshold inside the cabinet External humidity threshold range External temperature threshold range And the threshold of particulate matter concentration outside the cabinet Analyze decision-making events based on the same environmental state pattern: If decision events are frequent and the execution time of decision results is short under the environmental state mode, the decision threshold can be relaxed based on environmental data. If decision events are sparse and execution time is long in the decision results under the environmental state mode, then the decision threshold is tightened based on environmental data.

[0034] Specifically, a certain distribution cabinet has a preset internal temperature threshold range. The temperature range is (15℃, 35℃). A one-month backtracking period is set. After one month, the system performs a backtracking analysis of the historical database and finds 110 decision-making events recorded under high-temperature conditions, with an average execution time of 5 minutes. This determines the temperature threshold range inside the cabinet. Because (15℃, 35℃) is too sensitive, this method automatically adjusts the temperature threshold range. Adjust to (15℃, 36℃).

[0035] By establishing a historical database and setting a backtracking period, and conducting backtracking analysis on the historical database within the backtracking period, adaptive optimization of decision thresholds is achieved. Distribution cabinets in different regions and at different altitudes can automatically optimize and adapt to their environment as operational data accumulates during use, overcoming the shortcomings of traditional distribution cabinets that cannot adapt to dynamic changes such as seasons, regions, and equipment aging due to fixed thresholds.

[0036] Example 2, see Figure 2 An environment-adaptive intelligent monitoring system for power distribution cabinets, used to implement the aforementioned environment-adaptive intelligent monitoring method for power distribution cabinets, includes a data acquisition module, an environmental state identification module, a decision acquisition module, a priority ranking module, a decision execution module, and a backtracking optimization module, wherein... The data acquisition module is used to integrate several environmental acquisition sensors inside the cabinet to collect environmental data during the acquisition period. The environmental data includes environmental data inside the cabinet and environmental data outside the cabinet. The environmental status recognition module is used to match the environmental status recognition model with the external environmental data to obtain the environmental status pattern; The decision acquisition module is used to obtain a set of decision actions by taking the environmental state mode as the judgment condition and the external environmental data as the constraint condition and inputting it into the preset environmental decision rules. The priority sorting module is used to sort the decision actions within the decision action set by priority and obtain the optimal decision action set; The decision execution module is used to execute decision actions based on the optimal set of decision actions and record the decision results; The backtracking optimization module is used to build a historical database, record each decision event, preset the backtracking period, perform backtracking analysis on the historical database according to the backtracking period, and optimize the decision threshold.

[0037] Furthermore, the decision execution module is connected to an exhaust system, a dehumidification system, a refrigeration system, a heating system, and an internal circulation filtration system.

[0038] Obviously, the embodiments described above are merely some, not all, embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort should fall within the scope of protection of the present invention.

Claims

1. An intelligent monitoring method for an environment-adaptive power distribution cabinet, characterized in that, Includes the following steps: S1. Several environmental acquisition sensors are integrated inside the cabinet. The several environmental acquisition sensors have a preset acquisition period and acquire environmental data within the acquisition period. The environmental data includes environmental data inside the cabinet and environmental data outside the cabinet. S2. Preset an environmental state recognition model, and match the environmental state recognition model with the environmental data inside the cabinet to obtain an environmental state pattern; S3. Using the environmental state mode as the judgment condition and the external environmental data as the constraint condition, input them into the preset environmental decision rules to obtain a set of decision actions; S4. Evaluate the priority of each decision action in the decision action set, sort the priority of each decision action in the decision action set, and obtain the optimal decision action set; S5. Further execute decision actions based on the optimal decision action set, and record the decision results; S6. Establish a historical database to record each decision event, preset a backtracking period, perform backtracking analysis on the historical database according to the backtracking period, and optimize the decision threshold.

2. The intelligent monitoring method for an environmentally adaptive power distribution cabinet according to claim 1, characterized in that: The cabinet interior environmental data in S1 includes cabinet humidity. Cabinet temperature Concentration of particulate matter in the air inside the cabinet and condensation signal The external environmental data includes the external humidity. External temperature of cabinet Concentration of particulate matter in the air outside the cabinet , where i is a positive integer, representing the i-th acquisition cycle; The cabinet interior environment data vector for the i-th acquisition cycle is labeled as follows: The external environment data vector of the i-th acquisition cycle is labeled as .

3. The intelligent monitoring method for an environmentally adaptive power distribution cabinet according to claim 2, characterized in that, The environmental state identification model in S2 is specifically as follows: Using the cabinet interior environment data vector To determine the conditions, a state mapping function for the cabinet is established. The cabinet internal state mapping function Specifically: ； in, , , , , These represent the mapping functions based on the preset cabinet state in the i-th cycle. The corresponding five environmental state modes, the Indicates an abnormal humidity state, the Indicating an abnormal temperature state, the Indicates the internal contamination status, the Indicates the critical state of condensation, the Indicates a normal environmental state; The Indicates the humidity threshold range inside the cabinet, the This indicates the temperature threshold range inside the cabinet. This indicates the threshold concentration of particulate matter inside the cabinet. This indicates that the cabinet is in a critical state of condensation during the i-th collection cycle. This indicates that there is no risk of condensation inside the cabinet during the i-th collection cycle; The cabinet interior environment data vector Input the cabinet internal state mapping function The judgment condition set for the i-th period is obtained. The set of judgment conditions Includes at least one environmental state mode.

4. The intelligent monitoring method for an environmentally adaptive power distribution cabinet according to claim 3, characterized in that, The environmental decision rule in S3 uses external environmental data as a constraint condition as follows: Using the external environment data vector of the cabinet Establish constraint mapping functions. The constraint mapping function Specifically: ； in, , These represent the mapping functions for the i-th period based on preset constraints. The corresponding two constraints, the This indicates that ventilation is permitted. This indicates that ventilation is prohibited; The Indicates the outdoor humidity threshold range, the Indicates the temperature threshold range outside the cabinet, the Indicates the threshold concentration of particulate matter outside the cabinet; The external environment data vector Input the constraint mapping function The external constraints of the cabinet in the i-th period are obtained. The external constraints of the cabinet for and One of them.

5. The intelligent monitoring method for an environmentally adaptive power distribution cabinet according to claim 4, characterized in that, The environmental decision-making rules further include: Set up environmental adjustment action set The set of environmental adjustment actions It includes at least energy-saving standby mode, exhaust operation, cooling operation, heating operation, and internal circulation filtration operation; Establish environmental decision-making rules ,in, Let represent the set of judgment conditions for the i-th period. Let represent the external constraints of the cabinet in the i-th cycle. This represents the set of decision actions for the i-th cycle, and the environmental decision rule. The exit conditions are for The environmental decision rules Specifically: When the for When, match In power-saving standby mode; When the Not included ,and for When, prioritize matching This is for ventilation. When the Not included ,and for When, match It is at least one of the following: dehumidification, cooling, heating, and internal circulation filtration.

6. The intelligent monitoring method for an environmentally adaptive power distribution cabinet according to claim 5, characterized in that, Specifically, S4 is: S41. Evaluate the severity of the environmental state pattern corresponding to each decision action. The severity of the state is determined by the degree of deviation and the risk weight. Calculate the degree of deviation for each environmental state pattern. The This indicates the degree of deviation from environmental state mode j, specifically, when the decision data corresponding to environmental state mode j exceeds the boundary of its decision threshold, the excess amount is divided by the value of the boundary exceeded. The decision data is the cabinet state mapping function. The mapping data corresponding to the environmental state mode j mentioned above, and the decision threshold is the state mapping function inside the cabinet. The judgment threshold corresponding to the decision data mentioned above; S42. Assign a risk weight to each environmental state mode and calculate the severity of the state corresponding to each environmental state mode. , wherein This indicates the degree of deviation of the environmental state mode j. This represents the risk weight of the environmental state pattern j; S43. Preset a baseline rate of change for each decision data point. Calculate the rate of change for each decision data point based on the deviation between the current acquisition period and the previous acquisition period. Divide the rate of change by the preset baseline rate of change to obtain the state occurrence rate of the environmental state mode. ; S44. Calculate the urgency score for each of the environmental state modes. ,in The urgency weight indicates the severity of the situation. The urgency weight indicates the rate at which a state occurs; S45. Sort each environmental state mode from highest to lowest according to the urgency score, and sort the decision actions corresponding to the environmental state modes from front to back according to the sorting of the environmental state modes. That is, the higher the urgency of the environmental state mode, the higher the priority of its corresponding decision action, and obtain the optimal decision action set.

7. The intelligent monitoring method for an environmentally adaptive power distribution cabinet according to claim 6, characterized in that, The decision event includes environmental data, decision actions, and decision results, wherein the decision results include at least the time elapsed from the start to the end of the decision action, i.e., the execution time. The backtracking analysis includes clustering the environmental data in the decision events and statistically analyzing the decision actions and results of the decision events under each environmental state mode.

8. The intelligent monitoring method for an environmentally adaptive power distribution cabinet according to claim 7, characterized in that, The optimization of the decision threshold is specifically as follows: The decision threshold refers to the cabinet's internal state mapping function. Mapping function with constraints The decision thresholds include the humidity threshold range inside the cabinet. The temperature threshold range inside the cabinet The threshold for particulate matter concentration inside the cabinet The aforementioned external humidity threshold range The aforementioned external temperature threshold range and the threshold concentration of particulate matter outside the cabinet Analyze decision-making events based on the same environmental state pattern: If the decision events are intensive and the execution time of the decision results is short under the environmental state mode, then the decision threshold is relaxed based on the environmental data; If decision events are sparse and the execution time of decision results is long under the environmental state mode, then the decision threshold is tightened based on the environmental data.

9. An intelligent monitoring system for an environment-adaptive distribution cabinet, used to implement the intelligent monitoring method for an environment-adaptive distribution cabinet as described in claim 8, characterized in that, It includes a data acquisition module, an environmental status identification module, a decision acquisition module, a priority ranking module, a decision execution module, and a backtracking optimization module. The data acquisition module is used to integrate several environmental acquisition sensors inside the cabinet and collect environmental data during the acquisition period. The environmental data includes environmental data inside the cabinet and environmental data outside the cabinet. The environmental status recognition module is used to match the environmental status recognition model based on the external environment data of the cabinet to obtain the environmental status pattern. The decision acquisition module is used to obtain a set of decision actions by inputting the environmental state mode as the judgment condition and the external environmental data as the constraint condition into the preset environmental decision rules. The priority sorting module is used to sort the decision actions within the decision action set by priority to obtain the optimal decision action set. The decision execution module is used to execute decision actions according to the optimal decision action set and record the decision results; The backtracking optimization module is used to establish a historical database, record each decision event, preset a backtracking period, perform backtracking analysis on the historical database according to the backtracking period, and optimize the decision threshold.

10. The intelligent monitoring system for an environmentally adaptive power distribution cabinet according to claim 9, characterized in that, The decision execution module is connected to an exhaust device, a dehumidification device, a refrigeration device, a heating device, and an internal circulation filtration device.

Images