Frequency conversion control method and system for noise of exhaust system of transformer substation room based on genetic algorithm

Abstract

The invention provides a variable-frequency control method and system for noise of an exhaust system of a transformer substation room based on a genetic algorithm, and the method comprises the steps: collecting the temperature and noise data of the transformer substation room in real time through a distributed sensor network, and building a multi-target optimization model through the genetic algorithm in combination with a variable-frequency speed regulation technology; and the noise and the temperature are used as constraint conditions to be jointly solved with an optimization target. The genetic algorithm dynamically adjusts the operation frequency of the exhaust fan through the operations of population initialization, fitness evaluation, selection, crossover, variation and the like, so that the requirements of temperature control and noise minimization are balanced. The rotating speed of the exhaust fan can be adjusted in a self-adaptive mode. Compared with a traditional single-machine fixed wind speed or simple linkage control method, the technology can remarkably improve the comprehensive energy efficiency of the system, reduce energy waste and improve the operation environment of the transformer substation room. The technology is suitable for noise and temperature control requirements of various types of indoor transformer substations and similar scenes, and has high applicability and popularization value.

Description

Technical Field

[0001] The invention relates to the technical field of silent exhaust technology for transformer substations, in particular to a frequency conversion control method and system for noise of exhaust systems in transformer substations based on genetic algorithms. Background Art

[0002] In modern power systems, substations are an important part of power transmission and distribution. Ensuring their efficient, stable and safe operation is crucial to the reliability of the power grid. With the continuous increase in power demand, traditional open-air substations have gradually failed to meet the requirements of safety, environmental protection and energy saving, and indoor substations have gradually become the mainstream choice. Although indoor substations can reduce noise and environmental pollution compared to open-air substations, they still face problems such as noise pollution and heat dissipation. The noise pollution of substations mainly comes from transformers and auxiliary equipment, especially the noise of cooling fans and exhaust fans. Due to the limitations of indoor space and the centralized operation of equipment, the impact of noise in indoor substations is more significant. Therefore, solving the noise problem and improving the energy efficiency of the fan system are difficult problems that need to be solved in the current substation design and operation. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a frequency conversion control method and system for the noise of the exhaust system of the substation room based on genetic algorithm, combining low-noise exhaust fan and PID frequency conversion control technology optimized by genetic algorithm to achieve automatic adjustment of fan operating frequency, reduce substation room temperature and noise, and save energy and reduce consumption. The system can not only effectively reduce noise pollution and maintain temperature in the substation, but also achieve energy efficiency optimization and remote monitoring functions.

[0004] To achieve the above object, the present invention adopts the following technical solution: A frequency conversion control method for noise of a substation exhaust system based on a genetic algorithm comprises the following steps:

[0005] Step 1: Arrange multiple noise sensors and temperature sensors in the substation room; the noise sensor is used to monitor the noise level in each area of ​​the substation room in real time, and the average value of the monitoring values ​​of all noise sensors is input into the PLC control module as the comprehensive index of indoor noise; the temperature sensor is used to monitor the temperature inside and outside the substation room, obtain the temperature difference between indoor and outdoor, and input the temperature difference data into the PLC control module as a reference for temperature and noise control;

[0006] Step 2: The PLC control module transmits the collected noise data and temperature data to the host computer through the RS-485 communication protocol; in the host computer, the received data is processed, and the genetic algorithm is introduced to calculate and optimize the data, and the monitored temperature and noise data are displayed in real time in the monitoring interface of the host computer; the genetic algorithm dynamically adjusts the operating frequency of the fan according to the restriction of the current temperature threshold and the change trend of indoor noise and temperature. The goal is to minimize the noise generated by the fan operation while ensuring that the indoor temperature does not exceed the set threshold;

[0007] Step 3: After genetic algorithm calculation, the optimal speed control strategy generated by the host computer will be sent to the PLC control module through the RS-485 communication protocol; the PLC control module converts the speed control signal into a current frequency control signal and transmits it to the inverter of each fan; the inverter adjusts the speed of each fan according to the current frequency control signal to achieve precise control of noise and temperature;

[0008] Step 4: As the ambient temperature and noise change in real time, the PLC control module continuously transmits the latest data to the host computer. When the temperature approaches the temperature threshold, the genetic algorithm recalculates the optimization plan based on the updated data. Through this dynamic adjustment method, the PLC control module and the genetic algorithm work together to ensure that the exhaust fan system always adjusts the fan speed according to the actual conditions inside and outside the station during the entire operation process.

[0009] In a preferred embodiment, the optimization of the temperature data and the noise data by the genetic algorithm specifically includes: the relationship between the indoor temperature and the exhaust fan speed is derived from the heat balance and is expressed as:

[0010]

[0011] There is an approximate logarithmic relationship between noise and exhaust fan speed, expressed as:

[0012] N v =A·lg(n)+B.

[0013] In a preferred embodiment, the optimal speed control strategy specifically includes:

[0014] (1) Initialize the population

[0015] Population representation: Each individual represents a number of fans and the exhaust fan speed n of each fan, which is represented as an n-dimensional array, where q is the number of fans;

[0016] Population size: Select the population size A to represent the current solution space, randomly initialize the n-dimensional array in the population, and ensure that the speed of each wind turbine in the n-dimensional array is within a certain range;

[0017] (2) Fitness function

[0018] When calculating the room temperature under the action of several fans, the room temperature can be calculated by the following formula:

[0019]

[0020] Where: T int is the room temperature under the combined action of all fans, q is the number of fans, n is i , i = 0, 1, 2, q is the speed of each fan, k, ρ air 、v air , A room 、c air , Q heat All are empirical constants;

[0021] When calculating the noise of several fans, the noise level is calculated using the following formula:

[0022]

[0023] Where: N vt is the sum of the noise levels generated by all fans, q is the number of fans, i=0, 1, 2..., q is the noise generated by each fan; combined with the formula of noise and speed of a single fan, it is further rewritten as follows:

[0025]

[0026] Temperature control constraints:

[0027] According to the heat balance model, there is a direct mathematical relationship between the fan speed and the indoor temperature, namely:

[0028]

[0029] Where: T int is the room temperature under the combined action of all fans, q is the number of fans, n is i , i = 0, 1, 2, q is the speed of each fan, k, ρ air 、v air , A room 、c air , Q heat All are empirical constants;

[0030] The fitness function first evaluates whether the indoor temperature exceeds the set threshold under a given fan configuration. If the temperature exceeds the threshold, the fitness value of the solution is zero, indicating that the configuration is invalid; otherwise, the fitness value is adjusted according to the temperature deviation: the smaller the temperature deviation, the higher the fitness value;

[0031] The noise is related to the number of fans started and the speed of each fan. The lower the noise, the higher the adaptability.

[0032]

[0033] Among them: F temp is the fitness value of temperature, T int is room temperature, T th is the set temperature threshold;

[0034] Noise minimization constraints:

[0035] There is the following relationship between noise and fan speed:

[0036]

[0037] Where: N vt is the sum of the noise levels generated by all fans, q is the number of fans, n is i , i=

[0038] 0, 1, 2···, q are the rotation speeds of each fan, and A and B are empirical constants;

[0039] Fitness function F noise It will be adjusted according to the noise level, and the noise fitness function is as follows:

[0040]

[0041] Among them: F noise is the fitness value of the noise, N vt is the sum of the noise levels generated by all fans, and α is an adjustment factor used to control the impact of noise on fitness. If α is large, the penalty of noise will be more significant, and the speed of the fan needs to be controlled as low as possible.

[0042] The fitness function is further designed as follows:

[0043]

[0044] Where: N max is the set noise upper limit, when the noise N vt If this threshold is exceeded, the fitness value will drop rapidly, indicating that the noise of the configuration is seriously exceeded. p is the number of fans, and β is the penalty factor, which is used to adjust the impact of the number of fans on the fitness value. If the number of fans is too large, the β·p term will reduce the fitness value, thus forcing the genetic algorithm to select an appropriate number of fans.

[0045] (3) Select operation

[0046] The selection operation is used to select individuals with higher fitness from the current population as parent individuals; the selection method can be roulette selection or tournament selection, which can select better individuals according to the level of fitness;

[0047] (4) Crossover operation

[0048] The crossover operation is used to exchange the genes of two parent individuals, i.e. the speed values ​​of each wind turbine, to generate new offspring individuals. Common crossover methods include single-point crossover and uniform crossover.

[0049] (5) Mutation Operation

[0050] The mutation operation is used to randomly fine-tune the rotation speed of some individuals to maintain the diversity of the population and prevent falling into the local optimal solution; the amplitude of the mutation is set to a certain range;

[0051] (6) Update population

[0052] After the crossover and mutation operations, a new population is generated; a combination method of retaining the parent and offspring is selected, or individuals with poor fitness are eliminated;

[0053] (7) Termination conditions

[0054] The algorithm is stopped by setting the maximum number of iterations or when the fitness reaches a preset threshold; the optimal solution, i.e., the optimal speed of each exhaust fan, is finally output.

[0055] In a preferred embodiment, assuming steady-state conditions, the relationship between the station room temperature, heat source, and exhaust volume is obtained from the following heat conservation equation:

[0056] Q heat +Q inflow =Q outflow

[0057] Where Q inflow is the heat entering the station building, Q outflow It is the heat discharged by the exhaust fan;

[0058] When air enters a room from the outside, the relationship between the air velocity and the temperature difference between indoor and outdoor is expressed by heat transfer; the heat entering the room Q inflow Mainly determined by the following factors:

[0059] Q inflow =m·c air ΔT

[0060] Where m is the mass flow rate of air in kg / s, which is calculated from the air velocity and room volume:

[0061] m=ρ air ·v air·A room

[0062] Among them A room =L×W is the floor area of ​​the station building;

[0063] The exhaust volume of the exhaust fan is proportional to the rotation speed, so the exhaust volume of an exhaust fan in the station room is

[0064] Q outflow =Q fan = k·n

[0065] Heat removed by exhaust air volume Q outflow Determined by the mass flow rate and temperature difference of the air:

[0066] Q outflow =m·c air ·(T in -T out ).

[0067] In a preferred embodiment, the heat balance is:

[0068] Q heat +m·c air ·ΔT=k·v fan ·c air ·(T in -T out )

[0069] Under steady-state conditions, the indoor temperature T in Determined by the following equation:

[0070] Q heat +ρ air ·v air ·A room ·c air ΔT

[0071] = k·v fan ·ρ air ·v air ·A room ·c air ·(T in -T out )

[0072] Simplifying the related constant terms, we can get the relationship between the exhaust fan speed and the indoor temperature:

[0073]

[0074] When the temperature of the substation room is too high, the PLC controls the fan speed to increase.

[0075] Q heat +Q inflow <Qoutflow

[0076] When the exhaust temperature increases, the indoor temperature will drop, causing ΔT to increase, Q inflow It gets bigger until both sides of the equation are equal and balance is achieved again.

[0077] The present invention also provides a frequency conversion control system for the noise of the exhaust system of a substation building based on a genetic algorithm, and a frequency conversion control method for the noise of the exhaust system of a substation building based on a genetic algorithm; it includes a noise monitoring module, a temperature monitoring module, a PLC control module, a rectifier module, an energy consumption module and an inverter module.

[0078] In a preferred embodiment, the noise monitoring module specifically includes a noise sensor, and the noise sensor monitors the noise level in the environment in decibels (dB).

[0079] In a preferred embodiment, the temperature monitoring module specifically includes a temperature sensor, which monitors the temperature of the environment or the object and converts the temperature data into a digital signal.

[0080] In a preferred embodiment, the PLC control module is composed of a digital input and output module, an analog input module and an analog output module of a PLC programmable controller.

[0081] In a preferred embodiment, the rectifier module adopts a three-phase bridge rectifier circuit, the switching element is a diode, and the filter capacitor Cf is used to filter out the voltage ripple on the DC side of the rectifier circuit to stabilize the output voltage.

[0082] Compared with the prior art, the present invention has the following beneficial effects: This patent proposes an intelligent silent exhaust fan system for substation rooms, which successfully integrates low-noise design, genetic algorithm optimization and frequency conversion control technology, and comprehensively solves the noise pollution, heat dissipation and energy efficiency optimization problems faced by indoor substations during operation. Through real-time monitoring of noise and temperature, precise control of fan speed and implementation of dynamic optimization strategies, the system can significantly reduce indoor noise levels and energy consumption, and improve the operational reliability and environmental protection performance of substations. The modular and intelligent characteristics of the system design make it have good scalability and suitable for indoor substations of different sizes and needs. At the same time, combined with the collaborative optimization of PLC and genetic algorithm, this system further optimizes the noise level while ensuring the temperature control target, reflecting excellent technical advantages and application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 A system structure diagram of a preferred embodiment of the present invention;

[0084] Figure 2 A schematic diagram of a fan control process according to a preferred embodiment of the present invention;

[0085] Figure 3 Schematic diagram of noise and speed curve obtained in the literature;

[0086] Figure 4 A schematic diagram of a speed-temperature / noise curve of a preferred embodiment of the present invention;

[0087] Figure 5 The figure is a flow chart of an algorithm according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0088] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0089] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0090] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application; as used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations.

[0091] The frequency conversion control system of the substation exhaust system noise based on genetic algorithm, reference Figure 1 The automatic frequency conversion control system of the silent exhaust fan system of the intelligent substation adopts a modular design, including noise monitoring module, temperature monitoring module, PLC control module, rectifier module, energy consumption module and inverter module. Its basic structure is as follows: Figure 1 As shown. In the system design, the study of frequency converter is very important. Usually, frequency conversion speed regulation is divided into AC-AC frequency conversion and AC-DC-AC frequency conversion, and the latter is the most widely used in practice, with advantages such as low harmonic content and adjustable stator and rotor power factors. The following is a detailed description of each module:

[0092] 1. Noise monitoring module

[0093] The role of the noise sensor is to monitor and measure the noise level in the environment in decibels (dB). It can sense the intensity of sound, identify the source of noise pollution, and transmit this data to the control system or equipment for further analysis and processing. Noise sensors are set at the four corners of the station house to monitor the noise in the station house, and the average value of the four noise sensors is taken as the indoor noise input to the PLC control module.

[0094] 2. Temperature monitoring module

[0095] Use temperature sensors to monitor and measure the temperature of the environment or objects in real time, and convert temperature data into electrical signals or digital signals for further processing and analysis by the control system or equipment. Set 4 temperature sensors at the 4 corners of the station to monitor the station temperature, and set 1 temperature sensor outdoors to monitor the outdoor temperature; take the average value of the 4 indoor temperature sensors as the indoor temperature, take the reading of the outdoor temperature sensor as the outdoor temperature, and input the difference between the indoor temperature and the outdoor temperature into the PLC control module as the temperature difference.

[0096] 3.PLC control module

[0097] Figure 1 The PLC control module is the core of the variable frequency automatic control of the exhaust fan. The control system is mainly composed of the digital input / output module and analog input / output module of the PLC programmable controller. Its main functions are to compare and judge the temperature and noise, diagnose faults, and control outputs. At the same time, it can transmit information remotely for centralized monitoring.

[0098] 4. Rectifier module

[0099] The rectifier module adopts a three-phase bridge rectifier circuit, the switching element uses a diode, and the filter capacitor Cf is used to filter the voltage ripple on the DC side of the rectifier circuit and stabilize the output voltage. In addition, in order to prevent the instantaneous start and stop of the inverter from generating overcharge current on the filter capacitor, a current limiting resistor Rm is connected in series on the DC side of the rectifier circuit. At the same time, the voltage fluctuation on the DC side can be reduced to a certain extent.

[0100] 5. Energy consumption module

[0101] When the operating frequency of the motor is reduced, it will enter the power generation state and feed back the electric energy to the DC side of the rectifier module, causing the voltage Ud at both ends to increase, which will have a serious impact on the operation of electrical components and circuits. In order to avoid this situation, an energy consumption module is added between the inverter rectifier module and the inverter module, and the electric energy fed back to the DC side is consumed through its internal resistance element to ensure the safe operation of the system and the normal operation of the switching devices.

[0102] 6. Inverter module

[0103] The inverter module of the frequency converter uses IGBT as a switching device. Since there are inductive components in the fan device, reactive components will be generated in the current. Therefore, anti-parallel diodes are connected at both ends of each IGBT for reactive current feedback and to provide a channel for the fan to feed back electrical energy to the DC side.

[0104] 7. Host computer module

[0105] The host computer is a computer system that interacts with and controls the lower computer (such as a PLC, embedded device, or other controller) in an automated control system. The host computer is responsible for in-depth processing of the data received from the lower computer, and calculates the data by applying a genetic algorithm to determine the optimal frequency of the fan under specific temperature conditions to minimize noise. The host computer can send control commands to the lower computer based on user input or preset control logic, and also provides a suitable operation interface for real-time display of monitoring noise and temperature data and receiving user input.

[0106] PLC programmable controllers are widely used in industrial production, power supply and distribution, and system monitoring, and most of them generate the required frequency pulses for controlling frequency converters. There are two main ways to control frequency converters with PLC. One is to use analog input and output modules to use the collected indoor and outdoor temperature difference as system feedback to form a closed-loop control. The other is to control through a serial communication interface, such as using RS-485 serial communication to connect PLC and frequency converter, so as to control the exhaust fan speed and the number of starts and stops through the PLC program. The control result can be used as feedback to achieve zero-static speed regulation. Therefore, this method can achieve the most effective automatic control and is the most widely used.

[0107] According to the above analysis, by combining PLC with frequency converter, the exhaust fan speed and the number of fan starts and stops are controlled by using genetic algorithm program, and the corresponding PLC control strategy is formulated according to the actual situation on site.

[0108] The frequency conversion automation system uses communication equipment with RS-485 as the data interface to connect PCL, frequency converter and exhaust fan. This transmission mode is compatible with cables and optical fibers, with high transmission baud rate, long transmission distance and low distortion;

[0109] The temperature sensor measures the indoor (average) and outdoor temperatures of each substation room in real time, and sends the temperature difference to the PLC through the analog input module;

[0110] The noise sensor is used to measure the indoor noise of each substation in real time, and the noise reading is sent to the PLC through the analog input module;

[0111] The control circuit of the cooling fan adopts closed-loop control. The PLC generates corresponding frequency trigger pulses as the control signal of the frequency converter according to the temperature difference, noise and genetic algorithm results, and adjusts the fan speed and the number of fans switched on and off according to the difference between the input and feedback quantities, thereby reducing the temperature difference.

[0112] 1. Derivation of the relationship between temperature and exhaust fan speed

[0113] Assume that an exhaust fan is installed in each of the four corners of the substation building. The goal is to derive the relationship between the indoor temperature and the exhaust fan speed based on factors such as the size of the substation building to be determined, the temperature difference between indoor and outdoor, air velocity, exhaust fan air volume, heat source, and the basic principles of thermodynamics and fluid mechanics. The following briefly introduces the relevant plans and steps.

[0114] 1) Setting of basic parameters

[0115] Station room size: The station room can be roughly regarded as a rectangular parallelepiped with dimensions of L×W×H, which are the length, width and height of the room respectively, in meters.

[0116] Indoor and outdoor temperature difference: Assume the indoor temperature is T in , outdoor temperature is T out The temperature difference between the two is ΔT = T in -T out . The unit is degrees Celsius.

[0117] Air velocity: Air velocity v air Assumed to be a constant value in m / s.

[0118] Exhaust volume: The exhaust volume of each exhaust fan is Q fan , unit is m 3 / h. The exhaust volume of the exhaust fan is proportional to the rotation speed. The specific relationship is:

[0119] Q fan = k·n

[0120] Among them, k is the fan constant, and n is the speed of the exhaust fan in revolutions per minute.

[0121] Heat source: There may be multiple heat sources in the station building (such as power equipment, lighting equipment, etc.). Assume that the total heat load of these heat sources is Q heat , the unit is watt (w).

[0122] Specific heat capacity of the air in the station room: Assume that the specific heat capacity of the air in the station room is c air , the air density is ρ air .

[0123] 2) Heat balance equation

[0124] Considering the heat balance of the room, assuming steady-state conditions, the following heat conservation equation can be used to derive the relationship between the station room temperature, heat source, and exhaust volume:

[0125] Q heat +Q inflow =Q outflow

[0126] Where Q inflow is the heat entering the station building, Q outflowIt is the heat that is discharged through the exhaust fan.

[0127] When air enters a room from the outside, the relationship between the air velocity and the temperature difference between the inside and the outside can be expressed by heat transfer. inflow Mainly determined by the following factors:

[0128] Q inflow =m·c air ΔT

[0129] Where m is the mass flow rate of air in kg / s, which can be calculated from the air velocity and room volume:

[0130] m=ρ air ·v air ·A room

[0131] Among them A room =L×W is the floor area of ​​the station building.

[0132] The exhaust volume of the exhaust fan is proportional to the rotation speed. The exhaust volume of an exhaust fan in the station room is

[0133] Q outflow =Q fan = k·n

[0134] Heat removed by exhaust air volume Q outflow Determined by the mass flow rate and temperature difference of the air:

[0135] Q outflow =m·c air ·(T in -T out )

[0136] 3) Relationship between exhaust fan speed and indoor temperature

[0137] From the heat balance we get:

[0138] Q heat +m·c air ·ΔT=k·v fan ·c air ·(T in -T out )

[0139] Under steady-state conditions, the indoor temperature T in Determined by the following equation:

[0140] Q heat +ρ air ·v air ·A room ·c air ΔT

[0141] = k·v fan ·ρ air ·v air ·A room ·c air ·(T in -T out )

[0142] Simplifying the related constant terms, we can get the relationship between the exhaust fan speed and the indoor temperature:

[0143]

[0144] When the temperature of the substation room is too high, the PLC controls the fan speed to increase.

[0145] Q heat +Q inflow outflow

[0146] When the exhaust temperature increases, the indoor temperature will drop, causing ΔT to increase, Q inflow It gets bigger until both sides of the equation are equal and balance is achieved again.

[0147] 2. Relationship between exhaust fan speed and noise

[0148] The relationship between fan speed and noise is usually positively correlated, that is, the higher the speed of the exhaust fan, the greater the noise generated. The root cause of this phenomenon lies in the role of different physical phenomena in the working process of the exhaust fan. In order to explain this relationship in more detail, we can discuss it from the following aspects:

[0149] 1) Sources of noise

[0150] The noise of the exhaust fan mainly comes from the following aspects:

[0151] (1) Airflow noise (aerodynamic noise)

[0152] Airflow noise is generated by the interaction between the fan impeller and the air when it rotates. When the speed of the exhaust fan increases, the airflow velocity and kinetic energy of the airflow increase, resulting in stronger turbulence and aerodynamic noise when the airflow passes through the fan blades and exhaust duct. There is a positive correlation between airflow noise and fan speed.

[0153] (2) Mechanical noise (structure-borne noise)

[0154] The mechanical noise of the fan comes from the vibration and friction between the various components inside the fan (such as blades, bearings, rotors, etc.). At high speeds, the vibration frequency of the mechanical components increases, and the noise generated becomes more significant. This noise is usually low-frequency noise, but at high speeds, due to vibration and impact, the noise frequency and intensity may increase.​

[0155] (3) Fluid dynamics noise (eddy current noise)

[0156] When the exhaust fan impeller rotates, the airflow generates vortices on the blade surface, causing flow instability and eddy noise. At high speeds, the turbulence effect of the fluid is enhanced, causing the eddy to generate more noise.

[0157] (4) Exhaust fan vibration and resonance noise

[0158] During the operation of the fan, vibrations may occur due to imbalance, blade damage, installation problems, etc. These vibrations will be transmitted through the fan's supporting structure and cause resonance, resulting in noise amplification.

[0159] 2) Relationship between speed and noise

[0160] As the fan speed increases, the frequency components of the noise also change. At low speeds, the noise is mainly concentrated in the low-frequency range (such as mechanical noise and low-frequency vibration noise); at high speeds, high-frequency components such as airflow noise and eddy current noise will increase. The impact of high-frequency noise on humans is usually more obvious, especially in environments where low-frequency noise is better controlled.

[0161] Figure 3 This is the relationship curve between noise and speed obtained from the literature. It can be seen from the figure that there is a logarithmic relationship between noise and speed. This relationship can usually be expressed as:

[0162] N v =A·lg(n)+B

[0163] Where: N v is the noise level in dB, n is the speed in r / min, A and B are empirical constants

[0164] Under this relationship, every increase in the exhaust fan speed will lead to a logarithmic increase in noise. As the speed increases, the turbulence intensity, mechanical vibration and fluid dynamics effects of the airflow will increase accordingly, causing the noise level to rise.

[0165] 3. Genetic Algorithm

[0166] Genetic Algorithm (GA) is a computational model of biological evolution that simulates the natural selection and genetics mechanism of Darwin's theory of biological evolution. It is a randomized search method and can be regarded as a mathematical model of evolution. The algorithm has the characteristics of parallelism, high efficiency, and global search capability. It basically does not require any auxiliary knowledge, is not restricted by conditions such as differentiability and continuity, and has strong global search capabilities. Similar to genetic evolution in nature, for each generation of genetic algorithms, we specify a fitness function for a specific problem to select individuals. Individuals that meet the conditions are retained, and those that do not meet the conditions are eliminated. New individuals are obtained after multiple inheritances. In this way, following the genetic laws of nature, we obtain new individuals that are more adaptable to environmental requirements than old individuals. This is the basic idea of ​​​​the implementation of genetic algorithms.

[0167] This patent uses a genetic algorithm to optimize the operating parameters of multiple exhaust fans in a substation room to minimize the noise generated by the exhaust fan operation while satisfying the constraint that the indoor temperature does not exceed the set threshold. The relationship between the indoor temperature and the exhaust fan speed is derived from the heat balance and is expressed as:

[0168]

[0169] There is an approximate logarithmic relationship between noise and exhaust fan speed, which can be expressed as:

[0170] N v =A·lg(n)+B

[0171] Figure 4 It is the relationship curve between speed, noise and temperature. It can be seen from the figure that under the joint constraints of temperature threshold and noise threshold, there is a speed range that meets both temperature and noise control requirements.

[0172] Therefore, the optimization goal is to find the optimal combination between the speed n of multiple fans and the number q of fans through genetic algorithms, so as to minimize the noise and achieve an efficient and low-noise operation strategy while meeting the temperature control requirements.

[0173] A certain margin should be left to prevent the station room temperature from suddenly increasing, causing the control system to be unable to respond in time, causing the equipment to be in an unfavorable operating state.

[0174] 1) Algorithm Framework

[0175] In order to find the optimal control solution, the following steps are required to find the optimal speed and number of fans when they are running.

[0176] (1) Initialize the population

[0177] Population representation: Each individual represents a number of fans and the possible exhaust fan speed n of each fan, which can be represented as an n-dimensional array, where q is the number of fans.

[0178] Population size: Select the population size A to represent the current solution space, randomly initialize the n-dimensional array in the population, and ensure that the speed of each fan in the n-dimensional array is within a certain range (such as 0 to 1000 rpm).

[0179] (2) Fitness function

[0180] The fitness function is used to evaluate the quality of individuals. In this problem, the fitness function contains two parts: 1. Temperature constraint: The corresponding room temperature is calculated according to the exhaust fan speed. During the calculation process, the ventilation volume of several exhaust fans is directly added and subtracted, and then the indoor temperature value is calculated by the exhaust fan speed and indoor temperature formula. If the temperature exceeds the set threshold T th , then the fitness of the solution is 0, indicating that the solution is invalid. 2. Noise constraint: The noise level is calculated according to the speed of each exhaust fan so as to minimize the noise under the constraint of not exceeding the maximum temperature threshold.

[0181] When calculating the room temperature under the action of several fans, the room temperature can be calculated by the following formula:

[0182]

[0183] Where: T int is the room temperature under the combined action of all fans, q is the number of fans, n is i (i=0, 1, 2···, q) is the speed of each fan, k, ρ air 、v air , A room 、c air , Q heat All are empirical constants.

[0184] When calculating the noise of several fans, the noise level can be calculated using the following formula:

[0185]

[0186] Where: N vt is the sum of the noise levels generated by all fans, q is the number of fans, is the noise generated by each fan. Combining the formula of the noise and speed of a single fan, it can be further rewritten as follows:

[0187]

[0188] Temperature control constraints:

[0189] According to the heat balance model described above, there is a direct mathematical relationship between the fan speed and the indoor temperature, namely:

[0190]

[0191] Where: T int is the room temperature under the combined action of all fans, q is the number of fans, n is i (i=0, 1, 2···, q) is the speed of each fan, k, ρ air 、v air , A room 、c air , Q heat All are empirical constants.

[0192] Therefore, the fitness function first evaluates whether the indoor temperature exceeds the set threshold under the given fan configuration, which also takes into account the margin for sudden temperature increases during station operation. If the temperature exceeds the threshold, the fitness value of the solution is zero, indicating that the configuration is invalid. Otherwise, the fitness value is adjusted according to the temperature deviation: the smaller the temperature deviation, the higher the fitness value.

[0193] The noise is related to the number of fans started and the speed of each fan. The smaller the noise, the higher the adaptability.

[0194]

[0195] Among them: F temp is the fitness value of temperature, T int is room temperature, T th is the set temperature threshold.

[0196] Noise minimization constraints:

[0197] As mentioned above, there is the following relationship between noise and fan speed:

[0198]

[0199] Where: N vt is the sum of the noise levels generated by all fans, q is the number of fans, n is i (i=0, 1, 2,..., q) is the rotation speed of each fan, and A and B are empirical constants.

[0200] In order to minimize the noise and optimize the speed and number of fans in the genetic algorithm, the fitness function is designed in combination with the noise constraint. During the optimization process, we hope to reduce the noise by controlling the fan speed while ensuring that the temperature remains within the required range. Therefore, the fitness function F noise It will be adjusted according to the noise level, and the noise fitness function is as follows:

[0201]

[0202] Among them: F noise is the fitness value of the noise, N vt The noise level generated by all fans is summed, and α is an adjustment factor used to control the impact of noise on fitness. If α is large, the penalty of noise will be more significant, and the speed of the fan needs to be controlled as low as possible.

[0203] In order to further optimize noise control, a noise upper limit and penalty factor are introduced into the fitness function, so that when the noise exceeds a certain threshold, the fitness value will drop sharply, and when the system faces multiple fans, the impact of the number of fans on noise is considered. The penalty factor increases the complexity of the number of fans and speed in the configuration to prevent excessive noise caused by too many fans or too high speed. The fitness function is further designed as follows:

[0204]

[0205] Where: N max is the set noise upper limit, when the noise N vt If the threshold is exceeded, the fitness value will drop rapidly, indicating that the noise of the configuration is seriously exceeded. p is the number of fans, and β is the penalty factor, which is used to adjust the impact of the number of fans on the fitness value. If the number of fans is too large, the β·p term will reduce the fitness value, thus forcing the genetic algorithm to select an appropriate number of fans.

[0206] (3) Select operation

[0207] The selection operation is used to select individuals with higher fitness from the current population as parent individuals. The selection method can be roulette selection or tournament selection, which can select better individuals according to the level of fitness.

[0208] (4) Crossover operation

[0209] The crossover operation is used to exchange the genes of two parent individuals (i.e. the speed values ​​of each wind turbine) to generate new offspring individuals. Common crossover methods include single-point crossover and uniform crossover.

[0210] (5) Mutation Operation

[0211] The mutation operation is used to randomly fine-tune the speed of some individuals to maintain the diversity of the population and prevent falling into the local optimal solution. The amplitude of the mutation can be set to a certain range, such as making a small change near the current speed.

[0212] (6) Update population

[0213] After the crossover and mutation operations, a new population is generated. You can choose to retain the parent and offspring merging method, or choose to eliminate individuals with poor fitness.

[0214] (7) Termination conditions

[0215] Set the maximum number of iterations, or stop the algorithm when the fitness reaches the preset threshold. Finally, output the optimal solution (i.e. the optimal speed of each exhaust fan).

[0216] 2) Algorithm Explanation

[0217] (1) Initialize the population: Randomly generate the exhaust fan speed n and the number of running units q in the initial population. Fitness function: Calculate the corresponding room temperature and noise according to the speed, ensure that the room temperature does not exceed the threshold, and minimize the noise.

[0218] (2) Selection operation: Use the tournament selection method to select the parent with higher fitness.

[0219] (3) Crossover operation: Generate the child generation speed through the mean of the parent generation speed.

[0220] (4) Mutation operation: Randomly change the rotation speed with a certain probability to increase the diversity of the population.

[0221] (5) Optimization result: output the optimal speed of each exhaust fan.

[0222] 3) Exhaust fan control strategy based on genetic algorithm

[0223] The PLC (Programmable Logic Controller) is responsible for controlling the optimized exhaust fan speed configuration to each exhaust fan in real time. The PLC monitors the indoor temperature and noise data in real time, obtains feedback and adjusts the fan speed to achieve optimal control. The PLC monitors the temperature and noise in the substation room in real time through sensors and transmits the data to the control system. Then, according to the optimal speed configuration output by the genetic algorithm, the PLC adjusts the speed of each exhaust fan. As the temperature and noise data change, the PLC works in conjunction with the genetic algorithm to dynamically adjust the speed of the exhaust fan to ensure that the temperature does not exceed the set threshold while minimizing the noise.

[0224] Algorithm Implementation

[0225] First, set the various environmental parameters of the room, such as room size, heat source load, initial temperature, exhaust fan performance, etc. The genetic algorithm calculates the optimal exhaust fan speed configuration to ensure that the noise is minimized while meeting the temperature constraints. The PLC executes the optimized control strategy, adjusts the exhaust fan speed and the number of fans in operation in real time, and continues to optimize based on the feedback data. This ensures that the substation room meets the temperature control requirements while minimizing the environmental noise generated.

[0226] The present invention proposes a variable frequency control technology for the exhaust system of a substation house based on a genetic algorithm, which is used to realize the joint optimization control of multiple exhaust fans and minimize the operating noise under the premise that the room temperature of the substation house does not exceed the set threshold. The system adopts a distributed sensor network to collect the temperature and noise data of the substation house in real time, combines the variable frequency speed regulation technology, and establishes a multi-objective optimization model through a genetic algorithm, and jointly solves the noise and temperature as constraints and optimization objectives. The genetic algorithm dynamically adjusts the operating frequency of the exhaust fan through operations such as population initialization, fitness evaluation, selection, crossover and mutation, thereby balancing the needs of temperature control and noise minimization. The present invention can adaptively adjust the speed of the exhaust fan according to different environmental conditions and equipment operating status, so that the system can effectively reduce noise pollution while efficiently dissipating heat. Compared with the traditional single-machine fixed wind speed or simple linkage control method, the present technology can significantly improve the comprehensive energy efficiency of the system, reduce energy waste, and improve the operating environment of the substation house. The technology is suitable for the noise and temperature control needs of various types of indoor substations and similar scenarios, and has high applicability and promotion value.

Claims

1. A frequency conversion control method for noise of exhaust system of substation building based on genetic algorithm, characterized in that: The following steps are involved: Step 1: Arrange multiple noise sensors and temperature sensors in the substation room; the noise sensor is used to monitor the noise level in each area of ​​the substation room in real time, and the average value of the monitoring values ​​of all noise sensors is input into the PLC control module as the comprehensive index of indoor noise; the temperature sensor is used to monitor the temperature inside and outside the substation room, obtain the temperature difference between indoor and outdoor, and input the temperature difference data into the PLC control module as a reference for temperature and noise control; Step 2: The PLC control module transmits the collected noise data and temperature data to the host computer through the RS-485 communication protocol; in the host computer, the received data is processed, and the genetic algorithm is introduced to calculate and optimize the data, and the monitored temperature and noise data are displayed in real time in the monitoring interface of the host computer; the genetic algorithm dynamically adjusts the operating frequency of the fan according to the restriction of the current temperature threshold and the change trend of indoor noise and temperature. The goal is to minimize the noise generated by the fan operation while ensuring that the indoor temperature does not exceed the set threshold; Step 3: After genetic algorithm calculation, the optimal speed control strategy generated by the host computer will be sent to the PLC control module through the RS-485 communication protocol; the PLC control module converts the speed control signal into a current frequency control signal and transmits it to the inverter of each fan; the inverter adjusts the speed of each fan according to the current frequency control signal to achieve precise control of noise and temperature; Step 4: As the ambient temperature and noise change in real time, the PLC control module continuously transmits the latest data to the host computer. When the temperature approaches the temperature threshold, the genetic algorithm recalculates the optimization plan based on the updated data. Through this dynamic adjustment method, the PLC control module and the genetic algorithm work together to ensure that the exhaust fan system always adjusts the fan speed according to the actual conditions inside and outside the station during the entire operation process.

2. The frequency conversion control method of the noise of the exhaust system of the substation based on genetic algorithm according to claim 1 is characterized in that: The optimization of temperature data and noise data by genetic algorithm specifically includes: the relationship between indoor temperature and exhaust fan speed is derived from heat balance and is expressed as: There is an approximate logarithmic relationship between noise and exhaust fan speed, expressed as: N v =A·lg(n)+B。 3. The frequency conversion control method of the noise of the exhaust system of the substation building based on genetic algorithm according to claim 2 is characterized in that: The optimal speed control strategy specifically includes: (1) Initialize the population Population representation: Each individual represents a number of fans and the exhaust fan speed n of each fan, which is represented as an n-dimensional array, where q is the number of fans; Population size: Select the population size A to represent the current solution space, randomly initialize the n-dimensional array in the population, and ensure that the speed of each wind turbine in the n-dimensional array is within a certain range; (2) Fitness function When calculating the room temperature under the action of several fans, the room temperature can be calculated by the following formula: Where: T int is the room temperature under the combined action of all fans, q is the number of fans, n is i , i = 0, 1, 2, q is the speed of each fan, k, ρ air 、v air , A room 、c air , Q heat All are empirical constants; When calculating the noise of several fans, the noise level is calculated using the following formula: Where: N vt is the sum of the noise levels generated by all fans, q is the number of fans, i=0, 1, 2..., q is the noise generated by each fan; combined with the formula of noise and speed of a single fan, it is further rewritten as follows: Temperature control constraints: According to the heat balance model, there is a direct mathematical relationship between the fan speed and the indoor temperature, namely: Where: T int is the room temperature under the combined action of all fans, q is the number of fans, n is i , i = 0, 1, 2, q is the speed of each fan, k, ρ air 、v air , A room 、c air , Q heat All are empirical constants; The fitness function first evaluates whether the indoor temperature exceeds the set threshold under a given fan configuration. If the temperature exceeds the threshold, the fitness value of the solution is zero, indicating that the configuration is invalid; otherwise, the fitness value is adjusted according to the temperature deviation: the smaller the temperature deviation, the higher the fitness value; The noise is related to the number of fans started and the speed of each fan. The lower the noise, the higher the adaptability. Among them: F temp is the fitness value of temperature, T int is room temperature, T th is the set temperature threshold; Noise minimization constraints: There is the following relationship between noise and fan speed: Where: N vt is the sum of the noise levels generated by all fans, q is the number of fans, n is i , i = 0, 1, 2···, q is the rotation speed of each fan, A and B are empirical constants; Fitness function F noise It will be adjusted according to the noise level, and the noise fitness function is as follows: Among them: F noise is the fitness value of the noise, N vt is the sum of the noise levels generated by all fans, and α is an adjustment factor used to control the impact of noise on fitness. If α is large, the penalty of noise will be more significant, and the speed of the fan needs to be controlled as low as possible. The fitness function is further designed as follows: Where: N max is the set noise upper limit, when the noise N vt If this threshold is exceeded, the fitness value will drop rapidly, indicating that the noise of the configuration is seriously exceeded. p is the number of fans, and β is the penalty factor, which is used to adjust the impact of the number of fans on the fitness value. If the number of fans is too large, the β·p term will reduce the fitness value, thus forcing the genetic algorithm to select an appropriate number of fans. (3) Select operation The selection operation is used to select individuals with higher fitness from the current population as parent individuals; the selection method can be roulette selection or tournament selection, which can select better individuals according to the level of fitness; (4) Crossover operation The crossover operation is used to exchange the genes of two parent individuals, i.e. the speed values ​​of each wind turbine, to generate new offspring individuals. Common crossover methods include single-point crossover and uniform crossover. (5) Mutation Operation The mutation operation is used to randomly fine-tune the rotation speed of some individuals to maintain the diversity of the population and prevent falling into the local optimal solution; the amplitude of the mutation is set to a certain range; (6) Update population After the crossover and mutation operations, a new population is generated; a combination method of retaining the parent and offspring is selected, or individuals with poor fitness are eliminated; (7) Termination conditions The algorithm is stopped by setting the maximum number of iterations or when the fitness reaches a preset threshold; the optimal solution, i.e., the optimal speed of each exhaust fan, is finally output.

4. The frequency conversion control method of the noise of the exhaust system of a substation building based on genetic algorithm according to claim 3 is characterized in that: Assuming steady-state conditions, the following heat conservation equation gives the relationship between the station room temperature, heat source, and exhaust volume: Q heat +Q inflow =Q outflow Where Q inflow is the heat entering the station building, Q outflow It is the heat discharged by the exhaust fan; When air enters a room from the outside, the relationship between the air velocity and the temperature difference between indoor and outdoor is expressed by heat transfer; the heat entering the room Q inflow Mainly determined by the following factors: Q inflow =m·c air ·ΔT Where m is the mass flow rate of air in kg / s, which is calculated from the air velocity and room volume: m=ρ air ·v air ·A room Among them A room =L×W is the floor area of ​​the station building; The exhaust volume of the exhaust fan is proportional to the rotation speed, so the exhaust volume of an exhaust fan in the station room is Q outflow =Q fan =k·n Heat removed by exhaust air volume Q outflow Determined by the mass flow rate and temperature difference of the air: Q outflow =m·c air ·(T in -T out )。 5. The frequency conversion control method of the noise of the exhaust system of the substation building based on genetic algorithm according to claim 4 is characterized in that: From the heat balance: Q heat +m·c air ·ΔT=k·v fan ·c air ·(T in -T out ) Under steady-state conditions, the indoor temperature T in Determined by the following equation: Q heat +ρ air ·v air ·A room ·c air ·ΔT=k·v fan ·ρ air ·v air ·A room ·c air ·(T in -T out ) Simplifying the related constant terms, we can get the relationship between the exhaust fan speed and the indoor temperature: When the temperature of the substation room is too high, the PLC controls the fan speed to increase. Q heat +Q inflow <Q outflow When the exhaust temperature increases, the indoor temperature will drop, causing ΔT to increase, Q inflow It gets bigger until both sides of the equation are equal and balance is achieved again.

6. A variable frequency control system for noise of exhaust system of substation building based on genetic algorithm, characterized in that A frequency conversion control method for noise of a substation exhaust system based on a genetic algorithm according to any one of claims 1 to 5; It includes a noise monitoring module, a temperature monitoring module, a PLC control module, a rectifier module, an energy consumption module and an inverter module.

7. The frequency conversion control system of the noise of the exhaust system of the substation building based on genetic algorithm according to claim 6 is characterized in that: The noise monitoring module specifically includes a noise sensor, which monitors the noise level in the environment in decibels (dB).

8. The frequency conversion control system for noise of the exhaust system of a substation building based on genetic algorithm according to claim 6 is characterized in that: The temperature monitoring module specifically includes a temperature sensor, which monitors the temperature of the environment or an object and converts the temperature data into a digital signal.

9. The frequency conversion control system of the noise of the exhaust system of the substation building based on genetic algorithm according to claim 6 is characterized in that: The PLC control module consists of the digital input and output modules, analog input modules and analog output modules of the PLC programmable controller.

10. The frequency conversion control system of the noise of the exhaust system of the substation building based on genetic algorithm according to claim 6, characterized in that: The rectifier module adopts a three-phase bridge rectifier circuit, the switching element uses a diode, and the filter capacitor Cf is used to filter the voltage ripple on the DC side of the rectifier circuit and stabilize the output voltage.

Images