Air conditioner refrigeration performance testing method and system

Abstract

The application discloses a kind of air conditioner refrigeration performance test method and system, it is related to air conditioner performance test technical field, including, based on thermal characteristic parameter matrix, through air conditioner three-dimensional model mapping and multi-physical field coupling simulation, CFD simulation is executed to air conditioner refrigeration process, the frost wind index of evaporator under different loads and surge critical value are predicted, and air conditioner performance optimization test instruction is generated;According to air conditioner performance optimization test instruction, execute first dynamic thermal load test and obtain physical test data set, and deviation correction is carried out to air conditioner performance optimization test instruction by intelligent dynamic compensation algorithm;Through the air conditioner performance optimization test instruction after correction, execute second dynamic thermal load test, and generate refrigeration performance test report.Through the deep feature extraction of enhanced physical test data set and dynamic load correlation analysis, intelligent evaluation and optimization control of air conditioner refrigeration performance are realized.

Description

Technical Field

[0001] This invention relates to the field of air conditioning performance testing technology, and in particular to an air conditioning refrigeration performance testing method and system. Background Technology

[0002] Air conditioning cooling performance testing is a key technical aspect of the HVAC industry. Existing methods typically establish a testing system under steady-state operating conditions based on standards such as ISO 5151 and ASHRAE 37. Conventional technical solutions combine computational fluid dynamics (CFD) simulation with experimental verification. This involves constructing a geometric model of the air conditioning system, loading rated operating parameters, and simulating single-physics fields (such as temperature or flow fields) to predict evaporator frosting tendency and compressor surge boundaries. During testing, basic data is collected using temperature and pressure sensors under fixed load conditions, and empirical formulas are used to evaluate the coefficient of performance (COP) and reliability indicators.

[0003] However, the above-mentioned conventional methods have limitations in two aspects: insufficient adaptability to dynamic operating conditions: static simulation models are difficult to accurately simulate the transient thermal response characteristics of air conditioners when operating under varying loads, especially the nonlinear characteristics of evaporator frosting risk changing with load, which have limited accuracy in capturing these characteristics, leading to deviations in frosting index prediction; fragmented multi-field coupled data: existing testing systems rely on step-by-step acquisition of single-mode data such as temperature and pressure, and fail to establish cross-scale correlations between refrigerant flow field pulsation and mechanical vibration, which restricts the timeliness and accuracy of surge critical point identification. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an air conditioning cooling performance testing method to solve the problems of insufficient adaptability to dynamic operating conditions and the frosting prediction deviation caused by the fragmentation of multi-field coupled data.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for testing the cooling performance of an air conditioner, comprising,

[0008] Collect current frequency control parameters and building thermophysical property data, and construct a thermal property parameter matrix through a multi-parameter coupling algorithm;

[0009] Based on the thermal characteristic parameter matrix, CFD simulation of the air conditioning cooling process is performed through air conditioning three-dimensional model mapping and multi-physics field coupling simulation. The evaporator frosting wind index and surge critical value under different loads are predicted, and air conditioning performance optimization test instructions are generated.

[0010] According to the air conditioner performance optimization test instruction, the first dynamic heat load test is performed and the physical test dataset is obtained. The deviation of the air conditioner performance optimization test instruction is corrected by the intelligent dynamic compensation algorithm.

[0011] The second dynamic heat load test was performed using the revised air conditioning performance optimization test instructions, and a cooling performance test report was generated.

[0012] As a preferred embodiment of the air conditioning cooling performance testing method of the present invention, the current frequency control parameter refers to adjusting the alternating frequency of the electromagnetic field in the phase change energy storage tank by adjusting the frequency converter.

[0013] The building's thermophysical properties include its heat capacity, thermal conductivity, and thermal response time.

[0014] As a preferred embodiment of the air conditioning cooling performance testing method of the present invention, the steps for constructing the thermal characteristic parameter matrix through a multi-parameter coupling algorithm are as follows:

[0015] The finite volume method is used to perform non-uniform meshing and second-order implicit time discretization on the current frequency control parameters and the thermophysical properties of the building to generate thermal response characteristic data.

[0016] By combining thermal response characteristic data with thermophysical characteristic data, the frequency-heat capacity correlation is established using the least squares method, and the thermal conductivity correction term is coupled with the thermal response time to construct a thermal characteristic parameter matrix.

[0017] As a preferred embodiment of the air conditioning cooling performance testing method of the present invention, the steps of performing CFD simulation on the air conditioning cooling process through three-dimensional model mapping and multiphysics coupling simulation to predict the evaporator frosting wind index and surge critical value under different loads are as follows:

[0018] Reverse engineering is used to scan and obtain solid point cloud data. Surface reconstruction and parametric modeling are performed using CAD to generate an air conditioner model framework.

[0019] The thermal characteristic parameter matrix is ​​mapped to the air conditioning model framework as physical field boundary conditions through the parameterized topology mapping algorithm, thus forming the three-dimensional model of the air conditioner.

[0020] Based on the three-dimensional model of the air conditioner, CFD simulation of the air conditioning cooling process was performed through multi-physics field coupling simulation, and data on the temperature field distribution of the evaporator surface, the refrigerant pressure pulsation frequency, and the flow velocity field were collected.

[0021] Based on the temperature field distribution and flow velocity field data of the evaporator surface, the temperature field gradient analysis method combined with the joint judgment of Knudsen number and Lewis number is used to predict the evaporator frosting risk index under different loads.

[0022] Based on the refrigerant pressure pulsation frequency, a nonlinear dynamic stability analysis method is used, combined with phase space reconstruction and Lyapunov exponent calculation, to predict the surge critical value under different loads.

[0023] In a preferred embodiment of the air conditioning cooling performance testing method of the present invention, the steps for generating air conditioning performance optimization test instructions are as follows:

[0024] Principal component analysis was used to correlate the evaporator frosting wind index and surge critical value under different loads with the air conditioning operating condition parameters in the CFD simulation process in multiple dimensions, so as to obtain the comprehensive performance index vector after dimensionality reduction.

[0025] Based on the dimensionality-reduced comprehensive performance index vector, a genetic algorithm is used to search for the optimal solution in the controllable parameter space to generate air conditioning performance optimization test instructions.

[0026] In a preferred embodiment of the air conditioning cooling performance testing method of the present invention, the steps of performing the first dynamic heat load test and acquiring the physical test dataset, and correcting the deviation of the air conditioning performance optimization test command through an intelligent dynamic compensation algorithm are as follows:

[0027] According to the air conditioning performance optimization test instructions, the compressor frequency, expansion valve opening and fan speed parameters are defined, the first dynamic heat load test is performed, and the measured values ​​of evaporator surface temperature field distribution, refrigerant pressure pulsation frequency and flow velocity field are collected in real time to form a physical test dataset.

[0028] The measured values ​​in the physical test dataset are compared point by point with the evaporator surface temperature field distribution, refrigerant pressure pulsation frequency and flow velocity field data in the CFD simulation process to obtain the three-dimensional deviation matrix of temperature, pressure and flow velocity.

[0029] Based on the three-dimensional deviation matrix, an intelligent dynamic compensation algorithm based on fuzzy PID control is used to dynamically correct the air conditioner performance optimization test command.

[0030] In a preferred embodiment of the air conditioning cooling performance testing method of the present invention, the steps of performing a second dynamic heat load test and generating a cooling performance test report using the modified air conditioning performance optimization test command are as follows.

[0031] Based on the revised air conditioning performance optimization test instructions, a dynamic load change curve is constructed using a near-end strategy optimization algorithm.

[0032] Based on the dynamic load change curve, a second dynamic thermal load test was performed, and infrared thermal imaging data, ultrasonic flow velocity distribution and vibration spectrum data were collected in real time to generate an enhanced physical test dataset.

[0033] Based on the enhanced physical test dataset, performance features are extracted through wavelet packet decomposition;

[0034] A DNN is used to establish the temporal correlation between the enhanced physical test dataset and the dynamic load change curve, and feature tensor convolution aggregation is performed to predict the cooling performance score of the air conditioner.

[0035] A cooling performance test report is generated based on the dynamic load change curve, the air conditioner's cooling performance score, the evaporator frosting wind index and surge critical value under different loads.

[0036] In a second aspect, the present invention provides an air conditioning cooling performance testing system, including a data acquisition module for acquiring current frequency control parameters and building thermophysical characteristic data, and constructing a thermal characteristic parameter matrix through a multi-parameter coupling algorithm;

[0037] The simulation module is used to perform CFD simulation on the air conditioning cooling process based on the thermal characteristic parameter matrix, through the mapping of the air conditioning three-dimensional model and multi-physics field coupling simulation, to predict the evaporator frosting wind index and surge critical value under different loads, and generate air conditioning performance optimization test instructions.

[0038] The instruction correction module is used to perform the first dynamic heat load test and obtain the physical test dataset according to the air conditioner performance optimization test instruction, and to correct the deviation of the air conditioner performance optimization test instruction through an intelligent dynamic compensation algorithm.

[0039] The report generation module is used to perform a second dynamic heat load test using the revised air conditioning performance optimization test instructions, and generate a cooling performance test report.

[0040] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein the computer program, when executed by the processor, implements any step of the air conditioning cooling performance testing method as described in the first aspect of the present invention.

[0041] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein, when the computer program is executed by a processor, it implements any step of the air conditioning cooling performance testing method as described in the first aspect of the present invention.

[0042] The beneficial effects of this invention are as follows: Through multi-physics field coupling simulation based on thermal characteristic parameter matrix, dynamic interactive modeling of electromagnetic field-thermal field-flow field is realized, and the risk of evaporator frosting and surge critical value are accurately predicted; through deep feature extraction and dynamic load correlation analysis of enhanced physical test dataset, intelligent evaluation and optimization control of air conditioning cooling performance are realized. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart of the air conditioning cooling performance testing method;

[0045] Figure 2 Schematic diagram of an air conditioning cooling performance testing system;

[0046] Figure 3 A flowchart for generating air conditioner performance optimization test instructions;

[0047] Figure 4 This is a flowchart of the second dynamic thermal load test. Detailed Implementation

[0048] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0049] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0051] Reference Figures 1-4 As one embodiment of the present invention, this embodiment provides a method for testing the cooling performance of an air conditioner, comprising the following steps:

[0052] S1. Collect current frequency control parameters and building thermophysical property data, and construct a thermal property parameter matrix through a multi-parameter coupling algorithm;

[0053] Current frequency control parameters refer to adjusting the alternating frequency of the electromagnetic field in the phase change energy storage tank by using a frequency converter.

[0054] It should be noted that the acquisition process for the current frequency control parameters is as follows: A high-precision frequency acquisition device is connected to the output port of the inverter power supply to record the alternating frequency variation curve of the electromagnetic field in the phase change energy storage tank in real time. The sampling frequency is set to 10kHz to ensure the capture of complete harmonic components. During the acquisition process, ambient temperature and power supply voltage fluctuation data are recorded simultaneously. The acquisition duration of the current frequency control parameters is the entire cooling cycle of the air conditioning system. After FFT transformation, the fundamental frequency and the amplitude of the main harmonic components are extracted as valid parameters.

[0055] Thermophysical properties of a building include its heat capacity, thermal conductivity, and thermal response time.

[0056] It should be noted that the process of collecting the thermophysical properties data of the building is as follows: the heat capacity and thermal conductivity of the building envelope are measured by the transient plane heat source method, the test probe is heated with constant power and the temperature response curve is recorded, and the thermal conductivity matrix is ​​obtained by inversion; the thermal response time is determined by a step temperature excitation experiment.

[0057] The finite volume method is used to perform non-uniform meshing and second-order implicit time discretization on the current frequency control parameters and the thermophysical properties of the building to generate thermal response characteristic data.

[0058] Furthermore, unstructured meshing was implemented for the current frequency control parameters and the building's thermophysical properties data within the three-dimensional computational domain. The mesh density was refined to 0.5 mm in the boundary layer region of the phase change energy storage tank, while a progressively denser mesh transition was adopted in the building envelope region. The electromagnetic field control equations for the current frequency control parameters and the heat transfer equations for the building's thermophysical properties data were synchronously discretized using a coupled solver, with the time step controlled within the range of 1e-3 to 1e-5 seconds using an adaptive algorithm. A second-order implicit time discretization scheme was applied to process the transient terms, generating thermal response characteristic data that included the temperature gradient field, heat flux density distribution, and phase change rate.

[0059] By combining thermal response characteristic data with thermophysical characteristic data, the frequency-heat capacity correlation is established using the least squares method, and the thermal conductivity correction term is coupled with the thermal response time to construct a thermal characteristic parameter matrix.

[0060] Furthermore, the temperature fluctuation amplitude in the thermal response characteristic data and the heat capacity parameter in the building's thermophysical characteristic data are fitted using weighted least squares to establish a frequency-heat capacity correlation polynomial function. The thermal conductivity correction term is updated driven by the heat flux density anomaly region identification results in the thermal response characteristic data, and the correction coefficient is embedded in the thermal conductivity matrix in exponential form. The thermal response time is used as a time scale factor and tensor multiplied with the frequency-heat capacity relationship to finally form a thermal characteristic parameter matrix containing 12 dimensions, each representing the dynamic response of the electromagnetic-thermal-structural coupling field at different frequency bands.

[0061] It should be noted that the thermal conductivity correction term is a gradient compensation coefficient generated by dynamically comparing the results of identifying abnormal heat flux density areas in the thermal response characteristic data with the benchmark value of thermal conductivity in the building's thermophysical characteristic data.

[0062] S2. Based on the thermal characteristic parameter matrix, CFD simulation is performed on the air conditioning cooling process through air conditioning three-dimensional model mapping and multi-physics field coupling simulation to predict the evaporator frosting wind index and surge critical value under different loads, and generate air conditioning performance optimization test instructions.

[0063] Reverse engineering is used to scan and obtain solid point cloud data. Surface reconstruction and parametric modeling are performed using CAD to generate an air conditioner model framework.

[0064] Furthermore, a laser 3D scanner was used to collect multi-angle point cloud data of the air conditioner entity. The point cloud data was then used to generate a continuous surface model using the NURBS surface reconstruction algorithm in CAD software. Key feature lines were optimized through B-spline curve fitting. The parametric modeling process defined feature parameters such as compressor interface and evaporator flow channel to drive dimensions, ultimately generating the air conditioner model framework.

[0065] The thermal characteristic parameter matrix is ​​mapped to the air conditioning model framework as physical field boundary conditions through the parameterized topology mapping algorithm, thus forming the three-dimensional model of the air conditioner.

[0066] Furthermore, the parametric topology mapping algorithm decomposes the thermal characteristic parameter moments into three sets of physical field variables: electromagnetic field strength, heat flux density, and phase delay. The nodal data of the thermal characteristic parameter matrix are accurately mapped to the corresponding mesh elements of the air conditioner model framework using a finite element interpolation function. Boundary conditions are applied using a Dirichlet-Neumann hybrid format. The final structure of the air conditioner 3D model comprises three levels of data: geometric entities, material property distribution, and dynamic boundary conditions.

[0067] Based on the three-dimensional model of the air conditioner, CFD simulation of the air conditioning cooling process was performed through multi-physics field coupling simulation, and data on the temperature field distribution of the evaporator surface, the refrigerant pressure pulsation frequency, and the flow velocity field were collected.

[0068] Furthermore, after importing the 3D model of the air conditioner into the CFD solver, a coupled electromagnetic-thermal-fluid three-field solver was set up. The governing equations included Maxwell's equations, Navier-Stokes equations, and Fourier heat conduction equations. The coupled solution adopted a step-by-step iterative algorithm, completing three iterations of electromagnetic field calculation, flow field update, and temperature field correction at each time step. During the simulation, real-time data were collected on the evaporator surface temperature field distribution, refrigerant pressure pulsation frequency, and flow velocity field.

[0069] Based on the temperature field distribution and velocity field data of the evaporator surface, the temperature field gradient analysis method combined with the joint judgment of Knudsen number and Lewis number is used to predict the evaporator frosting risk index under different loads. The expression is:

[0070] ;

[0071] in, It is the evaporator frosting risk index under the i-th load. It is an empirical correction factor (with a value range of 0.5 ≤ ≤1.8), It is the ratio of the gas molecule free path to the characteristic scale of the evaporator surface under the i-th load. It is the critical threshold of the Knudsen number (within the range of 0.001 ≤ ≤0.1), It is the temperature sensitivity coefficient (with a value range of 0.2≤...). ≤0.8), It is the evaporator surface temperature under the i-th load. It is the air dew point temperature. It is the reference temperature for the difference between the evaporator surface temperature and the dew point temperature. This is the weighting coefficient for the temperature gradient (within the range of 0.05 ≤ 0.05). ≤0.3), It is the temperature gradient on the evaporator surface. It is the critical threshold of the temperature gradient (within the range of 2.5 ≤ ≤4.0);

[0072] It should be noted that the critical threshold of the Knudsen number is defined based on molecular dynamics simulations and high-speed microscopy imaging experimental data;

[0073] The critical threshold of the temperature gradient is defined based on historical experimental data and CFD simulation verification results;

[0074] Based on the refrigerant pressure pulsation frequency, a nonlinear dynamic stability analysis method, combined with phase space reconstruction and Lyapunov exponent calculation, is used to predict the surge critical value under different loads. The expression is as follows:

[0075] ;

[0076] in, It is the surge critical value under the i-th load. It is an empirical correction factor for the damping ratio (within the range of 0.1 ≤ ≤1.5), It is the pressure pulsation amplitude under the i-th load. It is the reference pressure pulsation amplitude. It is the dominant frequency of pressure pulsation under the i-th type of load. It is the compressor's natural frequency. It is the pressure loss sensitivity coefficient (with a value range of 0.02≤...). ≤0.15), It is the pressure difference between the inlet and outlet of the evaporator under the i-th load. It is the reference pressure under rated load.

[0077] It should be noted that before predicting the evaporator frosting risk index and surge critical value under different loads, all parameters involved in the calculation process were standardized by Z-score to achieve dimensional uniformity of all parameters in the expression.

[0078] Principal component analysis was used to correlate the evaporator frosting wind index and surge critical value under different loads with the air conditioning operating condition parameters in the CFD simulation process in multiple dimensions, so as to obtain the comprehensive performance index vector after dimensionality reduction.

[0079] Furthermore, the evaporator frosting wind index and surge threshold under different loads were combined with the air conditioning operating parameters (including compressor frequency, expansion valve opening, fan speed, evaporator inlet temperature, and refrigerant flow rate) from the CFD simulation to construct a multidimensional data matrix. KL transform was used to orthogonally decompose the multidimensional data matrix, retaining the top three principal components with the largest cumulative contribution. During principal component analysis, the evaporator frosting wind index and surge threshold were Z-score standardized to ensure uniformity of dimensions. The final generated comprehensive performance index vector contains three orthogonal eigencomponents: the first principal component (thermodynamic stability factor), the second principal component (flow uniformity index), and the third principal component (dynamic response coefficient). The weight coefficients of each component were determined through eigenvalue normalization.

[0080] Based on the dimensionality-reduced comprehensive performance index vector, a genetic algorithm is used to search for the optimal solution in the controllable parameter space to generate air conditioning performance optimization test instructions.

[0081] Furthermore, based on the dimensionality-reduced comprehensive performance index vector, within the three-dimensional parameter space composed of compressor frequency, expansion valve opening, and fan speed, the population is initialized using real-number encoding, and parameter optimization is achieved through simulated binary crossover and boundary mutation operators. The fitness function uses the reciprocal of the Euclidean distance of the comprehensive performance index vector as the optimization objective, employing a tournament selection strategy to retain elite individuals. Iteration terminates when the fitness change rate falls below a threshold for several consecutive generations, ultimately outputting an air conditioning performance optimization test instruction containing the optimal combination of compressor frequency, expansion valve opening, and fan speed.

[0082] It should be noted that the controllable parameter space refers to the three-dimensional optimization domain formed by the compressor frequency range, expansion valve opening range, and fan speed range.

[0083] S3. According to the air conditioner performance optimization test instruction, perform the first dynamic heat load test and obtain the physical test dataset, and correct the deviation of the air conditioner performance optimization test instruction through the intelligent dynamic compensation algorithm.

[0084] According to the air conditioning performance optimization test instructions, the compressor frequency, expansion valve opening and fan speed parameters are defined, the first dynamic heat load test is performed, and the measured values ​​of evaporator surface temperature field distribution, refrigerant pressure pulsation frequency and flow velocity field are collected in real time to form a physical test dataset.

[0085] Furthermore, based on the compressor frequency setpoint, expansion valve opening percentage, and fan operating speed parameters defined in the air conditioning performance optimization test instructions, corresponding operating conditions were configured on the test bench. During the test, an infrared thermal imager was used to record the measured values ​​of the evaporator surface temperature field distribution at fixed sampling intervals. Simultaneously, a high-frequency pressure sensor was used to collect the measured values ​​of the refrigerant pressure pulsation frequency, and particle image velocimetry technology was used to obtain the measured values ​​of the flow velocity field. All data streams were timestamped and stored as a physical test dataset containing spatial coordinates, time series, and physical quantity values.

[0086] The measured values ​​in the physical test dataset are compared point by point with the evaporator surface temperature field distribution, refrigerant pressure pulsation frequency and flow velocity field data in the CFD simulation process to obtain the three-dimensional deviation matrix of temperature, pressure and flow velocity.

[0087] Furthermore, point-by-point difference calculations were performed between the measured values ​​of the evaporator surface temperature field distribution in the physical test dataset and the CFD simulation temperature field data at the same grid node locations. The measured values ​​of the refrigerant pressure pulsation frequency were compared with the simulated spectrum data using frequency domain characteristics obtained through Fast Fourier Transform. The measured values ​​of the flow velocity field were analyzed for differences with the simulated flow field data using both vector angle and modulus. The three types of deviation data were reorganized according to spatial topological relationships into a three-dimensional deviation matrix consisting of a temperature deviation layer, a pressure deviation layer, and a flow velocity deviation layer. The dimensions of the three-dimensional deviation matrix were completely consistent with the CFD simulation grid.

[0088] Based on the three-dimensional deviation matrix, an intelligent dynamic compensation algorithm based on fuzzy PID control is used to dynamically correct the air conditioner performance optimization test command.

[0089] Furthermore, based on the temperature deviation, pressure pulsation frequency deviation, and flow velocity deviation data in the three-dimensional deviation matrix, the fuzzy PID control algorithm first converts each deviation quantity into fuzzy linguistic variables through a Gaussian membership function. Then, it activates a predefined library of 128 multivariable coupled control rules to perform Mamdani inference operations. The rule library fully covers the entire combined state space of temperature-pressure-flow velocity. In the defuzzification stage, the area center method is used to generate accurate compressor frequency compensation, expansion valve opening adjustment, and fan speed correction, ultimately achieving dynamic correction of the air conditioning performance optimization test command.

[0090] S4. Using the revised air conditioning performance optimization test command, perform the second dynamic heat load test and generate a cooling performance test report.

[0091] Based on the revised air conditioning performance optimization test instructions, a dynamic load change curve is constructed using the near-end strategy optimization algorithm (PPO).

[0092] Furthermore, the Proximal Policy Optimization (PPO) algorithm receives the corrected air conditioning performance optimization test instructions as initial policy parameters. Within the action space defined by compressor frequency, expansion valve opening, and fan speed, it outputs continuous action values ​​through a policy network. The PPO algorithm uses an objective function with importance sampling for policy updates, ultimately generating a smooth dynamic load change curve.

[0093] Based on the dynamic load change curve, a second dynamic thermal load test was performed, and infrared thermal imaging data, ultrasonic flow velocity distribution and vibration spectrum data were collected in real time to generate an enhanced physical test dataset.

[0094] Furthermore, after the dynamic load change curve is converted into a time-parameter sequence, the experimental bench is driven to perform a second dynamic thermal load test. An infrared thermal imager captures the temperature field distribution on the evaporator surface at fixed sampling intervals, an ultrasonic flowmeter measures the refrigerant flow vector field, and a vibration sensor array acquires the vibration spectrum of the compressor casing. After the three types of data are aligned using a time synchronization protocol, they are fused into an enhanced physical test dataset that includes temperature-flow-vibration coupling characteristics.

[0095] Based on the enhanced physical test dataset, performance features are extracted through wavelet packet decomposition;

[0096] Furthermore, based on the enhanced physical test dataset, the wavelet packet decomposition feature extraction process first performs normalization preprocessing on the original data to eliminate the dimensional differences of different physical quantities and fill in the missing sampling points; then, it uses the Daubechies4 wavelet basis function to perform a 5-level full decomposition to generate a complete wavelet packet tree structure containing 32 terminal nodes. The time-frequency coefficients of each node are obtained through the Mallet algorithm to obtain performance characteristics including temperature field uniformity, flow velocity stability and vibration intensity.

[0097] A DNN is used to establish the temporal correlation between the enhanced physical test dataset and the dynamic load change curve, and feature tensor convolution aggregation is performed to predict the cooling performance score of the air conditioner. The expression is as follows:

[0098] ;

[0099] Where H represents the air conditioner's cooling performance rating. is the weight coefficient of the nth feature channel (within the range of [0, 1]), N is the total number of feature channels, and V is the feature value obtained by performing feature tensor convolution on the performance features. It is the performance characteristic at time t. The dynamic load change curve is in The time window segment reflects the temporal changes of control parameters such as compressor frequency and expansion valve opening during the test process, where g is a fixed time period.

[0100] A cooling performance test report is generated based on the dynamic load change curve, the air conditioner's cooling performance score, the evaporator frosting wind index and surge critical value under different loads.

[0101] This embodiment also provides an air conditioning cooling performance testing system, including: a data acquisition module, used to acquire current frequency control parameters and building thermophysical characteristic data, and to construct a thermal characteristic parameter matrix through a multi-parameter coupling algorithm;

[0102] The simulation module is used to perform CFD simulation on the air conditioning cooling process based on the thermal characteristic parameter matrix, through the mapping of the air conditioning three-dimensional model and multi-physics field coupling simulation, to predict the evaporator frosting wind index and surge critical value under different loads, and generate air conditioning performance optimization test instructions.

[0103] The instruction correction module is used to perform the first dynamic heat load test and obtain the physical test dataset according to the air conditioner performance optimization test instruction, and to correct the deviation of the air conditioner performance optimization test instruction through an intelligent dynamic compensation algorithm.

[0104] The report generation module is used to perform a second dynamic heat load test using the revised air conditioning performance optimization test instructions, and generate a cooling performance test report.

[0105] This embodiment also provides a computer device applicable to the air conditioning cooling performance testing method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the air conditioning cooling performance testing method proposed in the above embodiment.

[0106] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0107] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the air conditioning cooling performance testing method proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0108] In summary, this invention achieves dynamic interactive modeling of electromagnetic field, thermal field, and flow field through multi-physics field coupled simulation based on thermal characteristic parameter matrix, accurately predicting evaporator frosting risk and surge threshold; and realizes intelligent evaluation and optimized control of air conditioning cooling performance through deep feature extraction and dynamic load correlation analysis of enhanced physical test dataset.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for testing the cooling performance of an air conditioner, characterized in that: include, Collect current frequency control parameters and building thermophysical property data, and construct a thermal property parameter matrix through a multi-parameter coupling algorithm; Based on the thermal characteristic parameter matrix, CFD simulation of the air conditioning cooling process is performed through 3D model mapping and multiphysics coupling simulation. This predicts the evaporator frosting wind index and surge threshold under different loads, and generates air conditioning performance optimization test instructions. The steps are as follows. Reverse engineering is used to scan and obtain solid point cloud data. Surface reconstruction and parametric modeling are performed using CAD to generate an air conditioner model framework. The thermal characteristic parameter matrix is ​​mapped to the air conditioning model framework as physical field boundary conditions through the parameterized topology mapping algorithm, thus forming the three-dimensional model of the air conditioner. Based on the three-dimensional model of the air conditioner, CFD simulation of the air conditioning cooling process was performed through multi-physics field coupling simulation, and data on the temperature field distribution of the evaporator surface, the refrigerant pressure pulsation frequency, and the flow velocity field were collected. Based on the temperature field distribution and flow velocity field data of the evaporator surface, the temperature field gradient analysis method combined with the joint judgment of Knudsen number and Lewis number is used to predict the evaporator frosting risk index under different loads. Based on the refrigerant pressure pulsation frequency, a nonlinear dynamic stability analysis method is used, combined with phase space reconstruction and Lyapunov exponent calculation, to predict the surge critical value under different loads. Principal component analysis was used to correlate the evaporator frosting wind index and surge critical value under different loads with the air conditioning operating condition parameters in the CFD simulation process in multiple dimensions, so as to obtain the comprehensive performance index vector after dimensionality reduction. Based on the dimensionality-reduced comprehensive performance index vector, a genetic algorithm is used to search for the optimal solution in the controllable parameter space to generate air conditioning performance optimization test instructions. According to the air conditioner performance optimization test instruction, the first dynamic heat load test is performed and the physical test dataset is obtained. The deviation of the air conditioner performance optimization test instruction is corrected by the intelligent dynamic compensation algorithm. The second dynamic heat load test was performed using the revised air conditioning performance optimization test instructions, and a cooling performance test report was generated.

2. The air conditioning cooling performance testing method as described in claim 1, characterized in that: The current frequency control parameter refers to adjusting the alternating frequency of the electromagnetic field in the phase change energy storage tank by using a frequency converter. The building's thermophysical properties include its heat capacity, thermal conductivity, and thermal response time.

3. The air conditioning cooling performance testing method as described in claim 2, characterized in that: The steps for constructing the thermal characteristic parameter matrix using a multi-parameter coupling algorithm are as follows: The finite volume method is used to perform non-uniform meshing and second-order implicit time discretization on the current frequency control parameters and the thermophysical properties of the building to generate thermal response characteristic data. By combining thermal response characteristic data with thermophysical characteristic data, the frequency-heat capacity correlation is established using the least squares method, and the thermal conductivity correction term is coupled with the thermal response time to construct a thermal characteristic parameter matrix.

4. The air conditioning cooling performance testing method as described in claim 3, characterized in that: The steps for performing the first dynamic heat load test and acquiring the physical test dataset, and then correcting the deviation of the air conditioner performance optimization test command using an intelligent dynamic compensation algorithm, are as follows: According to the air conditioning performance optimization test instructions, the compressor frequency, expansion valve opening and fan speed parameters are defined, the first dynamic heat load test is performed, and the measured values ​​of evaporator surface temperature field distribution, refrigerant pressure pulsation frequency and flow velocity field are collected in real time to form a physical test dataset. The measured values ​​in the physical test dataset are compared point by point with the evaporator surface temperature field distribution, refrigerant pressure pulsation frequency and flow velocity field data in the CFD simulation process to obtain the three-dimensional deviation matrix of temperature, pressure and flow velocity. Based on the three-dimensional deviation matrix, an intelligent dynamic compensation algorithm based on fuzzy PID control is used to dynamically correct the air conditioner performance optimization test command.

5. The air conditioning cooling performance testing method as described in claim 4, characterized in that: The steps for executing the second dynamic heat load test using the revised air conditioning performance optimization test command and generating a cooling performance test report are as follows. Based on the revised air conditioning performance optimization test instructions, a dynamic load change curve is constructed using a near-end strategy optimization algorithm. Based on the dynamic load change curve, a second dynamic thermal load test was performed, and infrared thermal imaging data, ultrasonic flow velocity distribution and vibration spectrum data were collected in real time to generate an enhanced physical test dataset. Based on the enhanced physical test dataset, performance features are extracted through wavelet packet decomposition; A DNN is used to establish the temporal correlation between the enhanced physical test dataset and the dynamic load change curve, and feature tensor convolution aggregation is performed to predict the cooling performance score of the air conditioner. A cooling performance test report is generated based on the dynamic load change curve, the air conditioner's cooling performance score, the evaporator frosting wind index and surge critical value under different loads.

6. An air conditioning cooling performance testing system, based on the air conditioning cooling performance testing method according to any one of claims 1 to 5, characterized in that: include, The data acquisition module is used to collect current frequency control parameters and building thermophysical property data, and to construct a thermal property parameter matrix through a multi-parameter coupling algorithm; The simulation module is used to perform CFD simulation on the air conditioning cooling process based on the thermal characteristic parameter matrix, through the mapping of the air conditioning three-dimensional model and multi-physics field coupling simulation, to predict the evaporator frosting wind index and surge critical value under different loads, and generate air conditioning performance optimization test instructions. The instruction correction module is used to perform the first dynamic heat load test and obtain the physical test dataset according to the air conditioner performance optimization test instruction, and to correct the deviation of the air conditioner performance optimization test instruction through an intelligent dynamic compensation algorithm. The report generation module is used to perform a second dynamic heat load test using the revised air conditioning performance optimization test instructions, and generate a cooling performance test report.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the air conditioning cooling performance testing method according to any one of claims 1 to 5.

8. 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 cooling performance testing method according to any one of claims 1 to 5.

Images