Optimized matching method for low-noise operation parameters of refrigerator compressor

Abstract

The invention discloses a refrigerator compressor low-noise operation parameter optimization matching method, and relates to the technical field of compressor noise control, compressor operation parameter data and broadband voiceprint data are acquired, voiceprint information is processed by using a quantum analysis technology, and a parameter reference model is constructed by combining physical constraint modeling and quantum calculation accelerated solution, so that the compressor low-noise operation parameter optimization matching method is realized. According to the method, parameter characteristic data are determined through data statistical processing and an incremental edge learning model, an optimal operation parameter matching scheme is determined by further combining broadband voiceprint feedback and applying an optimization algorithm, and the problems that in a traditional optimization method, data processing precision is insufficient, parameter model real-time performance is poor and multi-source voiceprint data integration efficiency is low are solved. An efficient and accurate parameter matching strategy is provided for low-noise operation of the refrigerator compressor, the user experience is improved, and the application scene of the noise reduction technology of the intelligent home equipment is expanded.

Description

Technical Field

[0001] The present invention relates to the technical field of compressor noise control, and more particularly to a method for optimizing and matching low-noise operating parameters of a refrigerator compressor. Background Art

[0002] During the use of refrigerators, the noise of the compressor has always been an important factor affecting the user experience. Traditional methods of controlling refrigerator compressor noise have many limitations. In the early days, most of them relied on the optimization of mechanical structure, such as adding shock-absorbing pads, etc. However, this method is often limited in effect and difficult to adapt to different operating conditions. With the development of technology, people began to pay attention to the impact of operating parameters on noise, and tried to reduce noise by optimizing operating parameters. However, the existing methods may not be comprehensive and accurate when obtaining operating parameter data, and have not fully utilized quantum analysis technology to process voiceprint data, resulting in an inaccurate grasp of noise characteristics. In terms of establishing parameter models, traditional modeling methods have a slow solution speed and cannot reflect the compressor in a timely manner. The parameter change patterns of the machine in actual operation are insufficient for processing and analyzing real-time data. It fails to effectively combine historical operating parameters with current parameters for in-depth comparative analysis to explore key parameter characteristics, making it difficult to determine the optimal operating parameter matching solution to achieve low-noise operation. In addition, the statistical analysis of multiple sets of operating parameter data is not detailed enough, and the distribution characteristics of data in each dimension and the dynamic characteristics of data changes over time are not fully considered, making it impossible to fully consider the timeliness and variability of data in the parameter optimization process. In the use of voiceprint data, the existing technology fails to effectively integrate the data of multiple voiceprint collection devices, and does not perform weighted processing on voiceprint data at different locations, resulting in inaccurate positioning and evaluation of noise sources.

[0003] The existing technology has problems such as inaccurate acquisition of operating parameter data and voiceprint processing, slow modeling and lack of real-time performance, and insufficient multi-dimensional data statistical analysis and voiceprint data integration and utilization, making it difficult for parameter optimization to adapt to low noise requirements. Summary of the Invention

[0004] In order to overcome the problems of inaccurate acquisition of operating parameter data and voiceprint processing in the existing technology, slow modeling and lack of real-time performance, insufficient statistical analysis of multi-dimensional data and insufficient integration and utilization of voiceprint data, the present invention discloses an optimization matching method for low-noise operating parameters of refrigerator compressors, which can effectively solve the above technical problems.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows: A method for optimizing and matching low-noise operating parameters of a refrigerator compressor comprises the following steps: Acquiring multiple sets of operating parameter data and corresponding broadband voiceprint data of the refrigerator compressor within a first time period; the broadband voiceprint data is acquired using broadband voiceprint acquisition equipment disposed around the refrigerator compressor and processed using quantum analysis technology, the operating parameter data including physical parameters in multiple dimensions; Performing physical constraint modeling on the operating parameter data and combining it with quantum computing to accelerate the solution, thereby obtaining a parameter reference model of the refrigerator compressor in the first time period; Obtaining operating parameter data and broadband voiceprint data of the refrigerator compressor at a current moment; the current moment is a moment after the first time period, and the operating parameter data at the current moment includes physical parameters of multiple dimensions; Performing data statistical processing on the physical parameters of each dimension based on the operating parameter data within the first time period and the operating parameter data at the current moment to obtain a data statistical value corresponding to each dimension; Based on the data statistics corresponding to each dimension and the operating parameter data at the current moment, using an incremental edge learning model, determining parameter characteristic data of the refrigerator compressor; Based on the parameter characteristic data and the parameter reference model, combined with feedback from broadband voiceprint data, the optimal operating parameter matching solution for the refrigerator compressor at the current moment is determined.

[0006] Preferably, performing physical constraint modeling on the operating parameter data and combining quantum computing with accelerated solution to obtain a parameter reference model of the refrigerator compressor in the first time period includes: Based on the physical characteristics and working principle of the refrigerator compressor, a mathematical model containing multiple physical constraints is established; Mapping the operating parameter data to the quantum state space, using quantum algorithms to accelerate the solution of the physical constraint model to obtain the parameter weight coefficient of each dimension; Based on the parameter weight coefficient of each dimension, a parameter reference model of the refrigerator compressor in the first time period is constructed.

[0007] Preferably, the data statistics include the data mean and data variance of each dimension; and the parameter characteristic data of the refrigerator compressor is determined including: Determine the parameter difference corresponding to each dimension based on the physical parameters of the operating parameter data at the current moment in each dimension and the data average value of the corresponding dimension; The parameter difference of each dimension and the data variance of the corresponding dimension are used as input and processed by the incremental edge learning model to obtain the parameter feature data corresponding to each dimension of the refrigerator compressor.

[0008] Preferably, the optimal operating parameter matching scheme for the refrigerator compressor at the current moment includes: Calculating the product of the parameter characteristic data of each dimension and the weight coefficient of the corresponding dimension in the parameter reference model to obtain the weighted parameter value corresponding to each dimension of the refrigerator compressor; Summing the weighted parameter values corresponding to each dimension to obtain a total parameter feature value of the refrigerator compressor at the current moment; Analyzing the broadband voiceprint data to extract characteristic information related to noise; Combining the parameter characteristic total value and the noise characteristic information of the broadband voiceprint data, an optimization algorithm is used to determine the optimal operating parameter matching solution for the refrigerator compressor at the current moment.

[0009] Preferably, there are multiple broadband voiceprint collection devices; the broadband voiceprint data in the first time period includes multiple groups of data corresponding to each broadband voiceprint collection device; the broadband voiceprint data at the current moment includes multiple groups of data corresponding to each broadband voiceprint collection device; the method includes: Determining measurement weight data for each broadband voiceprint collection device; the measurement weight data is determined based on a measurement position of the broadband voiceprint collection device around the refrigerator compressor; Calculating a noise characteristic value corresponding to each broadband voiceprint collection device; Determining a weighted noise characteristic value of each broadband voiceprint collection device based on the measurement weight data of each broadband voiceprint collection device and the noise characteristic value corresponding to the broadband voiceprint collection device; Based on the weighted noise characteristic value of each broadband voiceprint collection device and combined with the operating parameter data, an optimal operating parameter matching solution for the refrigerator compressor is determined.

[0010] Preferably, the first time period includes a plurality of detection time nodes; after obtaining the operating parameter data and broadband voiceprint data of the refrigerator compressor at the current moment, the method includes: Based on the operating parameter data and broadband voiceprint data corresponding to the current moment, and the operating parameter data and broadband voiceprint data corresponding to multiple adjacent detection time nodes before the current moment, the operating parameter data and broadband voiceprint data within the first time period are updated to obtain updated operating parameter data and broadband voiceprint data; the number of detection time nodes corresponding to the updated operating parameter data and broadband voiceprint data is consistent with the number of detection time nodes included in the first time period.

[0011] Preferably, after obtaining the operating parameter data and broadband voiceprint data of the refrigerator compressor at the current moment, the method includes: Calculating the minimum distance between the operating parameter data in the first time period and the operating parameter data at the current moment in each dimension; When the minimum distance value of at least one dimension is greater than a preset distance threshold, the operating parameter data and the parameter reference model within the first time period are corrected.

[0012] Preferably, when the minimum distance value of at least one dimension is greater than a preset distance threshold, correcting the operating parameter data and the parameter reference model within the first time period includes: Calculate the physical parameter of the operating parameter data at the current moment in each dimension and the difference between the physical parameter of the corresponding dimension at the previous detection time node at the current moment to obtain the data offset value corresponding to each dimension; Correcting the operating parameter data within the first time period based on the physical parameters of each dimension of the operating parameter data within the first time period and the data offset value corresponding to each dimension; The parameter reference model is reconstructed based on the corrected operating parameter data.

[0013] An electronic device comprises: a memory and at least one processor, wherein the memory stores instructions, and at least one processor calls the instructions in the memory to enable the device to execute each step of the optimization matching method as described above.

[0014] A computer-readable storage medium stores instructions, which, when executed by a processor, implement the steps of the above-mentioned optimization matching method.

[0015] Compared with the existing technology, the beneficial effects of the present invention are: the present invention obtains broadband voiceprint data around the refrigerator compressor through a broadband voiceprint acquisition device, and uses quantum analysis technology for processing. Compared with traditional voiceprint processing methods, quantum analysis technology can more deeply analyze the subtle features in the voiceprint data, improve the accuracy and richness of the voiceprint data, and at the same time, the obtained operating parameter data covers physical parameters of multiple dimensions, comprehensively reflecting the operating status of the compressor, and ensuring the integrity and accuracy of the acquisition of operating parameter data; based on the physical characteristics and working principles of the refrigerator compressor, a mathematical model containing multiple physical constraints is constructed, and the operating parameter data is mapped to the quantum state space, and the quantum algorithm is used to accelerate the solution, which not only improves the solution speed, but also can obtain more accurate parameter weight coefficients in a short time, thereby quickly constructing a parameter reference model. By obtaining data at multiple detection time nodes in the first time period and dynamically updating it in combination with the current time data, it can timely reflect the changing trend of the compressor operating parameters, and ensure that the parameter reference model accurately describes the real-time operating status of the compressor. The method solves the problems of slow modeling and lack of real-time performance in the existing technology. Based on the operating parameter data in the first time period and the operating parameter data at the current moment, data statistical processing is performed on each dimension to obtain statistical values such as data average and data variance. The parameter feature data is then determined by the incremental edge learning model, which fully mines the feature information contained in the multi-dimensional data and realizes in-depth analysis of the compressor operation status. At the same time, for multiple broadband voiceprint acquisition devices, the respective measurement weight data is determined, and the weighted noise feature value is calculated based on this. The voiceprint data at different positions are integrated to more accurately reflect the actual noise situation of the compressor. Finally, the optimal operating parameter matching scheme is determined by combining the parameter feature data, the parameter reference model and the feedback of the broadband voiceprint data through the optimization algorithm, which overcomes the defects of insufficient utilization of multi-dimensional data statistical analysis and voiceprint data integration in the existing technology, so that the operating parameter optimization of the refrigerator compressor can accurately adapt to the low noise requirements, improve the low noise operation performance of the refrigerator compressor, and provide users with a guarantee for reducing the overall noise level. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the implementation methods or the description of the prior art. Obviously, the drawings described below are merely exemplary. For ordinary technicians in this field, other implementation drawings can be derived based on the provided drawings without any creative work.

[0017] Figure 1 This is a step-by-step diagram of a method for optimizing and matching the low-noise operating parameters of a refrigerator compressor. DETAILED DESCRIPTION

[0018] The accompanying drawings are for illustrative purposes only and are not to be construed as limiting this patent; In order to better illustrate this embodiment, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product size; It is understandable to those skilled in the art that some well-known structures and descriptions thereof may be omitted in the drawings.

[0019] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0020] Example

[0021] A method for optimizing and matching low-noise operating parameters of a refrigerator compressor comprises the following steps: Acquiring multiple sets of operating parameter data and corresponding broadband voiceprint data of the refrigerator compressor within a first time period; the broadband voiceprint data is acquired using broadband voiceprint acquisition equipment disposed around the refrigerator compressor and processed using quantum analysis technology, the operating parameter data including physical parameters in multiple dimensions; Performing physical constraint modeling on the operating parameter data and combining it with quantum computing to accelerate the solution, thereby obtaining a parameter reference model of the refrigerator compressor in the first time period; Obtaining operating parameter data and broadband voiceprint data of the refrigerator compressor at a current moment; the current moment is a moment after the first time period, and the operating parameter data at the current moment includes physical parameters of multiple dimensions; Performing data statistical processing on the physical parameters of each dimension based on the operating parameter data within the first time period and the operating parameter data at the current moment to obtain a data statistical value corresponding to each dimension; Based on the data statistics corresponding to each dimension and the operating parameter data at the current moment, using an incremental edge learning model, determining parameter characteristic data of the refrigerator compressor; Based on the parameter characteristic data and the parameter reference model, combined with feedback from broadband voiceprint data, the optimal operating parameter matching solution for the refrigerator compressor at the current moment is determined.

[0022] The performing of physical constraint modeling on the operating parameter data and combining quantum computing with accelerated solution to obtain a parameter reference model of the refrigerator compressor in the first time period includes: Based on the physical characteristics and working principle of the refrigerator compressor, a mathematical model containing multiple physical constraints is established; Mapping the operating parameter data to the quantum state space, using quantum algorithms to accelerate the solution of the physical constraint model to obtain the parameter weight coefficient of each dimension; Based on the parameter weight coefficient of each dimension, a parameter reference model of the refrigerator compressor in the first time period is constructed.

[0023] The data statistics include the data mean and data variance of each dimension; the parameter characteristic data of the refrigerator compressor is determined including: Determine the parameter difference corresponding to each dimension based on the physical parameters of the operating parameter data at the current moment in each dimension and the data average value of the corresponding dimension; The parameter difference of each dimension and the data variance of the corresponding dimension are used as input and processed by the incremental edge learning model to obtain the parameter feature data corresponding to each dimension of the refrigerator compressor.

[0024] The optimal operating parameter matching scheme for the refrigerator compressor at the current moment includes: Calculating the product of the parameter characteristic data of each dimension and the weight coefficient of the corresponding dimension in the parameter reference model to obtain the weighted parameter value corresponding to each dimension of the refrigerator compressor; Summing the weighted parameter values corresponding to each dimension to obtain a total parameter feature value of the refrigerator compressor at the current moment; Analyzing the broadband voiceprint data to extract characteristic information related to noise; Combining the parameter characteristic total value and the noise characteristic information of the broadband voiceprint data, an optimization algorithm is used to determine the optimal operating parameter matching solution for the refrigerator compressor at the current moment.

[0025] There are multiple broadband voiceprint collection devices; the broadband voiceprint data in the first time period includes multiple groups of data corresponding to each broadband voiceprint collection device; the broadband voiceprint data at the current moment includes multiple groups of data corresponding to each broadband voiceprint collection device; the method includes: Determining measurement weight data for each broadband voiceprint collection device; the measurement weight data is determined based on a measurement position of the broadband voiceprint collection device around the refrigerator compressor; Calculating a noise characteristic value corresponding to each broadband voiceprint collection device; Determining a weighted noise characteristic value of each broadband voiceprint collection device based on the measurement weight data of each broadband voiceprint collection device and the noise characteristic value corresponding to the broadband voiceprint collection device; Based on the weighted noise characteristic value of each broadband voiceprint collection device and combined with the operating parameter data, an optimal operating parameter matching solution for the refrigerator compressor is determined.

[0026] The first time period includes a plurality of detection time nodes; after obtaining the operating parameter data and broadband voiceprint data of the refrigerator compressor at the current moment, the method includes: Based on the operating parameter data and broadband voiceprint data corresponding to the current moment, and the operating parameter data and broadband voiceprint data corresponding to multiple adjacent detection time nodes before the current moment, the operating parameter data and broadband voiceprint data within the first time period are updated to obtain updated operating parameter data and broadband voiceprint data; the number of detection time nodes corresponding to the updated operating parameter data and broadband voiceprint data is consistent with the number of detection time nodes included in the first time period.

[0027] After obtaining the operating parameter data and broadband voiceprint data of the refrigerator compressor at the current moment, the method includes: Calculating the minimum distance between the operating parameter data in the first time period and the operating parameter data at the current moment in each dimension; When the minimum distance value of at least one dimension is greater than a preset distance threshold, the operating parameter data and the parameter reference model within the first time period are corrected.

[0028] The step of modifying the operating parameter data and the parameter reference model within the first time period when the minimum distance value of at least one dimension is greater than a preset distance threshold comprises: Calculate the physical parameter of the operating parameter data at the current moment in each dimension and the difference between the physical parameter of the corresponding dimension at the previous detection time node at the current moment to obtain the data offset value corresponding to each dimension; Correcting the operating parameter data within the first time period based on the physical parameters of each dimension of the operating parameter data within the first time period and the data offset value corresponding to each dimension; The parameter reference model is reconstructed based on the corrected operating parameter data.

[0029] An electronic device comprises: a memory and at least one processor, wherein the memory stores instructions, and at least one processor calls the instructions in the memory to enable the device to execute each step of the optimization matching method as described above.

[0030] A computer-readable storage medium stores instructions, which, when executed by a processor, implement the steps of the above-mentioned optimization matching method.

[0031] In the specific implementation, please refer to Figure 1Five high-precision broadband voiceprint acquisition devices are evenly arranged at different locations around the refrigerator compressor, such as the top, side, and rear of the compressor. These devices have a wide-frequency response range (generally 20Hz-20kHz) and can accurately capture sound signals of various frequencies generated when the compressor is running. Each device has independent calibration data to ensure the accuracy and consistency of the collected sound signals, and a unique identifier is set for each acquisition device.

[0032] Install corresponding sensors at key locations of the refrigerator compressor to monitor operating parameters. These physical parameters include but are not limited to: The speed of the compressor is monitored in real time by a speed sensor with an accuracy of ±1rpm.

[0033] The exhaust pressure is measured using a pressure sensor with an accuracy of ±0.01MPa.

[0034] The suction pressure also uses a pressure sensor with the same accuracy as the exhaust pressure sensor.

[0035] The operating current is obtained through a current transformer with an accuracy of ±0.01A.

[0036] The operating voltage is monitored using a voltage sensor with an accuracy of ±0.1V.

[0037] The sensor transmits the real-time collected data to the data acquisition system. The sampling frequency of the data acquisition system is set to 1Hz, that is, the data value of each operating parameter is collected once per second, and the collected data is preliminarily filtered to remove high-frequency noise interference and ensure the accuracy and reliability of the data.

[0038] The first time period is set as the first 100 hours of continuous operation of the refrigerator compressor. The time period should be able to cover the operation of the refrigerator compressor under various working conditions, including startup, normal operation, load changes and other stages, so as to obtain comprehensive operating parameter data and broadband voiceprint data.

[0039] During the first time period, the data acquisition system simultaneously starts operating parameter monitoring and broadband soundprint collection. Every second of operation, it records the physical parameter values such as speed, exhaust pressure, intake pressure, operating current, and operating voltage collected by each operating parameter sensor, as well as the sound signal data obtained by the five broadband soundprint collection devices. The operating parameter data collected at the same time are combined into a set of operating parameter data records. The broadband soundprint data are respectively stored with the corresponding timestamp and collection device identifier for subsequent data association. During the collection process, the collected sound signal data are processed using quantum analysis technology. The specific steps are as follows: The analog sound signal is converted into a digital signal through an analog-to-digital converter, and the sampling frequency is set to 44.1kHz to meet the lossless digitization requirements of the audio signal.

[0040] The quantum Fourier transform algorithm is used to perform frequency domain transformation on digital signals, converting time domain signals into frequency domain signals, thereby obtaining the frequency components of the sound signal and its corresponding amplitude information. Compared with traditional Fourier transform, quantum Fourier transform has significant acceleration advantages when processing large-scale data, and can quickly and accurately extract key frequency features in sound signals.

[0041] The transformed frequency domain signal is subjected to quantum noise reduction processing, and the superposition and entanglement characteristics of quantum states are used to identify and remove the noise components in the signal, thereby improving the signal-to-noise ratio of the signal, so that the broadband voiceprint data can more clearly and accurately reflect the actual operating noise of the refrigerator compressor.

[0042] During the first 100-hour period, a total of 360,000 sets of operating parameter data records were collected, 3,600 sets per hour, 100 hours, as well as a corresponding large amount of broadband voiceprint data. These data will provide a data basis for physical constraint modeling and the construction of parameter reference models.

[0043] Based on the physical characteristics and operating principles of refrigerator compressors, we conducted an in-depth analysis of the interrelationships between various operating parameters and their impact on noise generation. Taking compressor speed as an example, the speed directly affects the mechanical vibration and gas flow within the compressor, which in turn generates varying degrees of noise. Specifically, we established a mathematical model that incorporates the following physical constraints: The relationship constraint between speed and exhaust pressure is established based on the compression ratio characteristic curve of the compressor. A nonlinear equation between speed and exhaust pressure is established, which is expressed as Pd = f1 (N), where Pd is the exhaust pressure, N is the speed, and f1 is the functional relationship obtained based on the actual performance of the compressor.

[0044] The relationship between suction pressure and operating current is constrained by considering the heat load of the evaporator and the operating efficiency of the compressor in the refrigeration system. The relationship between suction pressure and operating current is established, that is, I = f2(Ps), where I is the operating current, Ps is the suction pressure, and f2 is also a function fitted based on actual measured data.

[0045] The power constraints of the operating voltage and current follow the basic principles of electricity and establish the power relationship between the operating voltage V and the current I: P = V × I, where P is the input power of the compressor. This constraint is used to ensure that all operating parameters meet the requirements of electrical power balance during the modeling process.

[0046] The correlation constraints between noise and various operating parameters are established through experimental research and theoretical analysis. A multivariate linear regression model is established between the noise level (represented by the sound pressure level in the broadband soundprint data) and multiple operating parameters such as the speed N, exhaust pressure Pd, suction pressure Ps, operating current I, and operating voltage V. That is, L = a×N + b×Pd + c×Ps + d×I + e×V+ f, where L is the noise sound pressure level, and a, b, c, d, e, and f are regression coefficients. The above physical constraints are obtained by fitting data under different operating conditions. The mathematical model containing multiple equations is used to describe the intrinsic relationship between the operating parameters of the refrigerator compressor and noise.

[0047] The large amount of operating parameter data collected in the first time period is normalized so that its numerical range adapts to the representation requirements of the quantum state. The processed operating parameter data is then mapped to the quantum state space. Each operating parameter dimension corresponds to a quantum bit. The complex data relationship is represented by the superposition and entanglement states of the quantum bits. Quantum algorithms, such as quantum annealing algorithms or quantum genetic algorithms, are used to accelerate the solution of the physical constraint model. Taking the quantum annealing algorithm as an example, it can be regarded as a process of finding the lowest energy state (corresponding to the optimal solution) in the energy landscape of the quantum system: Initialize the state of the quantum bits and set the quantum bits corresponding to each operating parameter to a superposition state, representing all possible combinations of parameter values.

[0048] The Hamiltonian of the system is constructed so that its energy function corresponds to the objective function of the physical constraint model, such as minimizing the noise level. At the same time, the physical constraints are introduced into the Hamiltonian as penalty terms to ensure that the solution satisfies the physical constraints.

[0049] Gradually adjust the system's quantum annealing parameters, such as annealing time and quantum fluctuation intensity, so that the quantum system gradually evolves from the initial high-temperature and high-energy state to a low-temperature and low-energy state. In this process, the state of the quantum bit is constantly adjusted and eventually converges to a state that makes the Hamiltonian energy the lowest, that is, the parameter weight coefficient of each operating parameter dimension is obtained.

[0050] By accelerating the solution through quantum computing, the solution time is greatly shortened compared to traditional computing methods, from the original calculation time of several days to within a few hours, and the parameter weight coefficient of each dimension is efficiently obtained, providing a key basis for the construction of the parameter reference model.

[0051] Based on the obtained parameter weight coefficients for each dimension, a parameter reference model of the refrigerator compressor in the first time period is constructed in a weighted summation manner. The parameters of the five dimensions of speed, exhaust pressure, suction pressure, operating current, and operating voltage are multiplied by their corresponding weight coefficients respectively. Then, the results of each dimension are added together to obtain a comprehensive parameter characteristic value. This value can comprehensively reflect the performance status of the refrigerator compressor under different operating parameter combinations and its correlation with the noise level. The parameter reference model can be expressed as: Mr = w1×N + w2×Pd + w3×Ps + w4×I + w5×V Among them, Mr is the comprehensive parameter characteristic value of the parameter reference model, w1, w2, w3, w4, and w5 are the weight coefficients corresponding to the dimensions of each operating parameter. These weight coefficients are obtained through quantum computing acceleration. They reflect the importance of each operating parameter in affecting the performance and noise level of the refrigerator compressor. This parameter reference model will serve as an important reference standard for subsequent evaluation and optimization of the refrigerator compressor operating parameters at the current moment.

[0052] After the refrigerator compressor completes 100 hours of operation in the first time period, any subsequent operating moment is defined as the current moment. For example, the moment of 100 hours and 5 minutes in the subsequent operation process is taken as the current moment, at which time the refrigerator compressor is still in normal operation.

[0053] According to the same data collection method as the first time period, the operating parameter data and broadband voiceprint data of the refrigerator compressor are collected at the current moment. That is, the instantaneous values of the speed, exhaust pressure, suction pressure, operating current, and operating voltage are obtained through each operating parameter sensor to form the operating parameter data record at the current moment; at the same time, 5 broadband voiceprint collection devices are used to obtain the sound signal data at that moment, and quantum analysis technology is also used for processing to obtain the broadband voiceprint feature data at the corresponding moment, including information such as the frequency domain components of the sound signal and its amplitude.

[0054] Perform statistical processing on the physical parameters of the operating parameter data in each dimension (speed, exhaust pressure, intake pressure, operating current, and operating voltage) of the operating parameter data in the first time period and the operating parameter data at the current moment, and calculate the data mean and data variance corresponding to each dimension: For the speed dimension, calculate the average speed value μN and the variance σ²N of the speed data in all 360,000 sets of operating parameter data in the first time period. The average value μN is obtained by adding all the speed values and dividing it by the number of data sets. The variance σ²N is the sum of the squares of the differences between each speed value and the average value divided by the number of data sets.

[0055] Similarly, the data average μPd and variance σ²Pd of the exhaust pressure dimension, the data average μPs and variance σ²Ps of the suction pressure dimension, the data average μI and variance σ²I of the operating current dimension, and the data average μV and variance σ²V of the operating voltage dimension are calculated respectively. These data statistics reflect the average level and data fluctuation degree of each operating parameter dimension in the first time period, providing a statistical basis for determining the parameter characteristic data of the refrigerator compressor.

[0056] Based on the physical parameter values of the current operating parameter data in each dimension, as well as the previously calculated mean and variance of the corresponding dimension data, the incremental edge learning model is used to determine the parameter feature data of the refrigerator compressor: For each dimension, the difference between the physical parameter value at the current moment and the average value of the dimension data is calculated, that is, the parameter difference. For example, in the speed dimension, the parameter difference is ΔN = Ncurrent - μN, where Ncurrent is the speed value at the current moment.

[0057] The parameter difference of each dimension and the data variance of the corresponding dimension are used as input features and input into the incremental edge learning model. The incremental edge learning model is an efficient machine learning algorithm. It can quickly learn and update new data based on the existing model without retraining the entire model. In this embodiment, the incremental edge learning model is trained in advance, and part of the data in the first time period is used as a training set, so that the model can learn the mapping relationship between the parameter difference and variance of each operating parameter dimension and the performance status of the refrigerator compressor.

[0058] The incremental edge learning model outputs the parameter feature data corresponding to each dimension of the refrigerator compressor based on the input feature data, through internal neural network calculations, including signal transmission and processing in the input layer, hidden layer, and output layer. These parameter feature data comprehensively reflect the degree of deviation of each operating parameter dimension of the refrigerator compressor at the current moment from the average operating state in the first time period and the potential performance change trend. For example, the parameter feature data may be expressed as a numerical value, the absolute value of which indicates the degree of deviation, and the positive or negative sign indicates the direction of deviation (whether it is increasing or decreasing relative to the average state).

[0059] Calculate the product between the parameter characteristic data of each dimension and the weight coefficient of the corresponding dimension in the parameter reference model to obtain the weighted parameter value corresponding to each dimension. That is, for the speed dimension, the weighted parameter value is FN = fN×w1, where fN is the parameter characteristic data of the speed dimension, and w1 is the weight coefficient of the speed dimension in the parameter reference model; similarly, calculate the weighted parameter values FPd, FPs, FI, and FV of the exhaust pressure, intake pressure, operating current, and operating voltage dimensions.

[0060] The weighted parameter values of each dimension are added together to obtain the total parameter characteristic value Ftotal of the refrigerator compressor at the current moment = FN + FPd + FPs + FI + FV. The total parameter characteristic value Ftotal comprehensively reflects the degree of difference between the overall operating parameter state of the refrigerator compressor at the current moment and the reference state in the first time period, as well as the potential impact on the noise level.

[0061] Analyze the current broadband voiceprint data and extract noise-related feature information. Specifically, by analyzing the spectral characteristics of the broadband voiceprint data, determine the energy distribution of different frequency components in the sound signal, and identify the dominant frequency components and their energy associated with refrigerator compressor noise. For example, if the energy in a specific frequency range, such as 1000Hz-2000Hz, is significantly higher than that of other frequency components, this may be related to mechanical vibration or gas flow noise inside the compressor. The energy value in this frequency range is extracted as the noise feature value Feature_noise.

[0062] Combining the parameter feature total value Ftotal and the noise feature information Feature_noise of the broadband voiceprint data, a comprehensive evaluation function is constructed to evaluate the refrigerator compressor noise level under different operating parameter combinations. The comprehensive evaluation function can be expressed as: Evaluation =α×Ftotal +β×Feature_noise Among them, α and β are weight coefficients, which are set according to actual experience and the evaluation of the importance of the total value of parameter characteristics and noise characteristic information. For example, α is set to 0.6 and β is set to 0.4, reflecting the relative contribution of the two in noise assessment. Through optimization algorithms, such as particle swarm optimization algorithm or genetic algorithm, the search is carried out within the allowable operating parameter range of the refrigerator compressor to find the operating parameter combination that minimizes the comprehensive evaluation function Evaluation, that is, to determine the optimal operating parameter matching scheme of the refrigerator compressor at the current moment. The optimization algorithm continuously adjusts the values of each operating parameter (speed, exhaust pressure, suction pressure, operating current, operating voltage) through an iterative process, calculates the corresponding Evaluation value, and gradually approaches the optimal solution, and finally obtains the operating parameter setting that can minimize the refrigerator compressor noise at the current moment.

[0063] A detailed analysis was conducted on the measurement locations of the five broadband voiceprint collection devices placed around the refrigerator compressor. Considering factors such as the sensitivity of each location to the main noise sources of the refrigerator compressor, such as compressor body vibration, motor operation noise, refrigerant flow noise, and sound propagation path, the measurement weight data of each broadband voiceprint collection device was determined through a combination of experiments and numerical simulations. For example: The acquisition device located in the center of the top of the compressor is closer to the core vibration source of the compressor and is less obstructed during sound propagation. It responds more directly and sensitively to compressor vibration and motor noise. Therefore, it is given a higher measurement weight, such as 0.3.

[0064] The collection devices located on the sides and rear are assigned different weights according to their relative positions to the main noise source and the reflection and absorption of sound by surrounding structures. For example, the two collection devices on the side are each assigned a weight of 0.25, and the collection device at the rear is assigned a weight of 0.2. The sum of all weights is 1. This ensures that the data from each collection device can be reasonably included in the calculation according to its importance during the comprehensive evaluation.

[0065] For each broadband voiceprint collection device, the broadband voiceprint data collected at the current moment is extracted according to the above-mentioned method of extracting noise characteristic information, such as analyzing the spectrum characteristics to obtain the energy value within a specific frequency range, and calculating the noise characteristic value corresponding to each device. For example, the noise characteristic value of the top collection device is L1, the noise characteristic values of the two side collection devices are L2 and L3 respectively, and the noise characteristic value of the rear collection device is L4.

[0066] Based on the measurement weight data of each broadband voiceprint collection device, the weighted noise characteristic value of each device is calculated, that is, the weighted noise characteristic value of the top collection device is 0.3×L1, the weighted noise characteristic values of the two side collection devices are 0.25×L2 and 0.25×L3 respectively, and the weighted noise characteristic value of the rear collection device is 0.2×L4.

[0067] By adding up the weighted noise characteristic values of all broadband voiceprint collection devices, we can obtain a comprehensive weighted noise characteristic total value Ltotal = 0.3×L1 + 0.25×L2 + 0.25×L3 + 0.2×L4. This value more accurately reflects the actual noise level of the refrigerator compressor at the current moment because it integrates the noise information collected at different locations and weights them according to the importance of each location.

[0068] The comprehensive weighted noise characteristic total value Ltotal is combined with the operating parameter data and incorporated into the comprehensive evaluation function to further optimize the operating parameter matching scheme of the refrigerator compressor. That is, when determining the optimal operating parameter combination, not only the parameter characteristic total value Ftotal should be considered, but also the actual noise situation reflected by the broadband voiceprint data after weighted processing should be fully considered. By searching the optimization algorithm, the operating parameter setting that minimizes the comprehensive evaluation function is found to ensure that the refrigerator compressor reaches the optimal low-noise operating state at the current moment.

[0069] After obtaining the current operating parameter data and broadband voiceprint data, the operating parameter data and broadband voiceprint data within the first time period are updated based on the current operating parameter data and broadband voiceprint data, as well as multiple adjacent detection time nodes before the current time, such as the operating parameter data and broadband voiceprint data corresponding to the previous 10 hours. The specific operations are as follows: The data at the current moment replaces the data records of the earliest hour collected in the first time period. That is, a rolling update method is adopted to keep the total number of data records in the first time period unchanged and always cover the operating data of the last 100 hours. For example, if the current moment is the 100th hour and 5 minutes, then the original data from hours 0 to 1 is replaced with the data at the current moment. At the same time, the data from subsequent hours 1 to 100 are shifted forward in sequence to form new operating parameter data and broadband voiceprint data for the first time period. These updated data will continue to be used for subsequent physical constraint modeling and parameter reference model construction to ensure that the model can promptly reflect the recent changes in the operating status of the refrigerator compressor.

[0070] Calculate the minimum distance between the operating parameter data in the first time period and the operating parameter data at the current moment in each dimension. Euclidean distance is used as the measurement indicator here. For each operating parameter dimension (speed, exhaust pressure, intake pressure, operating current, operating voltage), calculate the absolute value of the difference between the physical parameter value at the current moment and the physical parameter value of this dimension in all data records in the first time period. Then find the minimum difference in each dimension, which is the minimum distance value of this dimension.

[0071] The preset distance threshold, for example, for the speed dimension, the preset distance threshold is 50rpm; the exhaust pressure dimension is 0.03MPa; the intake pressure dimension is 0.02MPa; the operating current dimension is 0.2A; and the operating voltage dimension is 0.3V. After calculating the minimum distance value of each dimension, determine whether there is at least one dimension whose minimum distance value is greater than the corresponding preset distance threshold. For example, if the minimum distance value of the speed dimension is 60rpm, which is greater than the preset 50rpm threshold, the correction condition is met.

[0072] When the minimum distance value of at least one dimension is greater than the preset distance threshold, it is necessary to correct the operating parameter data and parameter reference model in the first time period. First, calculate the difference between the physical parameter value of the operating parameter data in each dimension at the current moment and the physical parameter value of the corresponding dimension at the previous detection time node at the current moment (that is, 1 hour before the current moment) to obtain the data offset value corresponding to each dimension. For example, the data offset value of the speed dimension is ΔNshift = Ncurrent - Nprevious, where Nprevious is the speed value 1 hour before the current moment.

[0073] Based on the physical parameter values of the original operating parameter data in each dimension in the first time period and the calculated data offset value corresponding to each dimension, the operating parameter data in the first time period is corrected. The specific correction method can be to add the data offset value of the corresponding dimension to the physical parameter value of each dimension in each data record in the first time period, so as to obtain the corrected operating parameter data. For example, for the speed dimension, the corrected speed value is Ncorrected = Noriginal +ΔNshift, where Noriginal is the speed value at a certain moment in the first time period before correction.

[0074] Based on the revised operating parameter data, a new parameter reference model is constructed according to the previous physical constraint modeling and quantum computing acceleration solution steps. That is, a mathematical model containing physical constraint conditions is re-established, and the revised operating parameter data is mapped to the quantum state space. The parameter weight coefficients of each dimension are re-solved using the quantum algorithm, and a new parameter reference model is constructed to adapt to changes in the operating state of the refrigerator compressor, ensuring that subsequent optimization and matching methods can be based on an accurate and updated model, thereby continuously and effectively achieving low-noise operating parameter optimization of the refrigerator compressor.

[0075] The same or similar reference numerals correspond to the same or similar components; The terms used in the drawings to describe positional relationships are for illustrative purposes only and should not be construed as limiting this patent; Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the implementation methods of the present invention. For ordinary technicians in the field, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation methods here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A method for optimizing and matching the low-noise operating parameters of a refrigerator compressor, characterized in that: The following steps are involved: Acquiring multiple sets of operating parameter data and corresponding broadband voiceprint data of the refrigerator compressor within a first time period; the broadband voiceprint data is acquired using broadband voiceprint acquisition equipment disposed around the refrigerator compressor and processed using quantum analysis technology, the operating parameter data including physical parameters in multiple dimensions; Performing physical constraint modeling on the operating parameter data and combining it with quantum computing to accelerate the solution, thereby obtaining a parameter reference model of the refrigerator compressor in the first time period; Obtaining operating parameter data and broadband voiceprint data of the refrigerator compressor at a current moment; the current moment is a moment after the first time period, and the operating parameter data at the current moment includes physical parameters of multiple dimensions; Performing data statistical processing on the physical parameters of each dimension based on the operating parameter data within the first time period and the operating parameter data at the current moment to obtain a data statistical value corresponding to each dimension; Based on the data statistics corresponding to each dimension and the operating parameter data at the current moment, using an incremental edge learning model, determining parameter characteristic data of the refrigerator compressor; Based on the parameter characteristic data and the parameter reference model, combined with feedback from broadband voiceprint data, the optimal operating parameter matching solution for the refrigerator compressor at the current moment is determined.

2. The optimization matching method according to claim 1, characterized in that: The performing of physical constraint modeling on the operating parameter data and combining quantum computing with accelerated solution to obtain a parameter reference model of the refrigerator compressor in the first time period includes: Based on the physical characteristics and working principle of the refrigerator compressor, a mathematical model containing multiple physical constraints is established; Mapping the operating parameter data to the quantum state space, using quantum algorithms to accelerate the solution of the physical constraint model to obtain the parameter weight coefficient of each dimension; Based on the parameter weight coefficient of each dimension, a parameter reference model of the refrigerator compressor in the first time period is constructed.

3. The optimization matching method according to claim 1, characterized in that: The data statistics include the data mean and data variance of each dimension; the parameter characteristic data of the refrigerator compressor is determined including: Determine the parameter difference corresponding to each dimension based on the physical parameters of the operating parameter data at the current moment in each dimension and the data average value of the corresponding dimension; The parameter difference of each dimension and the data variance of the corresponding dimension are used as input and processed by the incremental edge learning model to obtain the parameter feature data corresponding to each dimension of the refrigerator compressor.

4. The optimization matching method according to claim 3, characterized in that: The optimal operating parameter matching scheme for the refrigerator compressor at the current moment includes: Calculating the product of the parameter characteristic data of each dimension and the weight coefficient of the corresponding dimension in the parameter reference model to obtain the weighted parameter value corresponding to each dimension of the refrigerator compressor; Summing the weighted parameter values corresponding to each dimension to obtain a total parameter feature value of the refrigerator compressor at the current moment; Analyzing the broadband voiceprint data to extract characteristic information related to noise; Combining the parameter characteristic total value and the noise characteristic information of the broadband voiceprint data, an optimization algorithm is used to determine the optimal operating parameter matching solution for the refrigerator compressor at the current moment.

5. The optimization matching method according to claim 1, characterized in that: There are multiple broadband voiceprint collection devices; the broadband voiceprint data in the first time period includes multiple groups of data corresponding to each broadband voiceprint collection device; the broadband voiceprint data at the current moment includes multiple groups of data corresponding to each broadband voiceprint collection device; the method includes: Determining measurement weight data for each broadband voiceprint collection device; the measurement weight data is determined based on a measurement position of the broadband voiceprint collection device around the refrigerator compressor; Calculating a noise characteristic value corresponding to each broadband voiceprint collection device; Determining a weighted noise characteristic value of each broadband voiceprint collection device based on the measurement weight data of each broadband voiceprint collection device and the noise characteristic value corresponding to the broadband voiceprint collection device; Based on the weighted noise characteristic value of each broadband voiceprint collection device and combined with the operating parameter data, an optimal operating parameter matching solution for the refrigerator compressor is determined.

6. The optimization matching method according to claim 1, characterized in that: The first time period includes a plurality of detection time nodes; after obtaining the operating parameter data and broadband voiceprint data of the refrigerator compressor at the current moment, the method includes: Based on the operating parameter data and broadband voiceprint data corresponding to the current moment, and the operating parameter data and broadband voiceprint data corresponding to multiple adjacent detection time nodes before the current moment, the operating parameter data and broadband voiceprint data within the first time period are updated to obtain updated operating parameter data and broadband voiceprint data; the number of detection time nodes corresponding to the updated operating parameter data and broadband voiceprint data is consistent with the number of detection time nodes included in the first time period.

7. The optimization matching method according to claim 1, characterized in that: After obtaining the operating parameter data and broadband voiceprint data of the refrigerator compressor at the current moment, the method includes: Calculating the minimum distance between the operating parameter data in the first time period and the operating parameter data at the current moment in each dimension; When the minimum distance value of at least one dimension is greater than a preset distance threshold, the operating parameter data and the parameter reference model within the first time period are corrected.

8. The optimization matching method according to claim 7, characterized in that: The step of modifying the operating parameter data and the parameter reference model within the first time period when the minimum distance value of at least one dimension is greater than a preset distance threshold comprises: Calculate the physical parameter of the operating parameter data at the current moment in each dimension and the difference between the physical parameter of the corresponding dimension at the previous detection time node at the current moment to obtain the data offset value corresponding to each dimension; Correcting the operating parameter data within the first time period based on the physical parameters of each dimension of the operating parameter data within the first time period and the data offset value corresponding to each dimension; The parameter reference model is reconstructed based on the corrected operating parameter data.

9. An electronic device, characterized in that: include: A memory and at least one processor, wherein the memory stores instructions, and at least one processor calls the instructions in the memory to enable the device to execute each step of the optimization matching method according to any one of claims 1 to 8.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, the steps of the optimization matching method according to any one of claims 1 to 8 are implemented.

Images