An air-conditioning automatic control method and system based on a cold and heat source machine room

Abstract

The present invention discloses an air-conditioning automatic control method and system based on a cold and heat source machine room, which relates to the technical field of air-conditioning automatic control. The method includes collecting the operation data of the cold and heat source machine room; calculating a cold and heat source switching index K1 according to the deviation between the outdoor temperature T1 and the target temperature T0 and in combination with the change trend of the relative humidity H1; when the cold and heat source switching index K1 exceeds a preset threshold, starting a load prediction module to generate a load prediction value P1; and controlling the water pump speed in a gradient adjustment manner according to the load prediction value P1 and dynamically adjusting the valve opening V1 through the temperature difference between the supply water temperature T2 and the return water temperature T3. The present invention significantly improves the accuracy of system operation, energy utilization efficiency and adjustment flexibility, can accurately adjust the water pump speed and valve opening in real time and dynamically according to the changes in outdoor temperature and humidity and the operation characteristics of equipment, and effectively solves the technical problems of inaccurate control and large energy consumption fluctuations in the air-conditioning system.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioner automatic control, and particularly to an air conditioner automatic control method and system based on a cold and heat source machine room. Background Art

[0002] Traditional air conditioner control methods mainly rely on simple temperature feedback regulation, and perform cold and heat source switching and equipment regulation by setting fixed start and stop temperature points. In recent years, the application of variable frequency technology and intelligent control algorithms has made the air conditioner system develop towards refinement and intelligence, and various control strategies such as fuzzy control and PID control have emerged. However, these control methods still have many limitations in practical applications: First, the control of a single temperature parameter cannot accurately reflect the characteristics of air conditioner load changes, resulting in system response lag; second, the equipment regulation method is relatively rough and does not fully consider the influence of the supply and return water temperature difference on system efficiency; third, the lack of the ability to predict future loads makes it impossible to achieve early regulation and smooth transition of the system; finally, in terms of energy consumption management, fixed time period control is often adopted and dynamic optimization is not carried out according to the actual operating conditions.

[0003] Currently, the air conditioner control systems on the market generally have problems such as low control accuracy, large energy consumption fluctuations, and slow adjustment response. The specific manifestations are as follows: First, the cold and heat source switching depends on the temperature threshold set by experience and does not consider the influence of humidity changes on human comfort; second, the water pump speed regulation uses fixed gears or simple proportional control, which is easy to cause energy waste and equipment impact; third, the valve opening control lacks real-time monitoring and dynamic regulation of the supply and return water temperature difference, affecting the heat exchange efficiency; fourth, the system lacks predictive regulation ability and often makes passive adjustments after obvious changes occur in the indoor environment. These technical problems seriously restrict the operating efficiency and control effect of the air conditioner system.

[0004] In view of this, there is an urgent need for an air conditioner control method that can comprehensively consider the characteristics of temperature and humidity changes, achieve load prediction and equipment coordinated regulation. An air conditioner automatic control method and system based on a cold and heat source machine room provided by the present invention solve the problems of low control accuracy, poor energy consumption efficiency, and adjustment lag existing in the prior art through multi-parameter acquisition and intelligent algorithms. Summary of the Invention

[0005] In view of the problems of inaccurate cold and heat source switching, uncoordinated equipment regulation, and low energy utilization efficiency existing in the existing air conditioner control system, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to implement an air conditioner control method based on multi-parameter intelligent collaboration, and improve the accuracy of system operation and energy utilization efficiency through comprehensive evaluation of temperature and humidity, load prediction, and dynamic regulation of equipment.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides an air-conditioning automatic control method based on a cold and heat source machine room, which includes collecting operation data of the cold and heat source machine room, where the operation data includes outdoor temperature T1, relative humidity H1, supply water temperature T2, return water temperature T3, and equipment energy consumption data E1; calculating a cold and heat source switching index K1 according to the deviation between the outdoor temperature T1 and the target temperature T0, in combination with the change trend of the relative humidity H1; when the cold and heat source switching index K1 exceeds a preset threshold, starting a load prediction module to generate a load prediction value P1; controlling the water pump speed in a gradient adjustment manner according to the load prediction value P1, and dynamically adjusting the valve opening V1 through the temperature difference between the supply water temperature T2 and the return water temperature T3, so as to achieve the adaptive control of the air-conditioning system in the cold and heat source machine room.

[0009] As a preferred solution of the air-conditioning automatic control method based on the cold and heat source machine room of the present invention, wherein: the method for obtaining the valve opening V1 is to divide the load prediction value P1 into several load intervals with a preset rated load as the step size, where the load intervals correspond to the reference water pump speed value N0; calculating the relative position coefficient β1 of the load prediction value P1 within the current load interval, where the relative position coefficient β1 is the difference between the load prediction value P1 and the lower limit of the load interval divided by the length of the load interval; substituting the relative position coefficient β1 into a cubic spline function to obtain a speed correction coefficient β2, where the speed correction coefficient β2 is used to smooth the speed change between adjacent load intervals; multiplying the reference water pump speed value N0 by the speed correction coefficient β2 to obtain the target water pump speed N1, and controlling the water pump speed to transition from the current water pump speed N2 to the target water pump speed N1 in a gradient adjustment manner; at the same time, calculating the temperature difference ΔT1 between the supply water temperature T2 and the return water temperature T3, dividing the temperature difference ΔT1 by the set temperature difference ΔT0 to obtain a temperature difference ratio R1; substituting the temperature difference ratio R1 into a logarithmic function to obtain a valve opening correction coefficient α1; multiplying the current valve opening V0 by the valve opening correction coefficient α1 to obtain the valve opening V1.

[0010] As a preferred solution of the air-conditioning automatic control method based on the cold and heat source machine room of the present invention, wherein: it further includes that when the temperature difference ratio R1 is less than a first preset threshold, it is determined that the refrigeration or heating efficiency of the air-conditioning system is insufficient, and the valve opening V1 is increased; when the temperature difference ratio R1 is greater than or equal to the first preset threshold and less than a second preset threshold, it is determined that the air-conditioning system is operating normally and there is no need to adjust the valve opening V1; when the temperature difference ratio R1 is greater than or equal to the second preset threshold, it is determined that the air-conditioning system is in a state of over-refrigeration or over-heating, and the valve opening V1 is decreased.

[0011] As a preferred embodiment of the air-conditioning automatic control method based on a cold and heat source machine room according to the present invention, the method for generating the load prediction value P1 is as follows: the equipment energy consumption data E1 is divided into several data segments according to an expected period, and a sampling sequence S1 is obtained based on sampling at equal time intervals; an energy consumption feature vector F1 is extracted from the sampling sequence S1, where the energy consumption feature vector F1 includes a peak-valley ratio, an energy consumption slope, and a fluctuation coefficient; the historical data with the highest similarity to the energy consumption feature vector F1 is selected from a historical database as a training sample set D1, where the similarity is calculated by the cosine value of the included angle of the feature vectors; the training sample set D1 is standardized by using a maximum-minimum normalization method to generate a standardized sample set D2; based on the standardized sample set D2, a neural network model M1 is constructed and trained; the sampled data of the equipment energy consumption data E1 is input into the trained neural network model M1, and the load prediction value P1 is output.

[0012] As a preferred embodiment of the air-conditioning automatic control method based on a cold and heat source machine room according to the present invention, a cold and heat source switching index K1 is calculated according to the deviation between the outdoor temperature T1 and the target temperature T0 in combination with the change trend of the relative humidity H1, including: the outdoor temperature T1 is spatially weighted by using a measurement point distance exponential decay method to obtain a weighted outdoor temperature value u; based on the difference between the weighted outdoor temperature value u and the target temperature T0, a temperature deviation ΔT is calculated by multiplying by a temperature distribution coefficient σ1, where the temperature distribution coefficient σ1 is determined by the dispersion degree of the temperatures of each measurement point; the relative humidity H1 is exponentially decayed and superimposed according to the sampling time sequence to obtain a humidity change index ΔH; the temperature deviation ΔT is substituted into a hyperbolic tangent function to output a temperature weight coefficient W1; at the same time, the humidity change index ΔH is substituted into an exponential decay function to output a humidity weight coefficient W2; the temperature deviation ΔT, the humidity change index ΔH, the temperature weight coefficient W1, and the humidity weight coefficient W2 are substituted into a coupling calculation formula to obtain the cold and heat source switching index K1.

[0013] As a preferred embodiment of the air-conditioning automatic control method based on a cold and heat source machine room according to the present invention, the method for collecting the operation data is as follows: the outdoor temperature T1 is collected by temperature sensors arranged at four directions and the top of the outer wall of the machine room; the outdoor relative humidity H1 is collected by humidity sensors installed at four directions of the outer wall of the machine room; the supply water temperature T2 is collected by a temperature sensor arranged at the outlet of the water supply pipeline; the return water temperature T3 is collected by a temperature sensor installed at the inlet of the return water pipeline; the equipment energy consumption data E1 is collected by an electric energy metering device installed at the power supply incoming end of the cold and heat source unit.

[0014] As a preferred solution of the air-conditioning automatic control method based on a cold and heat source machine room according to the present invention, wherein: the humidity sensor and the temperature sensor are integrated in the same measurement unit; there are three temperature measurement points at the outlet of the water supply pipeline, which are distributed in a fan shape; there are several temperature measurement points evenly distributed at the inlet of the return water pipeline; the energy consumption data E1 includes the electricity consumption, peak-valley values and change trends in each period.

[0015] In a second aspect, an embodiment of the present invention provides an air-conditioning automatic control system based on a cold and heat source machine room, which includes: an acquisition module for acquiring the operation data of the cold and heat source machine room, where the operation data includes the outdoor temperature T1, relative humidity H1, water supply temperature T2, return water temperature T3, and equipment energy consumption data E1; a calculation module for calculating a cold and heat source switching index K1 according to the deviation between the outdoor temperature T1 and the target temperature T0, in combination with the change trend of the relative humidity H1; a generation module for starting a load prediction module to generate a load prediction value P1 when the cold and heat source switching index K1 exceeds a preset threshold; an adjustment module for controlling the pump speed in a gradient adjustment manner according to the load prediction value P1, and dynamically adjusting the valve opening V1 through the temperature difference between the water supply temperature T2 and the return water temperature T3.

[0016] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and wherein: when the computer program instructions are executed by the processor, the steps of the air-conditioning automatic control method based on a cold and heat source machine room as described in the first aspect of the present invention are implemented.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and wherein: when the computer program instructions are executed by the processor, the steps of the air-conditioning automatic control method based on a cold and heat source machine room as described in the first aspect of the present invention are implemented.

[0018] The beneficial effects of the present invention are as follows: Through multi-parameter intelligent collaborative control, precise adaptive regulation of the air-conditioning system in the cold and heat source machine room is achieved; technologies such as multi-dimensional data acquisition, intelligent switching index calculation, neural network load prediction, and gradient regulation are adopted to break through the limitations of traditional air-conditioning control methods; a mapping relationship between load change and speed regulation is established based on load interval division and relative position coefficient calculation, and a cubic spline function is introduced to ensure the smoothness of speed change. At the same time, a gradient regulation method is adopted to reduce equipment impact; compared with the prior art, this method performs early speed regulation through the load prediction value, significantly improving the accuracy and response speed of system operation, and can accurately adjust the pump speed and valve opening in real time and dynamically according to the changes in outdoor temperature and humidity and the operating characteristics of equipment, effectively solving the technical problems of inaccurate control of the air-conditioning system and large energy consumption fluctuations. Description of the Drawings

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0020] Figure 1 It is a flowchart of the air-conditioning automatic control method based on the cold and heat source machine room for Embodiment 1. Specific Embodiments

[0021] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification.

[0022] Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0023] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or selectively exclusive embodiment with other embodiments.

[0024] Embodiment 1

[0025] Refer to Figure 1 , which is the first embodiment of the present invention. This embodiment provides an air-conditioning automatic control method based on the cold and heat source machine room, including: S1: Collect the operation data of the cold and heat source machine room, where the operation data includes the outdoor temperature T1, relative humidity H1, supply water temperature T2, return water temperature T3, and equipment energy consumption data E1.

[0026] S1.1: Collect the outdoor temperature T1 through the temperature sensors arranged at the four directions and the top of the outer wall of the machine room.

[0027] S1.2: At the same time, collect the outdoor relative humidity H1 through the humidity sensors installed at the four directions of the outer wall of the machine room.

[0028] S1.3: Collect the supply water temperature T2 through the temperature sensors arranged at the outlet of the water supply pipeline.

[0029] S1.4: Collect the return water temperature T3 through the temperature sensors installed at the inlet of the return water pipeline.

[0030] S1.5: Collect the equipment energy consumption data E1 through the electric energy metering device installed at the power supply inlet of the cold and heat source unit.

[0031] It should be noted that the installation height of the outdoor temperature and humidity sensor is 2 meters from the ground and is installed in a louver box. The louver box has functions of rain protection, sun protection and ventilation to ensure that the measurement results are not affected by sunlight and rain; three temperature measurement points are evenly arranged along the circumferential direction of the water supply pipe outlet, and the included angle between the temperature measurement points is 120 degrees, which can accurately reflect the water supply temperature distribution; four temperature measurement points are evenly arranged along the circumferential direction of the water return pipe inlet, and the included angle between the temperature measurement points is 90 degrees to ensure the representativeness of the water return temperature sampling; the energy consumption data E1 collects the power consumption of each period in real time through the electric energy metering device, records the peak-valley power consumption value and its occurrence time, and generates a 24-hour energy consumption change trend curve.

[0032] Specifically, the collection interval of the operation data is once every 5 minutes and is transmitted to the control center through the RS485 communication protocol.

[0033] S2: Calculate the cold and heat source switching index K1 according to the deviation between the outdoor temperature T1 and the target temperature T0, combined with the change trend of the relative humidity H1.

[0034] S2.1: Perform spatial weighting processing on the outdoor temperature T1 by using the measurement point distance exponential attenuation method to obtain the weighted outdoor temperature value u.

[0035] S2.2: Multiply the difference between the weighted outdoor temperature value u and the target temperature T0 by the temperature distribution coefficient σ1 to calculate the temperature deviation ΔT, where the temperature distribution coefficient σ1 is determined by the dispersion degree of the temperature of each measurement point.

[0036] S2.3: Perform exponential decay superposition on the relative humidity H1 according to the sampling time sequence to obtain the humidity change index ΔH.

[0037] S2.4: Substitute the temperature deviation ΔT into the hyperbolic tangent function and output the temperature weight coefficient W1.

[0038] Preferably, the specific formula of the hyperbolic tangent function is as follows:

[0039] ;

[0040] Wherein, and are both temperature adjustment coefficients.

[0041] S2.5: At the same time, substitute the humidity change index ΔH into the exponential decay function and output the humidity weight coefficient W2.

[0042] Preferably, the specific formula of the exponential decay function is as follows:

[0043] ;

[0044] Among them, and are both humidity attenuation coefficients.

[0045] It should be noted that for the exponential decay superposition, the time step is 3 sampling periods; the value range of the temperature weight coefficient W1 is between 0.6 and 0.8; the value range of the humidity weight coefficient W2 is between 0.2 and 0.4.

[0046] S2.6: Substitute the temperature deviation ΔT, the humidity change index ΔH, the temperature weight coefficient W1, and the humidity weight coefficient W2 into the coupling calculation formula to obtain the cold and heat source switching index K1.

[0047] S3: When the cold and heat source switching index K1 exceeds the preset threshold, start the load prediction module to generate the load prediction value P1.

[0048] Preferably, the load prediction module includes a neural network model M1.

[0049] Specifically, the LSTM network structure of the neural network model M1 includes an input layer, an LSTM layer, a fully connected layer, and an output layer; the number of nodes in the input layer is 48, corresponding to the sampling data of the previous 12 hours; the LSTM layer contains two layers, the number of LSTM units in the first layer is 32, and the number of LSTM units in the second layer is 16; the number of nodes in the fully connected layer is 16; the number of nodes in the output layer is 12, corresponding to the load prediction value for the next 3 hours.

[0050] Furthermore, activation functions for the forget gate, input gate, and output gate are set in the LSTM layer. The forget gate and the input gate use the Sigmoid activation function, and the output gate uses the tanh activation function; the fully connected layer uses the ReLU activation function, and the output layer uses the linear activation function.

[0051] Even further, initialize the weight matrix, recurrence weight matrix, and bias vector of the LSTM layer. The weight matrix and the recurrence weight matrix are generated by the Xavier initialization method, and the initial value of the bias vector is set to zero.

[0052] S3.1: Divide the device energy consumption data E1 into several data segments according to the expected period, and obtain the sampling sequence S1 based on equidistant sampling.

[0053] Exemplarily, the device energy consumption data E1 is segmented with a 24-hour period, each segment of data is divided into 96 sampling points, and the time interval between sampling points is 15 minutes.

[0054] S3.2: Extract the energy consumption feature vector F1 according to the sampling sequence S1, where the energy consumption feature vector F1 includes the peak-to-valley ratio, the energy consumption slope, and the fluctuation coefficient.

[0055] S3.3: Select the historical data with the highest similarity to the energy consumption feature vector F1 from the historical database as the training sample set D1, where the similarity is calculated by the cosine value of the included angle of the feature vectors.

[0056] S3.4: Perform standardization processing on the training sample set D1 using the maximum-minimum normalization method to generate the standardized sample set D2.

[0057] S3.5: Based on the standardized sample set D2, construct and train the neural network model M1.

[0058] Specifically, divide the standardized sample set D2 into a training set and a validation set. The proportion of the training set is 80%, and the proportion of the validation set is 20%. Train the neural network model M1 using the batch gradient descent method. The number of training samples per batch is 64, and the initial value of the learning rate is 0.01. Specifically, it includes: a. Input the training set data into the neural network model M1 in the order of time series; b. Calculate the time series features through the LSTM layer; c. Use the mean squared error as the loss function to calculate the error between the predicted value and the true value; d. Calculate the gradients of the weight matrix, recurrent weight matrix, and bias vector through the time series backpropagation algorithm; e. Update the weight matrix, recurrent weight matrix, and bias vector.

[0059] Furthermore, after each training cycle, use the validation set to evaluate the performance of the neural network model M1. When the validation error no longer decreases for multiple consecutive cycles, stop training; save the network parameters of the trained neural network model M1.

[0060] S3.6: Input the sampled data of the device energy consumption data E1 into the trained neural network model M1 to output the load prediction value P1.

[0061] Even further, the operation logic of outputting the load prediction value P1 includes constructing a time series input vector from the most recent 48 sampled data of the device energy consumption data E1; performing standardization processing on the time series input vector to obtain a standardized input vector.

[0062] Specifically, input the standardized input vector into the neural network model M1. Specifically, it includes: a. Process the time series features through the first layer of LSTM units to obtain the first hidden state; b. Based on the first hidden state, further extract the time series features through the second layer of LSTM units to obtain the second hidden state; c. Input the second hidden state into the fully connected layer to obtain the first feature vector; calculate the output of the output layer according to the first feature vector.

[0063] Furthermore, perform anti-standardization processing on the output of the output layer to obtain the load prediction value P1.

[0064] S4: According to the load prediction value P1, control the water pump speed in a gradient adjustment manner, and dynamically adjust the valve opening V1 through the temperature difference between the supply water temperature T2 and the return water temperature T3.

[0065] S4.1: According to the load prediction value P1, control the water pump speed in a gradient adjustment manner.

[0066] S4.1.1: Divide the load prediction value P1 into several load intervals with the preset rated load as the step size, where the load interval corresponds to the reference water pump speed value N0.

[0067] S4.1.2: Calculate the relative position coefficient β1 of the load prediction value P1 within the current load interval, where the relative position coefficient β1 is the difference between the load prediction value P1 and the lower limit of the load interval divided by the length of the load interval.

[0068] S4.1.3: Substitute the relative position coefficient β1 into the cubic spline function to obtain the speed correction coefficient β2, where the speed correction coefficient β2 is used to smooth the speed change between adjacent load intervals.

[0069] S4.1.4: Multiply the reference water pump speed value N0 by the speed correction coefficient β2 to obtain the target water pump speed N1, and control the water pump speed to transition from the current water pump speed N2 to the target water pump speed N1 through a gradient adjustment manner.

[0070] Preferably, a. Calculate the speed adjustment gradient , where is the preset adjustment period; b. Within each control period, the water pump speed is gradually adjusted according to the speed adjustment gradient G1; c. When the water pump speed reaches the target water pump speed N1, the speed adjustment is completed.

[0071] Illustratively, when the load of the air conditioning system is 45% of the rated load, the load prediction value P1 is within the 40%-60% load interval, and the corresponding reference water pump speed value N0 is 1200 revolutions per minute; the calculated relative position coefficient β1 is 0.25; substituting the relative position coefficient β1 into the cubic spline function gives the speed correction coefficient β2 as 1.05; finally, the target water pump speed N1 is 1260 revolutions per minute. If the current water pump speed N2 is 1150 revolutions per minute and the preset adjustment period T is 60 seconds, then the speed adjustment gradient G1 is 1.83 revolutions per minute per second, and the water pump speed will be gradually adjusted in place within 60 seconds.

[0072] S4.2: Dynamically adjust the valve opening V1 through the temperature difference between the supply water temperature T2 and the return water temperature T3.

[0073] S4.2.1: Simultaneously calculate the temperature difference ΔT1 between the supply water temperature T2 and the return water temperature T3, and divide the temperature difference ΔT1 by the set temperature difference ΔT0 to obtain the temperature difference ratio R1.

[0074] S4.2.2: Substitute the temperature difference ratio R1 into the logarithmic function to obtain the valve opening correction coefficient α1, where the value range of the valve opening correction coefficient α1 is from 0.5 to 1.5.

[0075] S4.2.3: Multiply the current valve opening V0 by the valve opening correction coefficient α1 to obtain the valve opening V1.

[0076] Furthermore, when the temperature difference ratio R1 is less than the first preset threshold, it is determined that the refrigeration or heating efficiency of the air-conditioning system is insufficient, and the valve opening V1 is increased; when the temperature difference ratio R1 is greater than or equal to the first preset threshold and less than the second preset threshold, it is determined that the air-conditioning system is operating normally and there is no need to adjust the valve opening V1; when the temperature difference ratio R1 is greater than or equal to the second preset threshold, it is determined that the air-conditioning system is in a state of over-refrigeration or over-heating, and the valve opening V1 is decreased.

[0077] Exemplarily, in the refrigeration mode, the first preset threshold is set to 0.8 and the second preset threshold is set to 1.2. The valve opening is adjusted based on the temperature difference ratio R1: when the temperature difference ratio R1 is less than 0.8, it indicates that the actual temperature difference is lower than the target value (for example, when the target temperature difference is 8 °C, the measured value is only 5 °C, and R1 is equal to 0.625), it is determined that the refrigeration efficiency is insufficient and the valve opening V1 is increased; when the temperature difference ratio R1 is greater than or equal to 0.8 and less than 1.2 (for example, when the measured temperature difference is 9 °C, R1 is equal to 1.125), the system is in a normal state and V1 remains unchanged; when the temperature difference ratio R1 is greater than or equal to 1.2 (for example, when the measured temperature difference is 10 °C, resulting in R1 being equal to 1.25), it is determined that the refrigeration is excessive and V1 is decreased.

[0078] It should be noted that the first preset threshold is determined based on the minimum energy efficiency operation requirements of the air-conditioning system, and this threshold is used to determine whether the refrigeration or heating efficiency is insufficient; the second preset threshold is determined based on the optimal operation stable range of the air-conditioning system, and this threshold is used to determine whether the system enters a state of over-refrigeration or over-heating.

[0079] Furthermore, increasing the valve opening V1 includes determining whether the valve opening correction coefficient α1 is greater than 1; if the valve opening correction coefficient α1 is greater than 1, then multiply the current valve opening V0 by the valve opening correction coefficient α1 greater than 1 to obtain the corrected valve opening V2; by increasing the valve opening V2, improve the heat exchange efficiency of the cold and heat sources.

[0080] Specifically, decreasing the valve opening V1 includes determining whether the valve opening correction coefficient α1 is less than or equal to 1; if the valve opening correction coefficient α1 is less than or equal to 1, then multiply the current valve opening V0 by the valve opening correction coefficient α1 less than 1 to obtain the corrected valve opening V3; by decreasing the valve opening V3, reduce energy consumption.

[0081] Furthermore, record the temperature change curve and the equipment energy consumption data E1 during the adjustment process. When the outdoor temperature T1 is maintained within the error range of the target temperature T0, store the current control parameters in the optimization database.

[0082] Moreover, based on the 72 consecutive sampling point data of the outdoor temperature T1, construct a temperature response curve C1, where the sampling interval of the temperature response curve C1 is 5 minutes; calculate the overshoot τ1 and the adjustment time τ2 of the temperature response curve C1, and compare the overshoot τ1 with the preset overshoot limit value τ0.

[0083] It should be noted that the overshoot τ1 is the ratio of the maximum temperature deviation to the steady-state deviation; the adjustment time τ2 is the time required for the temperature to enter the steady state.

[0084] Preferably, when the overshoot τ1 is less than the preset overshoot limit value τ0 and the adjustment time τ2 is less than the preset time τ3, calculate the temperature control quality index Q1 and the cumulative energy consumption value E2 of the adjustment process, where the temperature control quality index Q1 is the weighted sum of the overshoot τ1 and the adjustment time τ2; the cumulative energy consumption value E2 is the integral value of the equipment energy consumption data E1 within the adjustment time τ2.

[0085] Specifically, construct a comprehensive evaluation index J1 based on the temperature control quality index Q1 and the cumulative energy consumption value E2, where the comprehensive evaluation index J1 is in the form of a normal distribution function.

[0086] Furthermore, when the outdoor temperature T1 is within the range of ±0.5°C of the target temperature T0 for more than 30 minutes and the comprehensive evaluation index J1 is greater than the threshold value J0, then form a control parameter group consisting of the target water pump speed N1, the target valve opening V1, the cold and heat source switching index K1, and the load prediction value P1, and store it in the optimization database.

[0087] In summary, through multi-parameter intelligent collaborative control, the present invention realizes the precise adaptive regulation of the cold and heat source machine room air conditioning system; adopts technologies such as multi-dimensional data acquisition, intelligent switching index calculation, neural network load prediction, and gradient adjustment, breaking through the limitations of traditional air conditioning control methods; establishes a mapping relationship between load change and speed adjustment based on load interval division and relative position coefficient calculation, and introduces a cubic spline function to ensure the smoothness of speed change, and at the same time adopts a gradient adjustment method to reduce equipment impact; compared with the prior art, this method performs early speed adjustment through the load prediction value, significantly improving the accuracy and response speed of system operation, and can accurately adjust the water pump speed and valve opening in real time and dynamically according to the changes of outdoor temperature and humidity and the operating characteristics of equipment, effectively solving the technical problems of inaccurate control and large energy consumption fluctuations in the air conditioning system.

[0088] Embodiment 2

[0089] This is the second embodiment of the present invention. This embodiment also provides an air-conditioning automatic control system based on a cold and heat source machine room, including:

[0090] An acquisition module, configured to acquire the operation data of the cold and heat source machine room, where the operation data includes the outdoor temperature T1, relative humidity H1, supply water temperature T2, return water temperature T3, and equipment energy consumption data E1;

[0091] A calculation module, configured to calculate a cold and heat source switching index K1 according to the deviation between the outdoor temperature T1 and the target temperature T0, in combination with the change trend of the relative humidity H1;

[0092] A generation module, configured to start a load prediction module and generate a load prediction value P1 when the cold and heat source switching index K1 exceeds a preset threshold;

[0093] An adjustment module, configured to control the water pump speed in a gradient adjustment manner according to the load prediction value P1, and dynamically adjust the valve opening V1 through the temperature difference between the supply water temperature T2 and the return water temperature T3.

[0094] It should be noted that the technical solution of the air-conditioning automatic control system based on the cold and heat source machine room belongs to the same concept as the technical solution of the above-mentioned air-conditioning automatic control method based on the cold and heat source machine room. For the details not described in detail in the technical solution of the air-conditioning automatic control system based on the cold and heat source machine room in this embodiment, reference can be made to the description of the technical solution of the above-mentioned air-conditioning automatic control method based on the cold and heat source machine room.

[0095] The above-mentioned each unit module can be embedded in the processor in the computer device in a hardware form or be independent of it, or can be stored in the memory in the computer device in a software form, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned each module.

[0096] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a multi-task edge computing resource scheduling method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0097] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by the processor, it implements the method proposed in the above embodiment.

[0098] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. For the technical details not described in detail in this embodiment, reference can be made to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0099] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk, or an optical disc of a computer, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method of the embodiments of the present invention.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0101] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0103] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0105] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0106] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An air-conditioning automatic control method based on a cold and heat source machine room, characterized in that: including, collecting the operation data of the cold and heat source machine room, where the operation data includes the outdoor temperature T1, relative humidity H1, supply water temperature T2, return water temperature T3, and equipment energy consumption data E1; calculating the cold and heat source switching index K1 according to the deviation between the outdoor temperature T1 and the target temperature T0 and in combination with the change trend of the relative humidity H1; when the cold and heat source switching index K1 exceeds a preset threshold, starting the load prediction module to generate a load prediction value P1; controlling the water pump speed in a gradient adjustment manner according to the load prediction value P1, and dynamically adjusting the valve opening V1 through the temperature difference between the supply water temperature T2 and the return water temperature T3; dividing the load prediction value P1 into several load intervals with a preset rated load as the step size, where the load intervals correspond to the reference water pump speed value N0; calculating the relative position coefficient β1 of the load prediction value P1 within the current load interval, where the relative position coefficient β1 is the difference between the load prediction value P1 and the lower limit of the load interval divided by the length of the load interval; substituting the relative position coefficient β1 into a cubic spline function to obtain a speed correction coefficient β2, where the speed correction coefficient β2 is used to smooth the speed change between adjacent load intervals; multiplying the reference water pump speed value N0 by the speed correction coefficient β2 to obtain the target water pump speed N1, and controlling the water pump speed to transition from the current water pump speed N2 to the target water pump speed N1 through a gradient adjustment method; simultaneously calculating the temperature difference ΔT1 between the supply water temperature T2 and the return water temperature T3, and dividing the temperature difference ΔT1 by the set temperature difference ΔT0 to obtain a temperature difference ratio R1; substituting the temperature difference ratio R1 into a logarithmic function to obtain a valve opening correction coefficient α1; multiplying the current valve opening V0 by the valve opening correction coefficient α1 to obtain the valve opening V1; the method for collecting the operation data is collecting the outdoor temperature T1 through temperature sensors arranged at four directions and the top of the machine room outer wall; collecting the outdoor relative humidity H1 through humidity sensors installed at four directions of the machine room outer wall; collecting the supply water temperature T2 through temperature sensors arranged at the outlet of the water supply pipeline; collecting the return water temperature T3 through temperature sensors installed at the inlet of the return water pipeline; collecting the equipment energy consumption data E1 through an electric energy metering device installed at the power supply inlet end of the cold and heat source unit; the humidity sensor and the temperature sensor are integrated in the same measurement unit; there are three temperature measurement points distributed in a fan shape at the outlet of the water supply pipeline; there are several temperature measurement points evenly distributed at the inlet of the return water pipeline; the energy consumption data E1 includes the electricity consumption in each period, peak and valley values, and change trends.

2. The air-conditioning automatic control method based on a cold and heat source machine room according to claim 1, characterized in that: also including when the temperature difference ratio R1 is less than a first preset threshold, it is determined that the refrigeration or heating efficiency of the air conditioning system is insufficient, and the valve opening V1 is increased; when the temperature difference ratio R1 is greater than or equal to the first preset threshold and less than a second preset threshold, it is determined that the air conditioning system is operating normally, and there is no need to adjust the valve opening V1; when the temperature difference ratio R1 is greater than or equal to the second preset threshold, it is determined that the air conditioning system is in a state of over-refrigeration or over-heating, and the valve opening V1 is decreased.

3. The air-conditioning automatic control method based on a cold and heat source machine room according to claim 2, wherein: The method for generating the load prediction value P1 is as follows: The device energy consumption data E1 is divided into several data segments according to the expected period, and a sampling sequence S1 is obtained based on equidistant sampling. An energy consumption feature vector F1 is extracted according to the sampling sequence S1, where the energy consumption feature vector F1 includes the peak-to-valley ratio, energy consumption slope, and fluctuation coefficient. The historical data with the highest similarity to the energy consumption feature vector F1 is selected from the historical database as the training sample set D1, where the similarity is calculated by the cosine value of the included angle of the feature vectors. The training sample set D1 is standardized using the maximum-minimum normalization method to generate a standardized sample set D2. Based on the standardized sample set D2, a neural network model M1 is constructed and trained. The sampling point data of the device energy consumption data E1 is input into the trained neural network model M1, and the load prediction value P1 is output.

4. The air-conditioning automatic control method based on a cold and heat source machine room according to claim 3, characterized in that: According to the deviation between the outdoor temperature T1 and the target temperature T0, combined with the change trend of the relative humidity H1, the cold and heat source switching index K1 is calculated, including: The outdoor temperature T1 is spatially weighted using the measurement point distance exponential decay method to obtain the weighted outdoor temperature value u. Based on the difference between the weighted outdoor temperature value u and the target temperature T0, the temperature deviation ΔT is calculated by multiplying by the temperature distribution coefficient σ1, where the temperature distribution coefficient σ1 is determined by the dispersion degree of the temperatures at each measurement point. The relative humidity H1 is exponentially decayed and superimposed according to the sampling time series to obtain the humidity change index ΔH. The temperature deviation ΔT is substituted into the hyperbolic tangent function to output the temperature weight coefficient W1. At the same time, the humidity change index ΔH is substituted into the exponential decay function to output the humidity weight coefficient W2. The temperature deviation ΔT, the humidity change index ΔH, the temperature weight coefficient W1, and the humidity weight coefficient W2 are substituted into the coupling calculation formula to obtain the cold and heat source switching index K1.

5. An air-conditioning automatic control system based on a cold and heat source machine room, based on the air-conditioning automatic control method based on a cold and heat source machine room according to any one of claims 1 to 4, characterized in that: Including: A collection module for collecting the operation data of the cold and heat source machine room, where the operation data includes the outdoor temperature T1, relative humidity H1, supply water temperature T2, return water temperature T3, and device energy consumption data E1. A calculation module for calculating the cold and heat source switching index K1 according to the deviation between the outdoor temperature T1 and the target temperature T0, combined with the change trend of the relative humidity H1. A generation module for starting the load prediction module to generate the load prediction value P1 when the cold and heat source switching index K1 exceeds a preset threshold. An adjustment module for controlling the water pump speed in a gradient adjustment manner according to the load prediction value P1, and dynamically adjusting the valve opening V1 through the temperature difference between the supply water temperature T2 and the return water temperature T3.

6. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the air-conditioning automatic control method based on the cold and heat source machine room according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the air-conditioning automatic control method based on the cold and heat source machine room according to any one of claims 1 to 4.

Images