Neural fuzzy control-based automatic heat dissipation system for high-voltage and low-voltage distribution room
By constructing a monitoring network and a correlation network, the temperature changes in the power distribution room are simulated, thermal risks are predicted in real time, and heat dissipation strategies are formulated. This solves the problem of response lag in traditional temperature control systems and improves the safety and efficiency of the power distribution room.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-11
- Publication Date
- 2026-04-10
AI Technical Summary
Traditional temperature control systems cannot provide early warnings or interventions when the temperature rises rapidly but has not yet exceeded the limit, and lack predictive maintenance, leading to equipment overheating and potential failure risks.
An automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control is constructed. Through monitoring networks, propagation space and correlation networks, temperature changes are simulated, environmental and equipment parameters are collected in real time, thermal risks are predicted, and heat dissipation strategies are formulated for early warning and cooling.
Identifying potential risks before temperatures reach dangerous thresholds, issuing early warnings and initiating heat dissipation can improve the operational safety of power distribution rooms, prevent performance degradation and malfunctions caused by equipment overheating, and reduce sharp increases in energy consumption and equipment impact.
Smart Images
Figure CN121840416A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of heat dissipation technology for power distribution rooms, specifically an automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control. Background Technology
[0002] With the rapid development of IoT and smart grid technologies, higher demands are being placed on the real-time monitoring and intelligent management of power distribution room operation. Equipment within a power distribution room generates a significant amount of heat during operation. If this heat cannot be dissipated in time, it can lead to localized overheating, accelerated insulation aging, and even equipment failure or fire, posing a serious threat to the stable operation of the power system. Traditional temperature control systems typically only activate cooling devices when the temperature at the monitoring point exceeds a fixed threshold. This approach is slow and cannot provide early warnings or interventions during periods of rapid temperature rise before exceeding the limit, lacking predictive maintenance capabilities.
[0003] To address these issues, we propose an automatic cooling system for high and low voltage power distribution rooms based on neuro-fuzzy control. Summary of the Invention
[0004] The purpose of this invention is to provide an automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control, so as to solve the problems mentioned in the background art.
[0005] To achieve the above objectives, the present invention provides the following technical solution: an automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control, comprising: The model building module is used to collect data from the power distribution room to build a simulation model. The power distribution room data includes equipment load parameters and environmental parameters. The correlation prediction module is used to collect environmental parameters and equipment load parameters of corresponding monitoring points in the power distribution room in real time based on the simulation model to determine the target pheromone. Based on a single monitoring point and its corresponding propagation space, multiple target pheromones are correlated to obtain a correlation network. The heat dissipation control module uses a network to generate control information for the heat dissipation mechanism on the power distribution room. This control information includes the heat dissipation direction, target heat dissipation power, and heat dissipation location.
[0006] Preferably, the model building module includes: The data acquisition unit is used to obtain the physical structure parameters, equipment layout parameters, and equipment load parameters of the power distribution room. The building unit is used to construct a 3D simulation model based on physical structure parameters, equipment layout parameters, and equipment load parameters.
[0007] Preferably, the association prediction module includes: The building unit is used to deploy monitoring points based on multiple temperature sensors in the power distribution room, and to connect multiple monitoring points to form a monitoring network; The unit sets up a propagation space for each monitoring point. The propagation space includes a release point, an induction coil, and a propagation channel. The release point stores multiple pheromones. The determination unit is used to propagate pheromones in the propagation space based on the simulation model and the collected parameters, and to determine the target pheromone at each monitoring point based on the induction coil corresponding to each monitoring point. The association unit is used to associate multiple target pheromones based on a single monitoring point and its corresponding propagation space, thus obtaining an association network.
[0008] Preferably, the step of setting up a propagation space at the corresponding monitoring point, wherein the propagation space includes a release point, an induction coil, and a propagation channel, and the release point stores multiple pheromones includes: Release points are set up for each monitoring point, whereby the release points are used to store and manage multiple pheromones; Multiple sensing points are set up in a ring shape for each monitoring point, and the multiple sensing points are connected in sequence to form a sensing coil. Starting from a monitoring point and ending at an adjacent monitoring point, multiple curved propagation channels are set between the starting and ending points. The number of curved propagation channels corresponds to the distribution density of pheromones and is placed in the propagation space to obtain the propagation channels. The propagation space is formed by combining the propagation channel connected to the release point and the induction coil located at the monitoring point corresponding to the release point.
[0009] Preferably, the step of propagating pheromones in the propagation space based on the simulation model and collected parameters, and determining the target pheromone at each monitoring point based on the induction coil corresponding to each monitoring point, includes: The environmental parameters and equipment load parameters of the power distribution room collected in real time are input into the simulation model to generate pheromones and then placed in the propagation space of the corresponding monitoring points. The pheromone is made to enter multiple curved propagation channels from the release point, and the pheromone diffuses along the propagation channels toward adjacent monitoring points. The number of propagation channels dynamically changes in relation to the pheromone distribution density. Based on the temperature of the pheromone sensed by the induction coil at each monitoring point, the target pheromone corresponding to the monitoring point is determined from all pheromones.
[0010] Preferably, the step of inputting the real-time collected environmental parameters and equipment load parameters of the power distribution room into the simulation model to generate pheromones and placing them in the propagation space of the corresponding monitoring points includes: The initial temperature value of the pheromone to be generated is determined based on the simulation model; the load trend is predicted based on the dynamic change pattern of the equipment load parameters, and the initial release rate and initial concentration of the pheromone to be generated are determined. Create a unique data structure for each pheromone; assign initial temperature and initial concentration to the newly generated pheromone. The newly generated pheromones are placed in the release point of the corresponding monitoring point's propagation space and enter the state of waiting to be propagated.
[0011] Preferably, the step of determining the target pheromone corresponding to a monitoring point from all pheromones based on the temperature of the pheromone sensed by the induction coil corresponding to each monitoring point includes: The temperature values of pheromones sensed by each sensing point on the induction coil are acquired in real time. Based on preset filtering rules, target pheromones are selected from multiple pheromones sensed by the sensing point. The preset filtering rule is: select pheromones sensed at the sensing point whose estimated time to reach the cooling set value is shorter than a preset time as target pheromones.
[0012] Preferably, the heat dissipation control module includes: The strategy formulation unit is used to determine the monitoring points corresponding to each target pheromone based on the association network, activate the corresponding heat dissipation mechanism based on the location information of each monitoring point, formulate the heat dissipation power of the heat dissipation mechanism based on the difference between the target pheromone data and the preset temperature value, and correct the heat dissipation power based on the rate of change of the target pheromone data to obtain the target heat dissipation power. The orientation of the sensing coil where the target pheromone is located is used as the heat dissipation direction, the monitoring point corresponding to the sensing coil where the target pheromone is located is used as the heat dissipation position, and the heat dissipation direction, target heat dissipation power, and heat dissipation position are used as control information. The heat dissipation control unit is used to control the heat dissipation mechanism to dissipate heat from the power distribution room based on control information.
[0013] Compared with the prior art, the beneficial effects of the present invention are: By constructing a monitoring network, a propagation space, and a correlation network, isolated monitoring point data is transformed into a dynamic thermal risk correlation network. This network can pinpoint hotspots and more clearly and intuitively reveal the source of thermal risks, the direction of propagation, and the logical relationships between different risk points. By setting pheromones to simulate temperature changes in the power distribution room, and based on the rate of temperature change of the pheromones and the estimated time to reach the critical temperature, abnormal temperature change trends can be captured. This allows potential risks to be identified before the temperature actually reaches the dangerous threshold, and early warnings can be issued and heat dissipation can be initiated, improving the safety of power distribution room operation and preventing performance degradation and failure risks caused by equipment overheating. Attached Figure Description
[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0015] Figure 1 This is a system structure block diagram of the present invention; Figure 2 This is a schematic diagram of the propagation space of the present invention. Detailed Implementation
[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example
[0017] Please see Figures 1 to 2 This invention provides a technical solution for an automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control: an automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control, comprising: The model building module is used to collect data from the power distribution room to build a simulation model. The power distribution room data includes equipment load parameters and environmental parameters. The model building module includes: an acquisition unit, used to acquire the physical structure parameters, equipment layout parameters, and equipment load parameters of the power distribution room; and a construction unit, used to construct a 3D simulation model based on the physical structure parameters, equipment layout parameters, and equipment load parameters. Specifically, based on the physical structural parameters, equipment layout, and nominal heat generation power of the power distribution room, the physical structural parameters include spatial dimensions, wall material and thermal resistance, and the location and size of ventilation openings; the equipment load parameters include current, voltage, and power factor; and the environmental parameters include at least temperature and airflow velocity; the equipment layout includes the spatial locations of transformers, switch cabinets, and cable trays. A geometric and physical three-dimensional model of the power distribution room is created in a virtual space, and a communication connection is established with the data acquisition module to acquire the load information of high and low voltage equipment and the environmental parameters of each monitoring point in real time, and upload them to the simulation model through the communication connection. Driven by the real-time data, the simulation model dynamically calculates the temperature field distribution of the entire power distribution room over a period of time in the future, thereby enabling advance cooling preparations for the locations corresponding to the required monitoring points based on the temperature field distribution, preventing cooling from only starting when the temperature reaches the set value, improving heat dissipation efficiency, and reducing the impact of temperature changes on the equipment. The correlation prediction module is used to collect environmental parameters and equipment load parameters of corresponding monitoring points in the power distribution room in real time based on the simulation model to determine the target pheromone. Based on a single monitoring point and its corresponding propagation space, multiple target pheromones are correlated to obtain a correlation network. The correlation prediction module includes: a construction unit, used to deploy monitoring points based on multiple temperature sensors in the power distribution room, and connect the multiple monitoring points to form a monitoring network; a setting unit, used to set up propagation spaces for each monitoring point, wherein the propagation space includes a release point, an induction coil, and a propagation channel, and the release point stores multiple pheromones; a determination unit, used to propagate the pheromones in the propagation space based on the simulation model and the collected parameters, and determine the target pheromones corresponding to each monitoring point based on the induction coils corresponding to each monitoring point; and a correlation unit, used to correlate multiple target pheromones based on a single monitoring point and its corresponding propagation space to form a correlation network. The steps of setting up a propagation space corresponding to a monitoring point, wherein the propagation space includes a release point, an induction coil, and a propagation channel, and the release point stores multiple pheromones, include: setting up a release point corresponding to the monitoring point, wherein the release point is used to store and manage multiple pheromones; setting up multiple induction points arranged in a ring corresponding to the monitoring point, and connecting the multiple induction points sequentially to form an induction coil; setting up multiple curved propagation channels between the starting point and the ending point, with the number of curved propagation channels varying according to the pheromone distribution density (the variation in the number of propagation channels here is used to increase or decrease the number of curved propagation channels according to the pheromone distribution density; when some propagation channels are added, the pheromone distribution density will increase, and vice versa, thereby setting the corresponding propagation channels according to the pheromone data to adapt to the pheromone distribution density); and combining the propagation channels connected to the release point and the induction coil located on the monitoring point corresponding to the release point to form the propagation space. Specifically, the sensing point is located between two monitoring points, and each monitoring point has a sensing coil used to sense pheromones released by the corresponding release points of other monitoring points. Areas with high pheromone density correspond to narrowing the distance between adjacent propagation channels; areas with low pheromone density correspond to increasing the distance between adjacent propagation channels. The release point is located at the corresponding monitoring point, which is the geometric center of the sensing coil and is a logical unit responsible for the generation, storage, concentration updating, and elimination management of pheromones. The sensing coil is a ring-shaped sensing area, with multiple sensing points set around the monitoring point at a preset radius, and the sensing points are uniformly or non-uniformly distributed in a ring. Subsequently, these sensing points are connected sequentially by curves to form a closed ring structure, i.e., the sensing coil. The detection loop is used to detect pheromone signals passing through or arriving at the loop. Each detection loop automatically carries a critical temperature setpoint for its corresponding monitoring point. The heat dissipation power is adjusted based on the difference between the critical temperature setpoint and the temperature corresponding to the pheromone detected by the target detection point. The target detection point is selected from multiple detection points, with the detection point corresponding to the temperature of the pheromone with the smallest difference being chosen as the target detection point. The propagation channel is a curved path, such as an arc, S-shape, or a probabilistic random path, to simulate non-linear propagation in a real environment. Between the starting and ending points, there is not only a single propagation channel, but multiple parallel propagation channels. The spacing (i.e., distribution density) between these channels is not fixed but scaled according to the pheromone distribution density. Specifically, in areas with high pheromone concentration, the channel spacing is small and the distribution is dense; in areas with low pheromone concentration, the channel spacing is large and the distribution is sparse. A set of propagation channels, after scaling, together constitute the propagation channel connecting two monitoring points and are placed within the propagation space. The propagation space is a virtual space surrounding the monitoring point, used to realize the storage, sensing, and propagation of pheromones. By moving and propagating pheromones within it, the process of heat propagation from the heat source collected by the sensor corresponding to the monitoring point can be simulated. Based on the propagation distribution of pheromones, the heat source generated by the monitoring point can be monitored in real time, thereby predicting which monitoring points will subsequently exceed the preset temperature due to the heat source corresponding to the monitoring point. This allows for advance cooling of other affected monitoring points, improving the coordination of heat dissipation in the power distribution room. When all pheromone data in an induction loop do not meet the screening conditions, it indicates that there is no target pheromone in the induction loop corresponding to the monitoring point under the current circumstances.
[0018] Based on the simulation model and collected parameters, the pheromone is propagated in the propagation space. The steps for determining the target pheromone at each monitoring point based on the induction coil corresponding to each monitoring point include: inputting the environmental parameters and equipment load parameters of the power distribution room collected in real time into the simulation model to generate pheromones and placing them in the propagation space of the corresponding monitoring point; allowing the pheromone to enter multiple curved propagation channels from the release point, and the pheromone diffuses along the propagation channels towards adjacent monitoring points, wherein the number of propagation channels dynamically changes according to the distribution density of the pheromone; and determining the target pheromone at the monitoring point from all pheromones based on the temperature of the pheromone sensed by the induction coil corresponding to each monitoring point (here, the temperature of the pheromone refers to the initial temperature of the pheromone released from the release point corresponding to the target monitoring point).
[0019] The steps of inputting real-time collected environmental parameters and equipment load parameters of the power distribution room into the simulation model to generate pheromones and placing them in the propagation space of the corresponding monitoring points include: determining the initial temperature value of the pheromone to be generated based on the simulation model; predicting the load trend based on the dynamic change pattern of the equipment load parameters, and determining the initial release rate and initial concentration of the pheromone to be generated; creating a unique data structure for each pheromone; assigning the initial temperature and initial concentration to the newly generated pheromone; and placing the newly generated pheromone in the release point of the propagation space of the corresponding monitoring point to enter the propagation state. Specifically, the simulation model calculates the theoretical heat load of the corresponding monitoring point based on the equipment load parameters; dynamically determines the initial temperature value of the pheromone to be generated based on the difference between the theoretical heat load and the measured environmental parameters; predicts the load trend in the short term based on the dynamic change pattern of the equipment load parameters; determines the initial release rate and initial concentration of the pheromone to be generated based on the predicted load trend; creates a unique data structure for each pheromone, which includes at least the following fields: pheromone ID, source monitoring point ID, temperature value, concentration value, and generation timestamp; assigns the initial temperature and initial concentration contained in the pheromone configuration instruction to the newly generated pheromone; and places the newly generated pheromone in the release point of the corresponding monitoring point's propagation space, entering the propagation state.
[0020] Specifically, a pheromone is a virtual data entity that moves within a propagation space. It includes a temperature field that simulates heat values. This temperature field is dynamically updated during propagation according to rules simulating physical attenuation, accurately simulating the spatial propagation and distribution dynamics of heat within a power distribution room. The pheromone propagates to the current monitoring point via a propagation channel. The current monitoring point and the target monitoring point are adjacent. Since the target monitoring point's temperature will flow within the propagation space when heat dissipation is required, the flow of the pheromone simulates the actual temperature flow within the power distribution room, thus allowing the determination of the actual temperature. Regarding the propagation of pheromones, when a pheromone moves to the sensing coil corresponding to the current monitoring point, there will be pheromones from multiple directions on the sensing coil. Since temperature also propagates arbitrarily from multiple directions, this increases the accuracy of temperature propagation simulation. When the temperature of the sensor corresponding to the monitoring point exceeds the preset threshold and needs to be cooled down, the monitoring point at this time is equivalent to a heat source. It will continuously generate and release a large amount of pheromones through the release point. Each pheromone represents a small part of "virtual heat" emitted from the heat source. The heat will attenuate with distance and medium during the transmission process. The farther away from the heat source, the lower the temperature felt. Each pheromone has a "temperature" field.This value is not fixed. At the release point, its temperature equals the current temperature at the monitoring point. As it moves along the "propagation channel," its temperature gradually decreases according to a preset model (e.g., the temperature decreases by 0.1℃ for every unit distance moved), thus simulating heat dissipation in space. Due to factors such as equipment layout, ventilation, and obstacles in the power distribution room, the speed and intensity of heat transfer vary in different directions. Therefore, a curved propagation channel is used to simulate the diffraction and reflection of heat when it encounters obstacles. Increasing or decreasing the number of propagation channels simulates the distribution density of pheromones corresponding to different temperatures, thereby simulating the heat transfer capacity in different directions. In directions with strong heat transfer capacity... (For example, in the direction of a ventilation duct), the fewer the propagation channels, the more "virtual heat units" (pheromones) are released in that direction, simulating a stronger heat flow. A temperature sensor measures the combined temperature at that point, formed by the superposition of heat from all directions after transmission and attenuation. When these "pheromones" carrying attenuated temperature values arrive at the "sensing coil," they are captured by the sensing points. First, the temperature data of all pheromones sensed by all sensing points on the sensing coil are collected, identifying the pheromone (or several pheromones) with the highest temperature, or the pheromone with the fastest temperature change rate. The estimated time for each pheromone to reach its critical temperature is calculated, and the pheromone with the shortest estimated time is selected as the target. When the temperature corresponding to a target pheromone exceeds a set maximum safety threshold, a cooling command is triggered. Simultaneously, the fan speed or deflector angle in the direction of the target pheromone is adjusted. All sensed temperature data is intelligently analyzed to select the "critical temperature" (i.e., the target pheromone) that best represents the current urgency and risk location. Then, based on these "critical temperatures," a cooling strategy is formulated and executed. Temperature data from multiple pheromones sensed by the induction coils at each monitoring point are collected. Based on a preset urgency assessment model, the temperature data of the multiple pheromones are analyzed in parallel to calculate the urgency quantification value corresponding to each pheromone. Based on the urgency quantification value... Select one or more target pheromones representing the highest urgency and specific risk location from all pheromones; their temperature is the critical temperature. Output the critical temperature and its corresponding risk location information to trigger targeted cooling control. Compare the urgency quantification value of each pheromone with a preset urgency threshold. Select all pheromones whose urgency quantification value exceeds the urgency threshold as target pheromones. Alternatively, sort all pheromones according to their urgency quantification value from high to low. Select the top N pheromones as target pheromones, where N is an integer greater than or equal to 1. The urgency quantification value is the reciprocal of the estimated time required for the pheromone's temperature value to reach the preset critical temperature.
[0021] The step of determining the target pheromone corresponding to a monitoring point from all pheromones based on the temperature of the pheromone sensed by the induction coil corresponding to each monitoring point includes: acquiring the temperature value of the pheromone sensed by each sensing point on the induction coil in real time; and selecting the target pheromone from multiple pheromones sensed by the sensing point based on a preset screening rule, wherein the preset screening rule is: selecting the pheromone sensed at the sensing point whose estimated time to reach the cooling set value is shorter than a preset time as the target pheromone. The heat dissipation control module, based on the associated network, formulates control information for the heat dissipation mechanism on the power distribution room. The control information includes the heat dissipation direction, target heat dissipation power, and heat dissipation location. The heat dissipation control module includes: a strategy formulation unit, used to determine the monitoring points corresponding to each target pheromone based on the correlation network, activate the corresponding heat dissipation mechanism based on the location information of each monitoring point, formulate the heat dissipation power of the heat dissipation mechanism based on the difference between the target pheromone data and the preset temperature value, and correct the heat dissipation power based on the rate of change of the target pheromone data to obtain the target heat dissipation power, taking the orientation of the induction coil where the target pheromone is located as the heat dissipation direction, taking the monitoring point corresponding to the induction coil where the target pheromone is located as the heat dissipation position, and taking the heat dissipation direction, target heat dissipation power, and heat dissipation position as control information; and a heat dissipation control unit, used to control the heat dissipation mechanism to dissipate heat from the power distribution room according to the control information.
[0022] Specifically, the process involves identifying overheat monitoring points that serve as central nodes in the network; determining the physical location of these overheat monitoring points as primary heat dissipation locations; simultaneously, identifying the logical locations corresponding to one or more target pheromone child nodes with the highest edge weight connected to the central node, and determining them as auxiliary heat dissipation locations; determining the basic heat dissipation intensity based on the average temperature value of all target pheromone nodes connected to the central node in the network; calculating an intensity correction coefficient based on the difference between the highest temperature node in the network and the basic heat dissipation intensity; multiplying the basic heat dissipation intensity by the intensity correction coefficient to obtain the final target heat dissipation intensity; continuously monitoring changes in the structure and node attributes of the network; dynamically adjusting the heat dissipation control strategy based on these changes to form a closed-loop control; and generating instructions to reduce the heat dissipation intensity or shut down the heat dissipation mechanism when the temperature values of all target pheromone nodes in the network are below a preset safety threshold and remain stable.
[0023] This invention constructs a simulation model by collecting data from a power distribution room; multiple pheromones are set in the monitoring points and corresponding influence spaces (multiple pheromones are released by heat sources, and the distribution, density, and location information of the pheromones are monitored; the location of the target pheromone is determined based on the pheromone density, etc., and cooling is prepared when the temperature is about to exceed the limit); multiple target pheromones are correlated based on a single heat source to obtain a correlation network; environmental and load information of the corresponding monitoring points are collected in real time, and the target pheromone is determined based on the temperature predicted by the model; according to the correlation network of the target pheromones, a control strategy is formulated for the heat dissipation mechanism, and the heat dissipation mechanism in the corresponding area is activated to prepare for heat dissipation of the corresponding monitoring points in advance; when the corresponding temperature value is about to be reached, cooling preparation is carried out, and a preventive cooling command is generated to curb the expansion of the heat crisis. The temperature field simulation model can dynamically predict the spatial temperature distribution in the power distribution room at a specific time in the future and identify local high temperature points that have not yet formed but are about to form in advance.
[0024] By constructing a monitoring network, propagation space, and correlation network, isolated monitoring point data is transformed into a dynamic thermal risk correlation network. This network can pinpoint hotspots and more clearly and intuitively reveal the source of thermal risks, propagation direction, and logical relationships between different risk points. By setting pheromones to simulate temperature changes in the power distribution room, and based on the pheromone temperature change rate and the estimated time to reach the critical temperature, abnormal temperature change trends can be captured. This allows potential risks to be identified before the temperature actually reaches the dangerous threshold, and early warnings and cooling can be initiated in advance. This improves the safety of power distribution room operation, prevents performance degradation and failure risks caused by equipment overheating, avoids the sharp increase in energy consumption and equipment impact caused by traditional threshold control, and extends equipment lifespan.
[0025] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0026] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. An automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control, characterized in that, include: The model building module is used to collect data from the power distribution room to build a simulation model. The power distribution room data includes equipment load parameters and environmental parameters. The correlation prediction module is used to collect environmental parameters and equipment load parameters of corresponding monitoring points in the power distribution room in real time based on the simulation model to determine the target pheromone. Based on a single monitoring point and its corresponding propagation space, multiple target pheromones are correlated to obtain a correlation network. The heat dissipation control module uses a network to generate control information for the heat dissipation mechanism on the power distribution room. This control information includes the heat dissipation direction, target heat dissipation power, and heat dissipation location.
2. The automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control according to claim 1, characterized in that: The model building module includes: The data acquisition unit is used to obtain the physical structure parameters, equipment layout parameters, and equipment load parameters of the power distribution room. The building unit is used to construct a 3D simulation model based on physical structure parameters, equipment layout parameters, and equipment load parameters.
3. The automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control according to claim 1, characterized in that: The association prediction module includes: The building unit is used to deploy monitoring points based on multiple temperature sensors in the power distribution room, and to connect multiple monitoring points to form a monitoring network; The unit sets up a propagation space for each monitoring point. The propagation space includes a release point, an induction coil, and a propagation channel. The release point stores multiple pheromones. The determination unit is used to propagate pheromones in the propagation space based on the simulation model and the collected parameters, and to determine the target pheromone at each monitoring point based on the induction coil corresponding to each monitoring point. The association unit is used to associate multiple target pheromones based on a single monitoring point and its corresponding propagation space, thus obtaining an association network.
4. The automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control according to claim 3, characterized in that: The step of setting up a propagation space at the corresponding monitoring point, wherein the propagation space includes a release point, an induction coil, and a propagation channel, and the release point stores multiple pheromones includes: Release points are set up for each monitoring point, whereby the release points are used to store and manage multiple pheromones; Multiple sensing points are set up in a ring shape for each monitoring point, and the multiple sensing points are connected in sequence to form a sensing coil. Starting from a monitoring point and ending at an adjacent monitoring point, multiple curved propagation channels are set between the starting and ending points. The number of curved propagation channels corresponds to the distribution density of pheromones and is placed in the propagation space to obtain the propagation channels. The propagation space is formed by combining the propagation channel connected to the release point and the induction coil located at the monitoring point corresponding to the release point.
5. The automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control according to claim 1, characterized in that: The steps of propagating pheromones in the propagation space based on the simulation model and collected parameters, and determining the target pheromone at each monitoring point based on the induction coil corresponding to each monitoring point, include: The environmental parameters and equipment load parameters of the power distribution room collected in real time are input into the simulation model to generate pheromones and then placed in the propagation space of the corresponding monitoring points. The pheromone is made to enter multiple curved propagation channels from the release point, and the pheromone diffuses along the propagation channels toward adjacent monitoring points. The number of propagation channels dynamically changes in relation to the pheromone distribution density. Based on the temperature of the pheromone sensed by the induction coil at each monitoring point, the target pheromone corresponding to the monitoring point is determined from all pheromones.
6. The automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control according to claim 5, characterized in that: The step of inputting the real-time collected environmental parameters and equipment load parameters of the power distribution room into the simulation model to generate pheromones and placing them in the propagation space of the corresponding monitoring points includes: The initial temperature value of the pheromone to be generated is determined based on the simulation model; the load trend is predicted based on the dynamic change pattern of the equipment load parameters, and the initial release rate and initial concentration of the pheromone to be generated are determined. Create a unique data structure for each pheromone; assign initial temperature and initial concentration to the newly generated pheromone. The newly generated pheromones are placed in the release point of the corresponding monitoring point's propagation space and enter the state of waiting to be propagated.
7. The automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control according to claim 1, characterized in that: The step of determining the target pheromone corresponding to a monitoring point from all pheromones based on the temperature of the pheromone sensed by the induction coils corresponding to each monitoring point includes: The temperature values of pheromones sensed by each sensing point on the induction coil are acquired in real time. Based on preset filtering rules, target pheromones are selected from multiple pheromones sensed by the sensing point. The preset filtering rule is: select pheromones sensed at the sensing point whose estimated time to reach the cooling set value is shorter than a preset time as target pheromones.
8. The automatic heat dissipation system for high and low voltage power distribution rooms based on neural fuzzy control according to claim 1, characterized in that: The heat dissipation control module includes: The strategy formulation unit is used to determine the monitoring points corresponding to each target pheromone based on the association network, activate the corresponding heat dissipation mechanism based on the location information of each monitoring point, formulate the heat dissipation power of the heat dissipation mechanism based on the difference between the target pheromone data and the preset temperature value, and correct the heat dissipation power based on the rate of change of the target pheromone data to obtain the target heat dissipation power. The orientation of the sensing coil where the target pheromone is located is used as the heat dissipation direction, the monitoring point corresponding to the sensing coil where the target pheromone is located is used as the heat dissipation position, and the heat dissipation direction, target heat dissipation power, and heat dissipation position are used as control information. The heat dissipation control unit is used to control the heat dissipation mechanism to dissipate heat from the power distribution room based on control information.