Intelligent temperature and humidity control system for power distribution cabinet

Abstract

The invention relates to the technical field of power distribution cabinet temperature control, in particular to an intelligent temperature and humidity control system for a power distribution cabinet. Comprising an environmental parameter acquisition module, a data analysis processing module, a temperature and humidity regulation and control module, an energy consumption recovery optimization module and a monitoring alarm module. The environmental parameter acquisition module monitors environmental data such as temperature, humidity and voltage through a sensor, and the data analysis processing module analyzes a trend based on a time convolutional neural network. The temperature and humidity regulation and control module achieves optimal control through an optimization algorithm, and the energy consumption recovery optimization module recovers and optimizes energy through a genetic algorithm. And the monitoring alarm module adopts a Bayesian network to be combined with a self-adaptive sliding window mechanism to monitor environmental fluctuation in real time, and gives an alarm when the environmental fluctuation is abnormal. Efficient operation, safety and stability of the power distribution cabinet in a complex environment are ensured, the safety and reliability of the power distribution cabinet are improved, the operation and maintenance cost can be effectively reduced, and energy conservation and environmental protection are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of temperature control of a power distribution cabinet, and in particular to an intelligent temperature and humidity control system for a power distribution cabinet. Background Art

[0002] In modern industrial production and power systems, distribution cabinets, as an important part of electrical equipment, are widely used in places such as substations, factories and data centers. The internal equipment of the distribution cabinet is very sensitive to changes in ambient temperature and humidity, especially in high temperature or high humidity environments, which can easily cause electrical components to overheat, insulation performance degradation or even failure, thereby affecting the safety and stability of power supply. In order to ensure that the electrical equipment in the distribution cabinet can operate stably under suitable environmental conditions and reduce safety hazards, it is particularly important to effectively control the temperature and humidity of the distribution cabinet. At present, there are still the following problems: most of the existing technologies rely on simple heaters or fans for manual adjustment. Manual control cannot respond to environmental changes in real time, and it is difficult to handle abnormal fluctuations in temperature and humidity in a timely manner; the operating efficiency of traditional heating and cooling equipment is not high, which easily causes energy waste; the existing system lacks an efficient abnormality detection mechanism, resulting in delayed fault response and high false alarm rate, affecting system safety and maintenance efficiency. Summary of the invention

[0003] To solve the above problems, the present invention provides an intelligent temperature and humidity control system for a distribution cabinet, which solves the problem of how to achieve accurate real-time control of temperature and humidity in the distribution cabinet, avoid energy waste and efficiently detect anomalies, and ensure that electrical equipment operates stably in a suitable environment.

[0004] To achieve the above object, the technical solution adopted by the present invention is: An intelligent temperature and humidity control system for a power distribution cabinet, comprising an environmental parameter acquisition module, a data analysis and processing module, a temperature and humidity control module, an energy consumption recovery optimization module and a monitoring and alarm module which are sequentially connected in communication; The environmental parameter acquisition module is used to collect environmental parameters of the power distribution cabinet through a sensor network, and the environmental parameters include temperature, humidity, voltage, current, air pressure, air quality and dust of the power distribution cabinet; The data analysis and processing module is used to analyze the environmental change trend based on the environmental parameters using a time convolutional neural network algorithm and generate an analysis report; The temperature and humidity control module is used to generate an optimal temperature and humidity control strategy based on the analysis report using an optimization algorithm, and convert it into a control instruction, and perform temperature and humidity control on the power distribution cabinet in combination with an adaptive control algorithm; The energy consumption recovery optimization module is used to dynamically optimize the energy consumption of the system by using an energy consumption optimization algorithm based on a genetic algorithm, and to recover and reuse the excess heat and electrical energy generated in the system through an energy recovery mechanism; The monitoring and alarm module is used to monitor real-time data fluctuations based on preset environmental parameter thresholds and real-time monitoring data, using a Bayesian network anomaly detection algorithm combined with an adaptive sliding window mechanism. When environmental parameters fluctuate abnormally or exceed safety thresholds, an alarm signal is triggered and maintenance personnel are notified.

[0005] Furthermore, the operation process of the data analysis and processing module includes the following steps: Receiving the environmental parameters and performing preprocessing, including removing noise, screening outliers and signal smoothing; The preprocessed environmental parameters are input into the time convolutional neural network model in time series, and the changing characteristics of environmental parameters in different periods are extracted through the multi-layer convolution of the model. The analysis accuracy of environmental trend changes is enhanced according to the convolution kernel adaptive adjustment mechanism. Based on the output of the temporal convolutional neural network model, the correlation between various environmental parameters is deeply mined to identify the potential correlation between temperature, humidity and electrical load and environmental abnormal conditions; Combine historical data and trend analysis results to predict environmental changes in the future, issue early warnings for abnormal fluctuation risks, and generate detailed analysis reports.

[0006] Furthermore, the formula of the temporal convolutional neural network model is as follows:

[0007] in, represents the future predicted value of the environmental parameters of the power distribution cabinet; L represents the number of layers of the convolutional network, and the characteristics of the environmental parameters are extracted more deeply through the multi-layer convolution structure; f represents the activation function; K represents the time convolution window size, that is, the number of historical time steps considered at each moment; N represents the number of input environmental parameters; Indicates the weight distribution of different layers at different times and in different environmental parameters; represents the input value of the jth environmental parameter at the l-1th layer at time tk; represents the bias term of the lth layer; represents the residual connection term, is the residual coefficient, Represents a collection of raw input environment parameters.

[0008] Furthermore, the operation process of the temperature and humidity control module includes the following steps: Receive the analysis report, obtain the generated environmental change trend, calculate the optimal control range of real-time temperature and humidity, dynamically match the current load characteristics of the distribution cabinet, and set hierarchical control targets; Based on the temperature and humidity control target range, an immune optimization algorithm is used to generate an optimal temperature and humidity control strategy; The temperature and humidity control strategy is converted into control instructions, and combined with an adaptive control algorithm, the control equipment in the power distribution cabinet is dynamically adjusted to achieve precise control of temperature and humidity; The control effect is continuously monitored through a feedback mechanism, and the immune memory is enhanced based on real-time and historical data to adjust the temperature and humidity control strategies.

[0009] Furthermore, the formula of the immune optimization algorithm is as follows:

[0010] in, represents the optimal temperature and humidity control strategy; n represents the number of control targets; Represents the weight coefficient of the control target; Represents the actual control effect value of regulation target i; Represents the energy consumption weight factor, balancing the system energy consumption and regulation effect; E represents the system energy consumption value, including the energy consumption when the temperature and humidity control module is running; represents the penalty coefficient of the constraint condition; m represents the number of constraints, including the threshold of the environmental parameters of the power distribution cabinet; Indicates the degree of deviation of the current strategy from the constraints; Indicates the maximum allowable deviation value for each constraint.

[0011] Furthermore, the temperature and humidity control module includes a plurality of heating elements and cooling fans, and the heating elements and cooling fans are started and stopped according to the control instructions. It also includes a humidity control device to adjust the humidity in the distribution cabinet by evaporation or moisture absorption.

[0012] Furthermore, the energy consumption recovery optimization module includes an energy consumption optimization unit and an energy recovery and utilization unit; The energy consumption optimization unit is used to dynamically optimize the energy consumption of the system through a genetic algorithm, comprehensively analyze the real-time load and temperature and humidity requirements of the distribution cabinet, and optimize the energy consumption distribution; The energy recovery unit is used to convert thermal energy into electrical energy for system self-powering by utilizing waste heat and ambient humidity during system operation through an integrated thermoelectric conversion and condensed water collection mechanism, and to use the recovered water for environmental cooling storage.

[0013] Furthermore, the operation process of the energy consumption optimization unit includes the following steps: Receive real-time load data, temperature and humidity requirements, and current environmental parameters from the power distribution cabinet, and make a preliminary assessment of energy consumption requirements; An energy consumption optimization model is built based on a genetic algorithm, and a fitness function is set. The system energy consumption and operating efficiency are taken as optimization targets, and the weight coefficients of temperature and humidity requirements and load fluctuations are considered to generate the initial population. Use genetic operations such as crossover and mutation to iteratively update the population, optimize the energy consumption allocation plan of each generation of individuals, and select the energy consumption allocation plan with the highest energy efficiency; Output the optimal energy consumption allocation plan and convert it into control instructions for execution.

[0014] Furthermore, the adaptive sliding window mechanism specifically analyzes the volatility of the data, adaptively adjusts the sliding window size according to the size of the volatility, and performs statistical analysis on the monitoring data within the range of the sliding window to determine whether there are any abnormal conditions. If the monitoring data exceeds a preset threshold, an alarm is triggered in a timely manner and the abnormal data is recorded.

[0015] The beneficial effects of the present invention are: Through the environmental parameter acquisition module, the system of the present invention can collect multiple parameters such as temperature, humidity, voltage, current, etc. in the power distribution cabinet in real time, providing comprehensive basic data for subsequent analysis and regulation. At the same time, the data analysis and processing module uses the time convolution neural network algorithm to analyze the trend of environmental changes, realizes the accurate prediction of environmental parameters, and helps to take regulatory measures in advance to extend the life of the equipment. Based on the trend report generated by data analysis, the temperature and humidity control module can dynamically generate the optimal control strategy, and combine the adaptive control algorithm to achieve accurate temperature and humidity control, ensure that the power distribution cabinet operates under the most suitable environmental conditions, effectively prevent equipment from malfunctioning due to temperature and humidity changes, and improve the stability and safety of system operation. The system is equipped with an energy consumption recovery optimization module, which uses a genetic algorithm to optimize energy consumption, dynamically adjusts the energy consumption of the system, and improves energy utilization efficiency. In addition, through the energy recovery mechanism, the system can recycle and reuse excess heat and electricity, reduce energy waste, and achieve energy saving and environmental protection. The monitoring and alarm module monitors the fluctuation of real-time data through the Bayesian network anomaly detection algorithm and the adaptive sliding window mechanism. When an anomaly is detected or a parameter exceeds a threshold, the system will immediately trigger an alarm signal to notify maintenance personnel, ensuring timely intervention before potential failures occur, thereby improving system reliability and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a module schematic diagram of an intelligent temperature and humidity control system for a power distribution cabinet according to the present invention.

[0017] Figure 2 It is a flowchart of the operation process of the data analysis and processing module provided by one embodiment of the present invention.

[0018] Figure 3 It is a flow chart of the operation process of the temperature and humidity control module provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0019] See also Figure 1-3As shown, the present invention relates to an intelligent temperature and humidity control system for a power distribution cabinet.

[0020] Example An intelligent temperature and humidity control system for a power distribution cabinet, comprising an environmental parameter acquisition module, a data analysis and processing module, a temperature and humidity control module, an energy consumption recovery optimization module and a monitoring and alarm module which are sequentially connected in communication; The environmental parameter acquisition module is used to collect environmental parameters of the power distribution cabinet through a sensor network, and the environmental parameters include temperature, humidity, voltage, current, air pressure, air quality and dust of the power distribution cabinet; It should be noted that the sensor network in the environmental parameter acquisition module is used to collect environmental data inside and outside the power distribution cabinet in real time. These sensors cover the following categories: Temperature sensors: Placed at key locations inside and outside the distribution cabinet to accurately measure the temperature inside and outside the cabinet to ensure data accuracy.

[0021] Humidity sensor: used to monitor the humidity level in the power distribution cabinet to prevent problems such as circuit short circuit caused by excessive humidity.

[0022] Voltage and current sensors: measure the working status of the power system of the distribution cabinet in real time to prevent overload or other power anomalies.

[0023] Air pressure sensor: monitors the changes in air pressure inside the distribution cabinet to ensure the stability of system operation.

[0024] Air quality sensor: detects the pollution level of the air around the distribution cabinet, mainly used to identify potential risks such as smoke and volatile organic compounds.

[0025] Dust sensor: monitors the dust content inside and outside the cabinet to prevent poor heat dissipation and circuit failure caused by dust accumulation.

[0026] All sensors are connected to the acquisition terminal and upload data to the data analysis and processing module through wired or wireless networks.

[0027] The data analysis and processing module is used to analyze the environmental change trend based on the environmental parameters using a time convolutional neural network algorithm and generate an analysis report; The operation process of the data analysis and processing module includes the following steps: Receiving the environmental parameters and performing preprocessing, including removing noise, screening outliers and signal smoothing; The preprocessed environmental parameters are input into the time convolutional neural network model (TCN) in time series. The changing characteristics of environmental parameters in different periods are extracted through the multi-layer convolution of the model, and the analysis accuracy of environmental trend changes is enhanced according to the convolution kernel adaptive adjustment mechanism. Specifically, the preprocessed environmental parameter data is input into the TCN model in time series. The temporal convolutional neural network is suitable for processing time series data and can extract multi-level features from it.

[0028] In the TCN model, multiple layers of one-dimensional convolution are set up, and each layer of convolution extracts features of different time ranges in order to capture short-term fluctuations and long-term trends of environmental parameters. By extending the convolution, the model can extract trend information from a longer time span, thereby more effectively capturing the characteristics of environmental parameters changing over time. During the model training process, the convolution kernel will be adaptively adjusted according to the different characteristics of the environmental parameters. For example, temperature and humidity parameters may require a smaller convolution kernel to capture subtle changes, while parameters such as current and voltage use a larger convolution kernel to capture periodic fluctuations. The adaptive adjustment mechanism of the convolution kernel is used to enhance the analysis accuracy of TCN on environmental trend changes, so that the model can more accurately predict future environmental changes.

[0029] Based on the output of the temporal convolutional neural network model, the correlation between various environmental parameters is deeply mined to identify the potential correlation between temperature, humidity and electrical load and environmental abnormal conditions; Specifically, based on the output of the TCN model, deep correlation mining is performed on parameters such as temperature, humidity, voltage, and current. The features of different parameters are fused into a feature vector to deeply analyze the relationship between various environmental parameters. For example, the interactive relationship between temperature, humidity, and electrical load is analyzed to observe whether rising humidity will cause current fluctuations. Multidimensional correlation analysis methods (such as Pearson correlation coefficient or multivariate regression analysis) are used to identify potential associations between parameters such as temperature, humidity, and electrical load and abnormal environmental conditions. For example, increased humidity may be accompanied by increased temperature and increased electrical load, indicating that the cooling system may fail.

[0030] Combine historical data and trend analysis results to predict environmental changes in the future, issue early warnings for abnormal fluctuation risks, and generate detailed analysis reports.

[0031] Specifically, the environmental parameters for a certain period of time in the future are predicted by combining historical data and features extracted by the TCN model. The TCN model is used to predict environmental changes in the short term (such as 1-2 hours) to help operation and maintenance personnel understand upcoming fluctuations. Combined with historical data over a longer period of time, trends such as temperature, humidity, and voltage are predicted for the next few days or weeks, making it easier to formulate maintenance plans in advance. The TCN model can also identify potential abnormal fluctuations by predicting the amplitude and frequency of data fluctuations. If the predicted value fluctuates drastically or exceeds the normal range in a short period of time, the module will determine it as a potential abnormal situation. When the predicted parameters exceed the set safety threshold, the module will trigger an early warning signal to notify the operation and maintenance personnel to take measures in advance.

[0032] Furthermore, the formula of the temporal convolutional neural network model is as follows:

[0033] in, represents the future predicted value of the environmental parameters of the power distribution cabinet; L represents the number of layers of the convolutional network, and the characteristics of the environmental parameters are extracted more deeply through the multi-layer convolution structure; f represents the activation function; K represents the time convolution window size, that is, the number of historical time steps considered at each moment; N represents the number of input environmental parameters; Indicates the weight distribution of different layers at different times and for different environmental parameters. For example, the weights for temperature and humidity are larger, ensuring that the model gives priority to key parameters when predicting environmental changes. represents the input value of the jth environmental parameter at the l-1th layer at time tk; Represents the bias term of the lth layer, which is used to adjust the overall prediction value of the model to ensure that the prediction output conforms to the actual changes in the distribution cabinet environment; represents the residual connection term, is the residual coefficient, Represents a collection of raw input environment parameters.

[0034] The temperature and humidity control module is used to generate the optimal temperature and humidity control strategy based on the analysis report and the optimization algorithm, and convert it into control instructions, and combine the adaptive control algorithm to control the temperature and humidity of the distribution cabinet; the temperature and humidity control module includes a number of heating elements and cooling fans, and the heating elements and cooling fans are started and stopped according to the control instructions, and also includes a humidity control device to adjust the humidity in the distribution cabinet by evaporation or moisture absorption.

[0035] The operation process of the temperature and humidity control module includes the following steps: Receive the analysis report, obtain the generated environmental change trend, calculate the optimal control range of real-time temperature and humidity, dynamically match the current load characteristics of the distribution cabinet, and set hierarchical control targets; Specifically, the temperature and humidity control module receives an analysis report from the data analysis and processing module. The report contains the current values ​​of environmental parameters, predicted change trends, and abnormal warning information. Based on the environmental change trends and parameter correlation analysis in the analysis report, the module calculates the optimal control range of temperature and humidity. For example, when the load of the distribution cabinet increases, in order to avoid overheating of the equipment, the upper temperature limit will be appropriately lowered, and the upper humidity limit will be adjusted to a level to prevent condensation. Combined with the current electrical load status of the distribution cabinet, the module dynamically adjusts the control range of temperature and humidity. For example, when the load is high, the lower limit of the temperature control range will be lowered to reduce the risk of overheating, and the upper humidity control limit will be slightly increased to prevent static electricity from being generated in the equipment due to excessive dryness.

[0036] The module sets different levels of control targets according to different temperature and humidity requirements, including: Basic goal: Maintain the temperature and humidity inside the distribution cabinet within a safe range.

[0037] Optimization goal: further optimize temperature and humidity, extend equipment life, and reduce energy consumption.

[0038] Extreme target: Under extreme load or abnormal conditions, ensure that the temperature and humidity do not exceed the equipment's extreme tolerance range.

[0039] Based on the temperature and humidity control target range, an immune optimization algorithm is used to generate an optimal temperature and humidity control strategy; It should be noted that the immune optimization algorithm is used to generate the optimal temperature and humidity control strategy according to the control target range. The immune optimization algorithm simulates the biological immune system and continuously optimizes the control strategy through operations such as antibody selection, cloning and mutation. The fitness function of the algorithm considers multiple factors, including temperature, humidity, energy consumption and equipment status. The algorithm will give priority to the strategy combination with the best control effect and the lowest energy consumption. During the iterative process of the immune optimization algorithm, a variety of control strategies are generated by dynamically adjusting the start and stop combination of temperature and humidity equipment, and the optimal strategy is selected through fitness evaluation. For example, when the current temperature is high, the cooling fan is turned on first; when the humidity is high, the dehumidification equipment is started.

[0040] The temperature and humidity control strategy is converted into control instructions, and combined with an adaptive control algorithm, the control equipment in the power distribution cabinet is dynamically adjusted to achieve precise control of temperature and humidity; It should be noted that the generated optimal control strategy is converted into the start and stop instructions of the equipment. It includes: Heating element control: The command specifically controls the start or stop of the heating element to ensure that the heating equipment starts at low temperatures and stabilizes the temperature.

[0041] Cooling fan control: The command adjusts the on / off state of the cooling fan according to the temperature rise, and starts the fan to cool down when the temperature is high.

[0042] Humidity control device: Instructions to control the evaporation or moisture absorption state of the humidity regulating device according to the humidity level, such as increasing evaporation when the humidity is too low and starting moisture absorption when the humidity is too high.

[0043] Combined with the adaptive control algorithm, the state of the control device is dynamically adjusted according to the real-time changes of the environment and the device. For example, when the ambient temperature fluctuates greatly, the adaptive algorithm will speed up the response speed of the control device to ensure that the temperature and humidity are maintained within the set range.

[0044] The control effect is continuously monitored through a feedback mechanism, and the immune memory is enhanced based on real-time and historical data to adjust the temperature and humidity control strategies.

[0045] Furthermore, the formula of the immune optimization algorithm is as follows:

[0046] in, represents the optimal temperature and humidity control strategy, including the temperature and humidity control effect, energy consumption, and the degree of satisfaction of the constraint conditions; n represents the number of control targets; The weight coefficient representing the control target is set according to the importance of different environmental parameters to determine the impact of each parameter (such as temperature or humidity) in the overall control strategy. For example, the weights of temperature and humidity may be high because they directly affect the safety of the device; Represents the actual control effect value of control target i, based on the data collected by the environmental parameter acquisition module and the environmental trend result generated by the time convolutional neural network analysis. For example, the control effect of temperature and humidity can be measured according to the optimal control range it achieves; It represents the energy consumption weight factor, which balances the system energy consumption and the control effect to avoid excessive consumption. This parameter is used in the energy recovery optimization module to dynamically optimize the energy consumption and appropriately recover heat energy through the genetic algorithm. E represents the system energy consumption value, including the energy consumption during the operation of the temperature and humidity control module. Represents the penalty coefficient of the constraint condition, which is used to control the penalty intensity when the constraint condition is not met. This parameter affects the impact of the constraint condition on fitness. For example, when the environmental parameters are abnormal, the system needs to punish these fluctuations to ensure the stability of the system; m represents the number of constraints, including the threshold of the environmental parameters of the distribution cabinet; Indicates the degree of deviation of the current strategy from the constraints; Indicates the maximum allowable deviation value for each constraint.

[0047] The energy consumption recovery optimization module is used to dynamically optimize the energy consumption of the system by using an energy consumption optimization algorithm based on a genetic algorithm, and to recover and reuse the excess heat and electrical energy generated in the system through an energy recovery mechanism; Wherein, the energy consumption recovery optimization module includes an energy consumption optimization unit and an energy recovery and utilization unit; The energy consumption optimization unit is used to dynamically optimize the energy consumption of the system through a genetic algorithm, comprehensively analyze the real-time load and temperature and humidity requirements of the distribution cabinet, and optimize the energy consumption distribution; The energy recovery unit is used to convert thermal energy into electrical energy for system self-powering by utilizing waste heat and ambient humidity during system operation through an integrated thermoelectric conversion and condensed water collection mechanism, and to use the recovered water for environmental cooling storage.

[0048] It should be noted that during the operation of the system, excess heat generated by cooling equipment, transformers and other components is collected through heat exchangers. The collected heat is input into the thermoelectric converter to convert thermal energy into electrical energy. The thermoelectric converter generates current through temperature difference, and the generated electrical energy is directly used to power some control modules and sensors to achieve the self-powered demand of the system and reduce dependence on external power supply.

[0049] When the ambient humidity is high, the condensed water collection device will collect the moisture in the system cooling process to prevent excessive humidity from entering the system. The collected condensed water is directed to the temperature and humidity control module to assist in cooling or increasing humidity. Especially in the case of high temperature or low humidity, the condensed water can absorb heat through evaporation, reduce the internal temperature of the system, or be used to increase humidity to prevent static electricity.

[0050] The energy recovery optimization module continuously monitors the current energy consumption and recovery effect, and feeds back real-time data to the energy optimization unit. For example, if the thermoelectric conversion efficiency decreases, the system will appropriately increase the proportion of electricity distribution to avoid power shortages. Combined with the real-time monitored energy consumption and temperature and humidity demand data, the energy optimization unit will adjust the parameters of the genetic algorithm according to the actual effect, such as increasing the weight coefficients of load and temperature and humidity requirements in the fitness function, so that the algorithm can adaptively adjust when actual demand changes.

[0051] The operation process of the energy consumption optimization unit includes the following steps: Receive real-time load data, temperature and humidity requirements, and current environmental parameters from the power distribution cabinet, and make a preliminary assessment of energy consumption requirements; An energy consumption optimization model is built based on a genetic algorithm, and a fitness function is set. The system energy consumption and operating efficiency are taken as optimization targets, and the weight coefficients of temperature and humidity requirements and load fluctuations are considered to generate the initial population. Specifically, an energy consumption optimization model is established based on a genetic algorithm. First, an initial population containing multiple energy consumption allocation schemes is generated, and each individual represents an energy consumption allocation combination (such as the start-stop combination of cooling fans, heating elements, and humidity control devices and their respective power allocations). The fitness function is designed with the optimization goals of minimizing the total energy consumption of the system and maximizing the operating efficiency. The fitness function not only considers the total energy consumption, but also the following weight coefficients: ensuring that the allocated energy consumption can meet the set temperature and humidity control requirements to prevent overcooling or overheating. When the load fluctuates greatly, the weight of the cooling demand is appropriately increased to cope with the increase in heat caused by excessive load.

[0052] Use genetic operations such as crossover and mutation to iteratively update the population, optimize the energy consumption allocation plan of each generation of individuals, and select the energy consumption allocation plan with the highest energy efficiency; Specifically, individuals with higher fitness are selected from the population for crossover to generate a new generation of individuals. The crossover operation combines the energy allocation schemes of the parent individuals to generate new combinations, thereby enhancing population diversity and improving the search space. Some individuals are randomly selected for mutation to explore new energy allocation combinations. The mutation operation can change the power distribution of the cooling fan, adjust the working time of the heating element, or the operating mode of the humidity control device to achieve a better energy allocation effect. The fitness of each generation of individuals is recalculated, and individuals with high fitness are selected as the population basis of the next generation, and unfit individuals are eliminated. Through multiple iterative updates, the allocation scheme with the lowest energy consumption and the highest efficiency is gradually screened out.

[0053] Output the optimal energy consumption allocation plan and convert it into control instructions for execution.

[0054] The monitoring alarm module is used to monitor real-time data fluctuations based on preset environmental parameter thresholds and real-time monitoring data, using a Bayesian network anomaly detection algorithm combined with an adaptive sliding window mechanism. When environmental parameters fluctuate abnormally or exceed a safety threshold, an alarm signal is triggered and maintenance personnel are notified. The adaptive sliding window mechanism specifically analyzes the volatility of the data, adaptively adjusts the sliding window size according to the size of the volatility, and performs statistical analysis on the monitoring data within the range of the sliding window to determine whether there is an abnormal situation. If the monitoring data exceeds the preset threshold, an alarm is triggered in time and the abnormal data is recorded.

[0055] It should be noted that the system will pre-set safety thresholds for parameters such as temperature, humidity, voltage, and current based on the design requirements and working environment of the power distribution cabinet equipment. For example, the safety range of temperature may be set to 0°C-50°C, and the range of humidity may be set to 30%-70%. During operation, the module compares the real-time collected data with the preset threshold to quickly identify whether there is a situation that exceeds the safety range. If the monitoring data approaches or exceeds the threshold, the system will respond in a graded manner according to the degree of excess. For example, a slight excess of the threshold triggers a level 1 alarm, and a severe excess triggers a level 2 or level 3 alarm, so that maintenance personnel can allocate resources reasonably.

[0056] Using Bayesian networks to model the correlation between different environmental parameters (such as temperature, humidity, voltage, etc.) can identify potential anomalies beyond conventional thresholds. For example, if the temperature and humidity are detected to increase at the same time, but the current decreases, the system will infer possible risks (such as cooling system failure). Bayesian networks can dynamically adjust the sensitivity of anomaly detection based on historical data and real-time data. It will increase detection sensitivity when the parameters fluctuate greatly and enhance the ability to capture abnormal situations. By analyzing the fluctuation pattern of historical data, possible abnormal events can be predicted. For example, the changing trends of voltage, current and temperature can be used to predict whether equipment overload or short circuit will occur.

[0057] The sliding window mechanism is a method of analyzing data in segments. It determines whether an abnormality occurs by analyzing data fluctuations within a dynamically adjusted window range: When the parameter fluctuation is large (for example, a sharp rise in temperature), the sliding window will automatically shrink to capture every subtle fluctuation and ensure that the abnormality is quickly identified. When the environmental parameters are relatively stable, the sliding window will increase to reduce false alarms triggered by data noise. The collected data is statistically analyzed within the sliding window range, and the mean, variance and other indicators of the fluctuation are calculated to determine whether the fluctuation is abnormal. For example, if the temperature and humidity data show an abnormal upward trend continuously within the sliding window, it may indicate that the environmental control system is abnormal. When judging the data for abnormality within the sliding window, the module will comprehensively evaluate the threshold and volatility to determine whether there is an abnormal situation. For example, if the temperature data in the sliding window approaches or exceeds the threshold multiple times, it will be judged as abnormal and trigger an alarm.

[0058] When the system detects that environmental parameters exceed the threshold or fluctuate abnormally, the module will trigger an alarm signal in time according to the alarm level, including the following: Sound alarm: The buzzer installed inside the system sounds to alert nearby people.

[0059] Light Warning: The indicator light mounted on the outside of the switchboard flashes to provide a visual reminder.

[0060] Remote notification: The system pushes alarm information to the maintenance personnel's equipment in real time through SMS, email, mobile applications, etc., ensuring that remote monitoring personnel can also obtain abnormal information in time.

[0061] Alarm information recording: Detailed information of each alarm event, including alarm time, alarm level, parameter value, etc., will be recorded in the system log for subsequent analysis and maintenance. The system will automatically generate an alarm report to help maintenance personnel analyze the cause and frequency of the alarm and formulate further improvement measures.

[0062] In summary, the present invention monitors temperature, humidity, voltage, current and other parameters in real time through various sensors of the environmental parameter acquisition module, and realizes efficient abnormality detection and alarm through the Bayesian network and adaptive sliding window mechanism, ensuring the timely response of the distribution cabinet under abnormal conditions, thereby reducing the failure rate. By using optimization algorithms and adaptive control algorithms, the temperature and humidity control targets are dynamically adjusted according to real-time analysis reports, the temperature and humidity in the distribution cabinet are accurately controlled, the equipment life is extended, and the equipment energy consumption is reduced. At the same time, the optimal control strategy is generated through the immune optimization algorithm to effectively avoid excessive energy consumption in temperature and humidity control.

[0063] The data analysis and processing module of the present invention uses a time convolutional neural network (TCN) to analyze the time series of environmental parameters such as temperature, humidity, and voltage. It can accurately capture short-term fluctuations and long-term trends, predict future environmental changes by combining historical data with real-time trends, and warn of possible abnormal fluctuations in advance, helping maintenance personnel optimize maintenance strategies. The energy distribution is dynamically optimized by the genetic algorithm in the energy recovery optimization module, and the excess heat is converted into electrical energy using a thermoelectric conversion device to achieve self-power supply of the system. In addition, by collecting and reusing condensed water, the environmental humidity is reduced while also reducing dependence on external energy. The monitoring and alarm module implements comprehensive alarms through sound, light, and remote notifications, notifies maintenance personnel in a timely manner, and can be processed according to the alarm level, thereby improving the efficiency and safety of equipment maintenance.

[0064] The above implementation modes are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary engineering and technical personnel in the field shall fall within the protection scope determined by the claims of the present invention.

Claims

1. An intelligent temperature and humidity control system for a power distribution cabinet, characterized in that: It includes an environmental parameter acquisition module, a data analysis and processing module, a temperature and humidity control module, an energy recovery optimization module and a monitoring and alarm module which are sequentially connected in communication; The environmental parameter acquisition module is used to collect environmental parameters of the power distribution cabinet through a sensor network, and the environmental parameters include temperature, humidity, voltage, current, air pressure, air quality and dust of the power distribution cabinet; The data analysis and processing module is used to analyze the environmental change trend based on the environmental parameters using a time convolutional neural network algorithm and generate an analysis report; The temperature and humidity control module is used to generate an optimal temperature and humidity control strategy based on the analysis report using an optimization algorithm, and convert it into a control instruction, and perform temperature and humidity control on the power distribution cabinet in combination with an adaptive control algorithm; The energy consumption recovery optimization module is used to dynamically optimize the energy consumption of the system by using an energy consumption optimization algorithm based on a genetic algorithm, and to recover and reuse the excess heat and electrical energy generated in the system through an energy recovery mechanism; The monitoring and alarm module is used to monitor real-time data fluctuations based on preset environmental parameter thresholds and real-time monitoring data, using a Bayesian network anomaly detection algorithm combined with an adaptive sliding window mechanism. When environmental parameters fluctuate abnormally or exceed safety thresholds, an alarm signal is triggered and maintenance personnel are notified; The operation process of the temperature and humidity control module includes the following steps: Receive the analysis report, obtain the generated environmental change trend, calculate the optimal control range of real-time temperature and humidity, dynamically match the current load characteristics of the distribution cabinet, and set hierarchical control targets; Based on the temperature and humidity control target range, an immune optimization algorithm is used to generate an optimal temperature and humidity control strategy; The temperature and humidity control strategy is converted into control instructions, and combined with an adaptive control algorithm, the control equipment in the power distribution cabinet is dynamically adjusted to achieve precise control of temperature and humidity; Continuously monitor the control effect through the feedback mechanism, enhance immune memory based on real-time and historical data, and adjust the temperature and humidity control strategy; The formula of the immune optimization algorithm is as follows: ； in, represents the optimal temperature and humidity control strategy; n represents the number of control targets; Represents the weight coefficient of the control target; Represents the actual control effect value of regulation target i; Represents the energy consumption weight factor, balancing the system energy consumption and regulation effect; E represents the system energy consumption value, including the energy consumption when the temperature and humidity control module is running; represents the penalty coefficient of the constraint condition; m represents the number of constraints, including the threshold of the environmental parameters of the power distribution cabinet; Indicates the degree of deviation of the current strategy from the constraints; Indicates the maximum allowable deviation value for each constraint.

2. The intelligent temperature and humidity control system for a power distribution cabinet according to claim 1, characterized in that: The operation process of the data analysis and processing module includes the following steps: Receiving the environmental parameters and performing preprocessing, including removing noise, screening outliers and signal smoothing; The preprocessed environmental parameters are input into the time convolutional neural network model in time series, and the changing characteristics of environmental parameters in different periods are extracted through the multi-layer convolution of the model. The analysis accuracy of environmental trend changes is enhanced according to the convolution kernel adaptive adjustment mechanism. Based on the output of the temporal convolutional neural network model, the correlation between various environmental parameters is deeply mined to identify the potential correlation between temperature, humidity and electrical load and environmental abnormal conditions; Combine historical data and trend analysis results to predict environmental changes in the future, issue early warnings for abnormal fluctuation risks, and generate detailed analysis reports.

3. The intelligent temperature and humidity control system for a power distribution cabinet according to claim 2, characterized in that: The formula of the temporal convolutional neural network model is as follows: ； in, represents the future predicted value of the environmental parameters of the power distribution cabinet; L represents the number of layers of the convolutional network, and the characteristics of the environmental parameters are extracted more deeply through the multi-layer convolution structure; f represents the activation function; K represents the time convolution window size, that is, the number of historical time steps considered at each moment; N represents the number of input environmental parameters; Indicates the weight distribution of different layers at different times and in different environmental parameters; represents the input value of the jth environmental parameter at the l-1th layer at time tk; represents the bias term of the lth layer; represents the residual connection term, is the residual coefficient, Represents a collection of raw input environment parameters.

4. The intelligent temperature and humidity control system for a power distribution cabinet according to claim 1, characterized in that: The temperature and humidity control module includes a plurality of heating elements and cooling fans, which are started and stopped according to the control instructions. It also includes a humidity control device, which adjusts the humidity in the distribution cabinet by evaporation or moisture absorption.

5. The intelligent temperature and humidity control system for a power distribution cabinet according to claim 1, characterized in that: The energy consumption recovery optimization module includes an energy consumption optimization unit and an energy recovery and utilization unit; The energy consumption optimization unit is used to dynamically optimize the energy consumption of the system through a genetic algorithm, comprehensively analyze the real-time load and temperature and humidity requirements of the distribution cabinet, and optimize the energy consumption distribution; The energy recovery unit is used to convert thermal energy into electrical energy for system self-powering by utilizing waste heat and ambient humidity during system operation through an integrated thermoelectric conversion and condensed water collection mechanism, and to use the recovered water for environmental cooling storage.

6. The intelligent temperature and humidity control system for a power distribution cabinet according to claim 5, characterized in that: The operation process of the energy consumption optimization unit includes the following steps: Receive real-time load data, temperature and humidity requirements, and current environmental parameters from the power distribution cabinet, and make a preliminary assessment of energy consumption requirements; An energy consumption optimization model is built based on a genetic algorithm, and a fitness function is set. The system energy consumption and operating efficiency are taken as optimization targets, and the weight coefficients of temperature and humidity requirements and load fluctuations are considered to generate the initial population. Use genetic operations such as crossover and mutation to iteratively update the population, optimize the energy consumption allocation plan of each generation of individuals, and select the energy consumption allocation plan with the highest energy efficiency; Output the optimal energy consumption allocation plan and convert it into control instructions for execution.

7. The intelligent temperature and humidity control system for a power distribution cabinet according to claim 1, characterized in that: The adaptive sliding window mechanism specifically analyzes the volatility of the data, adaptively adjusts the sliding window size according to the size of the volatility, and performs statistical analysis on the monitoring data within the range of the sliding window to determine whether there are any abnormal conditions. If the monitoring data exceeds a preset threshold, an alarm is triggered in a timely manner and the abnormal data is recorded.

Images