Modulation mode optimization method, controller, electronic device, and refrigeration device

Abstract

The application discloses a modulation mode optimization method, a controller, electronic equipment and refrigeration equipment. Key characteristic parameters of a modulation mode of a compressor are found based on a dual optimization target of system power loss minimization and output current harmonic content minimization, and then an optimal modulation strategy of the compressor can be obtained by a control system of the refrigeration equipment according to current working conditions of the refrigeration equipment and the acquired key characteristic parameters, so that the compressor is controlled to work in a two-phase modulation mode or a three-phase modulation mode. Through the above method, the limitation that a traditional method depends on fixed rules, a single model or artificial experience to determine the modulation mode of the compressor is broken, dual adaptation of the modulation strategy to the body difference of the compressor and real-time working conditions is realized, and the overall adaptive ability and long-term operation reliability of the system are enhanced.

Description

Technical Field

[0001] This application relates to the field of refrigerator control technology, and in particular to a method for optimizing modulation, a controller, electronic equipment, and refrigeration equipment. Background Technology

[0002] In refrigerators, the compressor is the core component of the refrigeration system, and its control method directly affects system performance and energy efficiency. Currently, the mainstream refrigerator compressor control strategies typically employ two-phase modulation or three-phase modulation.

[0003] In related technologies, the variable frequency control of refrigerator compressors can switch between two modulation methods. However, the judgment conditions for switching modulation methods are relatively simple. For example, they can switch based on the high or low level signal of the IPM module or the high or low voltage vector amplitude of the compressor. The setting of the parameters and switching threshold used to judge the switching depends on the experience judgment of the designer, which limits the adaptability of the control strategy and the optimization effect is not comprehensive enough. Summary of the Invention

[0004] This application provides a method for optimizing modulation, a controller, an electronic device, and a cooling device, which can determine the optimal modulation method under the current operating conditions in real time.

[0005] In a first aspect, embodiments of this application provide a method for optimizing the modulation mode of a compressor, comprising: The system of the compressor is subjected to multiple sets of sample operating data under different operating conditions and different modulation methods. The sample operating data includes system input power, system output power and three-phase output current of the compressor. The modulation methods include two-phase modulation and three-phase modulation. The system power loss is determined based on the system input power and the system output power, the output current harmonic content is determined based on the three-phase output current, and the modulation method under different operating conditions is screened with the dual optimization objectives of minimizing the system power loss and minimizing the output current harmonic content, so as to obtain the correspondence between the target operating condition and the optimal modulation strategy. A multidimensional feature dataset is constructed based on the target sample operation data corresponding to the target operating condition and the electrical calibration parameters of the compressor. The correlation between each parameter in the multidimensional feature dataset and the corresponding optimal modulation strategy is determined, and the top few parameters with the highest correlation are determined as key feature parameters. Using the target operating condition and the key feature parameters as input parameters and the optimal modulation strategy as output parameters, a preset mapping model is trained to obtain a target mapping model, which is then embedded into the control system of the refrigeration equipment.

[0006] In some embodiments, acquiring multiple sets of sample operating data of the compressor system under different operating conditions and different modulation methods includes at least one of the following: Based on multiple preset operating conditions and the corresponding modulation methods, the compressor is set with operating parameters in sequence, the compressor is controlled to run under the operating conditions corresponding to the operating parameters, and sample operating data under each preset operating condition is obtained to obtain multiple sets of sample operating data. The sample operating data corresponds to the modulation method of the preset operating condition. The compressor's operating parameters and modulation methods under multiple actual operating conditions during actual operation are obtained, and the actual operating data under each actual operating condition is obtained as sample operating data to obtain multiple sets of sample operating data and modulation methods corresponding to the sample operating data.

[0007] In some embodiments, the sample operating data further includes at least one of the compressor's rotational speed, real-time power, phase current amplitude, carrier frequency, and whether overmodulation is enabled; the compressor's electrical calibration parameters include at least one of phase resistance, D-axis and Q-axis inductance, back electromotive force coefficient, and moment of inertia.

[0008] In some embodiments, determining the harmonic content of the output current based on the three-phase output current includes: The phase output current of the compressor is obtained within a preset number of cycles, and the three-phase output current is obtained by averaging the phase output current according to the three-phase division. The three-phase output current is subjected to a fast Fourier transform to obtain the harmonic current of each phase output current; the harmonic current includes several odd harmonic currents other than the fundamental current. The total harmonic content is determined based on the amplitude of the harmonic current.

[0009] In some embodiments, the optimization objective of minimizing the harmonic content of the output current is specifically: The percentage of the total harmonic content of the output current of each phase to the fundamental current amplitude of the output current of each phase is determined to obtain the harmonic distortion rate of the output current of each phase. The optimization objective is to ensure that the harmonic distortion rate of at least one phase output current meets a preset first distortion rate range and / or that the overall harmonic distortion rate of the three-phase output current meets a preset second distortion rate range.

[0010] In some embodiments, the selection of modulation methods under different operating conditions based on the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content includes: Construct a candidate set of operating conditions; each candidate set of operating conditions includes one or more sets of candidate data under the same operating condition and different modulation methods, and the candidate data consists of two elements: the system power loss and the harmonic distortion rate; Minimizing both system power loss and harmonic distortion rate are set as the objectives of Pareto screening. Pareto screening is performed on the candidate data within the same set of candidate operating conditions to obtain at least one set of target candidate data within the same set of candidate operating conditions. Determine the target operating condition corresponding to each group of target candidate data in the target operating condition candidate set, and take the modulation method corresponding to the target operating condition as the optimal modulation method for the target operating condition.

[0011] In some embodiments, determining the correlation between each parameter in the multidimensional feature dataset and the corresponding optimal modulation strategy, and identifying the top few parameters with the highest correlation as key feature parameters, includes: Determine the correlation coefficients between each parameter in the multidimensional feature dataset under the same target operating condition and the optimal modulation scheme of the target operating condition; The screening range is determined based on the maximum and / or minimum values ​​of the correlation coefficients. All parameters whose correlation coefficients fall within the screening range are taken as key feature parameters under the target working conditions, thereby determining the key feature parameters corresponding to different target working conditions.

[0012] In some embodiments, training a preset mapping model to obtain a target mapping model includes: The preset mapping model is trained using different algorithms to obtain multiple candidate mapping models; The target mapping model is obtained by filtering the candidate mapping models according to their generalization ability and prediction accuracy.

[0013] In some embodiments, embedding the target mapping model into the control system of the refrigeration equipment includes: The target mapping model is converted into a decision tree; the input of the decision tree is the current operating condition of the refrigeration equipment and the acquired key feature parameters, and the output is the optimal modulation strategy of the compressor. The decision tree is converted into executable code or an executable program to be embedded into the control system. Alternatively, the target mapping model can be ported to the storage space of the control system; Alternatively, the target mapping model can be ported to the edge computing device of the control system, wherein the control system is used to send the current operating condition of the refrigeration equipment and the acquired key feature parameters to the edge computing device, and to receive the optimal modulation strategy of the compressor returned by the edge computing device.

[0014] Secondly, embodiments of this application also provide a controller, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for optimizing the modulation mode of the compressor as described in the first aspect.

[0015] Thirdly, embodiments of this application also provide an electronic device, including the controller described in the foregoing embodiments.

[0016] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for causing a controller to perform an optimization method for the modulation mode of a compressor as described in the first aspect.

[0017] Fifthly, embodiments of this application also provide a computer program product, including a computer program or computer instructions, characterized in that the computer program or computer instructions are stored in a computer-readable storage medium, a processor of a refrigeration device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions to cause the refrigeration device to perform the compressor modulation optimization method as described in the first aspect.

[0018] In a sixth aspect, embodiments of this application also provide a refrigeration device, including a compressor and a control system; the control system is configured to receive an optimal modulation strategy of the compressor obtained by the method described in the first aspect, and control the compressor to operate in a two-phase modulation mode or a three-phase modulation mode according to the optimal modulation strategy of the compressor.

[0019] The modulation optimization method, controller, electronic device, and refrigeration equipment of this application embodiment have at least the following beneficial effects: Multiple sets of sample operating data of the compressor system under different operating conditions and modulation methods are obtained. Based on the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content, modulation methods under different operating conditions are screened to obtain the initially screened optimal modulation strategies under different target operating conditions. To further determine which parameters have a significant impact on the optimal modulation strategy, the target sample operating data corresponding to the target operating conditions and the compressor's electrical calibration parameters are integrated to construct a multi-dimensional feature dataset. Through correlation analysis between each parameter in the multi-dimensional feature dataset and the optimal modulation strategy, the parameters are identified. By analyzing the intrinsic correlation and influence between the modulator and the optimal modulation strategy, the top few key feature parameters with the highest correlation are identified. Then, the target mapping model is trained using the key feature parameters. Finally, the target mapping model is embedded into the control system of the refrigeration equipment. In this way, the control system of the refrigeration equipment can obtain the optimal modulation strategy of the compressor based on the current operating conditions of the refrigeration equipment and the obtained key feature parameters, and control the compressor to operate in two-phase modulation mode or three-phase modulation mode. Through the above method, the limitations of traditional methods that rely on fixed rules, single models or manual experience to determine the modulation mode of the compressor are overcome. The modulation strategy achieves dual adaptation to the differences in the compressor itself and real-time operating conditions, thereby enhancing the overall adaptive capability and long-term operational reliability of the system.

[0020] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description and the accompanying drawings. Attached Figure Description

[0021] Figure 1 A flowchart illustrating the overall process of optimizing the modulation method of a compressor according to one embodiment of this application; Figure 2 A flowchart for calculating harmonic content is provided as an embodiment of this application; Figure 3 A flowchart illustrating the selection of dual optimization objectives provided in one embodiment of this application; Figure 4 This is a flowchart illustrating the determination of key feature parameters provided in one embodiment of this application; Figure 5 This is a flowchart illustrating the training and selection of a target mapping model according to one embodiment of this application; Figure 6 This is an example of an overall method flowchart provided in this application; Figure 7 This is a schematic diagram of the connection relationship of the controller provided in one embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various implementations. Simultaneously, the steps or actions described in the method description can be rearranged or adjusted in a manner readily apparent to those skilled in the art. Therefore, the various orders in the specification and drawings are merely for the clear description of a particular embodiment and do not imply a mandatory order, unless otherwise stated that a particular order must be followed.

[0023] In the description of this application, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0024] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0025] As the core component of the refrigeration system, the compressor's control method directly affects system performance and energy efficiency. Currently, mainstream control strategies typically employ two-phase or three-phase modulation. Two-phase modulation has relatively simple control logic, lower hardware implementation costs, and lower switching losses. However, under load fluctuations or low-speed operation, this method easily leads to current waveform distortion and significant torque pulsation, resulting in increased compressor vibration, noise, and decreased efficiency. Three-phase modulation can output a three-phase current closer to an ideal sine wave, thus achieving stable electromagnetic torque and lower noise performance, contributing to improved overall system energy efficiency. However, its control algorithm is more complex, and at higher speeds, switching losses are relatively large, potentially weakening its energy efficiency advantages. In existing technologies, compressors are typically controlled using a fixed modulation method, making it impossible to dynamically adjust the control strategy according to actual operating conditions. This single-mode control method struggles to optimize performance under different load conditions, failing to fully leverage the advantages of different modulation methods under specific operating conditions, and also failing to achieve comprehensive optimization of three-phase current waveform and system energy consumption across the entire operating range, thus limiting further improvements in the compressor's overall energy efficiency and operational adaptability. Currently, although a few studies have attempted to improve performance by switching modulation methods, their switching judgment conditions are usually based on only a single parameter, resulting in a limited range of application for the control strategy and insufficient optimization effect.

[0026] For example, related technologies acquire the voltage vector amplitude of the compressor in real time and judge the voltage vector amplitude. If the voltage vector amplitude is less than the modulation switching threshold, the compressor is controlled by two-phase modulation; if the voltage vector amplitude is greater than or equal to the modulation switching threshold, the compressor is controlled by three-phase modulation. Alternatively, the compressor's current operating frequency is acquired in real time and judged. If the current operating frequency is greater than or equal to the frequency threshold, the compressor is controlled by two-phase modulation; if the current operating frequency is less than the frequency threshold, the compressor is controlled by three-phase modulation. Alternatively, the current of the IPM is sampled to obtain a current signal. When the voltage signal corresponding to the current signal is greater than the reference voltage, a first level is output to the microcontroller; when it is less than the reference voltage, a first level is output to the microcontroller, so that the microcontroller can select three-phase modulation or two-phase modulation to control the intelligent power module according to the first level or the second level.

[0027] Therefore, it can be seen that the relevant technologies all use a single parameter to determine whether the compressor should use a two-phase modulation mode or a three-phase modulation mode. The setting of the parameters used for switching and the switching threshold depends on the experience judgment of the designers. In actual scenarios, this has its limitations and cannot provide a modulation mode that is completely and accurately suitable for the current operating conditions.

[0028] Based on this, embodiments of this application provide a modulation scheme optimization method, controller, electronic device, and refrigeration equipment. Multiple sets of sample operating data of the compressor system under different operating conditions and modulation schemes are acquired. Based on the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content, modulation schemes under different operating conditions are screened to obtain the initially selected optimal modulation strategies for different target operating conditions. To further determine which parameters have a significant impact on the optimal modulation strategy, the target sample operating data corresponding to the target operating conditions and the compressor's electrical calibration parameters are integrated to construct a multi-dimensional feature dataset. Through correlation analysis of each parameter in the multi-dimensional feature dataset with the optimal modulation strategy, the correlation between each parameter and the optimal modulation strategy is identified. By analyzing the intrinsic correlation and influence between optimal modulation strategies, the top few key feature parameters with the highest correlation are identified. Then, the target mapping model is trained using these key feature parameters. Finally, the target mapping model is embedded into the control system of the refrigeration equipment. In this way, the control system of the refrigeration equipment can obtain the optimal modulation strategy for the compressor based on the current operating conditions of the refrigeration equipment and the acquired key feature parameters, controlling the compressor to operate in two-phase or three-phase modulation mode. Through the above method, the limitations of traditional methods that rely on fixed rules, single models, or manual experience to determine the compressor modulation mode are overcome. This method achieves dual adaptation of the modulation strategy to the differences in the compressor itself and real-time operating conditions, enhancing the overall adaptive capability and long-term operational reliability of the system.

[0029] The various embodiments of the method for optimizing the modulation mode of the compressor of this application will be further described below with reference to the accompanying drawings.

[0030] Reference Figure 1 As shown, Figure 1 This is an overall flowchart of the method for optimizing the modulation mode of a compressor provided in this application embodiment. The method for optimizing the modulation mode includes, but is not limited to, the following steps: Step S110: Obtain multiple sets of sample operating data of the compressor system under different operating conditions and different modulation methods. The sample operating data includes system input power, system output power and compressor three-phase output current; the modulation methods include two-phase modulation and three-phase modulation. Step S120: Determine the system power loss based on the system input power and system output power, determine the output current harmonic content based on the three-phase output current, and select the modulation method under different operating conditions with the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content, so as to obtain the correspondence between target operating conditions and optimal modulation strategies. Step S130: Construct a multidimensional feature dataset based on the target sample operation data corresponding to the target operating condition and the electrical calibration parameters of the compressor; determine the correlation between each parameter in the multidimensional feature dataset and the corresponding optimal modulation strategy; and determine the top few parameters with the highest correlation as key feature parameters. Step S140: Using the target operating condition-key characteristic parameters as input parameters and the optimal modulation strategy as output parameters, the preset mapping model is trained to obtain the target mapping model, and the target mapping model is embedded into the control system of the refrigeration equipment.

[0031] By setting the compressor's operating parameters and modulation method according to preset operating conditions and modulation methods, multiple sets of sample operating data for the compressor system can be obtained. Alternatively, by collecting parameters of the compressor operating under different actual operating conditions and modulation methods, multiple sets of sample operating data for the compressor system can also be obtained. The mapping relationship between operating condition, modulation method, and sample operating data constitutes this part of the data. In addition to system input power, system output power, and compressor three-phase output current, the sample operating data may also include at least one of the following: compressor speed, real-time power, phase current amplitude, carrier frequency, and whether modulation has been enabled. It is understandable that the collected sample operating data is not limited to specific parameter types and quantities, because in subsequent processes, it is necessary to further determine the correlation between each parameter and the modulation method. Collecting more types of parameters as sample operating data can help to explore the degree of influence of different parameters on the modulation method and avoid missing key parameters.

[0032] Then, the system power loss is determined using the system input power and system output power, and the output current harmonic content is determined based on the three-phase output current. The above operating conditions, modulation methods, and sample operating data are screened with the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content. A comprehensive judgment is then made on the preferred modulation method under different operating conditions. System power loss and output current harmonic content are two negatively correlated indicators. Low system power loss indicates a high degree of discontinuity in the switching action of the modulation strategy. In this case, the fitting accuracy of the output voltage waveform to the ideal sine wave is low, resulting in a higher content of low-order harmonics in the output current. Low output current harmonic content indicates a high degree of continuity in the switching action of the modulation strategy. In this case, the output voltage can fit the ideal sine wave with higher accuracy, but at the cost of more frequent operation of the driving switching devices, leading to increased switching losses and higher system power loss. Therefore, the purpose of the above dual optimization is to find one or more modulation methods that can achieve a balance between system power loss and harmonic content. Thus, while pursuing energy saving, the waveform quality and stability of the three-phase output current are ensured, avoiding the power quality problems that may be introduced by considering switching modulation methods based on a single parameter in related technologies.

[0033] After the above dual-optimization target screening, the correspondence between target operating conditions and optimal modulation strategies is obtained. From these optimal modulation strategies, it is necessary to determine which parameters have the greatest impact on the modulation strategy. The parameters used for decision-making include not only the target sample operating parameters corresponding to the target operating conditions, but also the electrical calibration parameters of the compressor. The electrical calibration parameters of the compressor include at least one of the following: phase resistance, D-axis and Q-axis inductance, back electromotive force coefficient, and moment of inertia. Therefore, the parameters used for decision-making can cover the operating parameters of the system in which the compressor is located and the electrical parameters of the compressor itself, thereby allowing for the matching of modulation strategies suitable for specific operating conditions and specific models of compressors. A multidimensional feature dataset is constructed for the target sample operating parameters and the compressor's electrical calibration parameters. The multidimensional feature dataset includes the target sample operating parameters and the compressor's electrical calibration parameters under different operating conditions. For example, there are a total of n parameters for each target operating condition, and the multidimensional feature dataset has m target operating conditions. The multidimensional feature dataset can be represented as an m*n matrix, where m and n are both positive integers. By determining the correlation between n parameters of each target operating condition in the multidimensional feature dataset and the corresponding optimal modulation strategy, one or more parameters with the greatest intrinsic correlation and influence on the optimal modulation strategy under that target operating condition can be identified as key feature parameters. This eliminates most parameters that have little impact on the modulation strategy, reducing the operational burden on the refrigeration equipment and facilitating the rapid determination of the optimal modulation strategy.

[0034] Based on the aforementioned key feature parameters and corresponding optimal modulation strategies, a preset mapping model is trained to obtain a target mapping model, which is then embedded into the control system of the refrigeration equipment. The preset mapping model can be an untrained model, trained in the laboratory using the aforementioned key feature parameters and corresponding optimal modulation strategies before being used in the refrigeration equipment. Alternatively, the preset mapping model can be the current mapping model in the refrigeration equipment. During operation, the refrigeration equipment uses the aforementioned key feature parameters and corresponding optimal modulation strategies to train the current mapping model, obtaining the target mapping model to replace the original mapping model, thus achieving long-term model optimization in actual operation. It is understood that the above model can be based on reinforcement learning algorithms, random forest algorithms, neural network algorithms, etc., and this application does not impose any restrictions on this.

[0035] It is understandable that, in addition to directly embedding the target mapping model into the control system of the refrigeration equipment, the target mapping model can also be transformed before embedding to suit scenarios with low computing power of the refrigeration equipment. For example, the target mapping model can be transformed into a decision tree, and then the decision tree can be transformed into an executable program and loaded into the control system, and so on.

[0036] In some embodiments, acquiring multiple sets of sample operation data of the compressor system under different operating conditions and modulation methods can take two different scenarios: one is using training data provided by the laboratory or manufacturer as sample operation data, and the other is using data collected during the actual operation of the refrigeration equipment as sample operation data. These two scenarios can also be used in combination to cover optimization at both the pre- and post-shipment stages of the refrigeration equipment.

[0037] For the first scenario, operating parameters are sequentially set for the compressor based on multiple preset operating conditions and corresponding modulation methods. The compressor is controlled to operate under the corresponding operating conditions, and sample operating data is acquired for each preset operating condition, resulting in multiple sets of sample operating data. The sample operating data corresponds to the modulation method of the preset operating condition. In the laboratory, multiple preset operating conditions and corresponding modulation methods are set. Each time, one preset operating condition and modulation method is applied to set the compressor's operating parameters and control the compressor's operation (or simulate operation). During compressor operation, parameters under that operating condition are collected as sample operating data, and then the optimization method in subsequent steps is executed. For the second scenario, the operating parameters and modulation methods of the compressor under multiple actual operating conditions are acquired during actual operation, and the actual operating data under each actual operating condition is acquired as sample operating data, resulting in multiple sets of sample operating data and the modulation method corresponding to the sample operating data. During actual operation of the refrigeration equipment, data is collected at certain intervals to obtain the parameters of multiple actual operating conditions and the corresponding modulation methods. The actual operating data of that actual operating condition is used as sample operating data, and then the optimization method in subsequent steps is executed.

[0038] Reference Figure 2 As shown, in some embodiments, determining the harmonic content of the output current based on the three-phase output current in step S120 includes: Step S210: Obtain the phase output current of the compressor within a preset number of cycles, and calculate the three-phase output current by averaging the phase output current according to the three-phase division. Step S220: Perform a fast Fourier transform on the three-phase output current to obtain the harmonic current of each phase output current; the harmonic current includes several odd harmonic currents other than the fundamental current. Step S230: Determine the total harmonic content based on the amplitude of the harmonic current.

[0039] The phase output currents collected over multiple cycles are averaged to avoid errors caused by fluctuations in single sampling data. For example, the output current of each phase over 10 cycles can be averaged (or a weighted average can be used) to obtain the three-phase output current. A Fast Fourier Transform is performed on the output current of each phase to obtain the fundamental current and several odd harmonic currents (typically 5th, 7th, 11th, 13th, and 17th orders, but more are possible). The total harmonic content is obtained based on the amplitude of these odd harmonic currents. For example, the current amplitudes of the 5th, 7th, 11th, 13th, and 17th orders of each phase are expressed as follows: , , , , Total harmonic content .

[0040] Furthermore, the total harmonic content can be replaced by the harmonic distortion rate to simplify the dual optimization objective. The harmonic distortion rate is expressed as the total harmonic content. With fundamental current amplitude The ratio of system power loss to harmonic distortion rate. It is worth noting that system power loss and harmonic distortion rate are two negatively correlated indicators. Low system power loss indicates a high degree of discontinuity in the switching action of the modulation strategy. In this case, the output voltage waveform has a lower fitting accuracy to the ideal sine wave, resulting in a higher content of low-order harmonics in the output current. Conversely, a low content of harmonics in the output current indicates a higher degree of continuity in the switching action of the modulation strategy. In this case, the output voltage can fit the ideal sine wave with higher accuracy, but at the cost of more frequent operation of the driving switching devices, leading to increased switching losses and higher system power loss. Therefore, under the dual optimization objective, the selection of indicators needs to consider both system power loss and harmonic distortion rate, which are negatively correlated. Specifically, refer to... Figure 3 As shown, step S120 above, which selects modulation methods under different operating conditions with the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content, includes: Step S310: Construct a candidate set of operating conditions; each candidate set of operating conditions includes one or more sets of candidate data under the same operating condition and different modulation methods. The candidate data consists of two elements: system power loss and harmonic distortion rate. Step S320: Minimize system power loss and minimize harmonic distortion rate as the objectives of Pareto screening. Perform Pareto screening on candidate data within the same operating condition candidate set to obtain at least one set of target candidate data within the same operating condition candidate set. Step S330: Determine the target operating condition corresponding to each group of target candidate data in the operating condition candidate set, and take the modulation method corresponding to the target operating condition as the optimal modulation method of the target operating condition.

[0041] Each candidate set of operating conditions represents a correspondence between [Operating Condition], [Modulation Method], and [System Power Loss and Harmonic Distortion Rate]. The same operating condition can correspond to either two-phase or three-phase modulation, and multiple sets of candidate data can exist under the same operating condition and modulation method. Using the same operating condition as the dividing dimension, Pareto selection is performed on one or more sets of candidate data under different modulation methods. The Pareto selection process is based on minimizing both system power loss and harmonic distortion rate as selection objectives, choosing results that satisfy both low system power loss and low harmonic distortion rate. Specifically, candidate data can be compared pairwise to select Pareto optimal solutions or sets of Pareto optimal solutions. For example, for a set of candidate data A including system power loss A1 and harmonic distortion rate A2, if no other set of candidate data has a system power loss less than A1 and a harmonic distortion rate less than A2, then candidate data A is considered one of the Pareto optimal solutions. Based on the Pareto screening results above, we obtain the target operating condition, modulation scheme, and Pareto optimal candidate data. The modulation scheme corresponding to the Pareto optimal candidate data is then used as the optimal modulation scheme for the target operating condition (the optimal modulation scheme for the target operating condition after Pareto screening can only be two-phase modulation or three-phase modulation).

[0042] To avoid the problem of excessively high harmonic distortion rates in the Pareto optimal candidate data obtained through Pareto screening, an additional range restriction on the harmonic distortion rate is added to the Pareto screening process. Specifically, the optimization objective is that the harmonic distortion rate of at least one phase output current meets a preset first distortion rate range and / or the overall harmonic distortion rate of the three-phase output current meets a preset second distortion rate range. A first distortion rate range for each phase output current can be preset; if the harmonic distortion rate of each phase output current in the three phases of the candidate data meets the first distortion rate range, then the candidate data set is considered to meet the aforementioned requirements. Alternatively, a second distortion rate range for the overall three-phase output current can be preset; if the overall harmonic distortion rate of the three-phase output current in the candidate data meets the second distortion rate range, then the candidate data set is considered to meet the aforementioned requirements. It is understood that adding a range restriction on the harmonic distortion rate can occur before or after Pareto screening.

[0043] Reference Figure 4 As shown, in some embodiments, in step S130 above, the correlation between each parameter in the multidimensional feature dataset and the corresponding optimal modulation strategy is determined, and the top few parameters with the highest correlation are determined as key feature parameters, including: Step S410: Determine the correlation coefficients between each parameter in the multidimensional feature dataset under the same target working condition and the optimal modulation scheme of the target working condition; Step S420: Determine the screening range based on the maximum and / or minimum values ​​of the correlation coefficients, and take all parameters whose correlation coefficients are within the screening range as key feature parameters under the target working conditions, thereby determining the key feature parameters corresponding to different target working conditions.

[0044] The multidimensional feature dataset includes target sample operating parameters and compressor electrical calibration parameters under different operating conditions, which can be represented as an m*n matrix. There are m target operating conditions, meaning each target operating condition is m-dimensional. Each target operating condition has n target sample operating parameters and compressor electrical calibration parameters, meaning the feature data for each target operating condition is n-dimensional. In the correlation analysis step, for the n-dimensional feature data of the same target operating condition, the correlation between the n parameters and the optimal modulation scheme corresponding to the target operating condition is calculated. Different algorithms can be used for correlation calculation, and this application does not impose any limitations. For example, the rank correlation coefficient algorithm calculates the nonlinear correlation between each parameter and the optimal modulation scheme, which is suitable for situations where the types of parameters in the n-dimensional feature data may differ significantly, and can be compatible with calculating the correlation between different types of parameters and modulation schemes. Alternatively, analysis of variance can be used. Analysis of variance further considers whether the mean of a certain parameter is significantly different between different modulation schemes under the same target operating condition, and uses the significant correlation of the calculation results to determine the relationship between the parameter and the modulation scheme.

[0045] Taking the rank correlation coefficient algorithm as an example, the correlation coefficients of various parameters in n-dimensional feature data can be obtained. Some parameters may have lower correlations, while others may have higher correlations. It is necessary to filter the parameters to retain one or more parameters that have the strongest intrinsic correlation and influence on the optimal modulation strategy. If the filtering method follows the conventional approach of setting a fixed correlation coefficient threshold (e.g., filtering key feature parameters based on values ​​greater than the threshold), it may not be suitable for situations where the types of parameters in n-dimensional feature data can vary greatly. This is because the correlation coefficients of these parameters are often quite discrete or do not exhibit a certain distribution pattern, and a fixed correlation coefficient threshold may be inaccurate. Therefore, it is advisable to determine the filtering range based on the maximum and minimum values ​​of the correlation coefficients. For example, the average value can be calculated based on the maximum and minimum values ​​as the correlation coefficient threshold; alternatively, 30% of the maximum value can be used as the threshold; or 10 times the minimum value can be used as the threshold, and so on. This can remove most parameters that have little impact on the modulation strategy, reducing the operational burden in the cooling equipment and facilitating the rapid determination of the optimal modulation strategy.

[0046] Reference Figure 5 As shown, in some embodiments, step S140 above involves training a preset mapping model to obtain a target mapping model, including: Step S510: Train the preset mapping model based on different algorithms to obtain multiple candidate mapping models; Step S520: Select the target mapping model based on the generalization ability and prediction accuracy of the candidate mapping models.

[0047] Different algorithms can be used to train the mapping model. For example, a random forest algorithm suitable for embedded environments or a K-nearest neighbor algorithm can be used. Mapping models trained using different algorithms are retained as candidate mapping models. Based on the generalization ability and prediction accuracy of these candidate mapping models, the model with the highest generalization ability and prediction accuracy is selected as the target mapping model.

[0048] In some embodiments, embedding the target mapping model into the control system of the refrigeration equipment in step S140 above includes: The target mapping model is transformed into a decision tree; the input of the decision tree is the current operating condition of the refrigeration equipment and the acquired key feature parameters, and the output is the optimal modulation strategy of the compressor. The decision tree is then transformed into executable code or an executable program to be embedded into the control system. Alternatively, the target mapping model can be ported to the storage space of the control system; Alternatively, the target mapping model can be ported to the edge computing device of the control system, which is used to send the current operating conditions of the refrigeration equipment and the acquired key characteristic parameters to the edge computing device, as well as to receive the optimal modulation strategy of the compressor returned by the edge computing device.

[0049] The above three scenarios illustrate different ways of embedding control systems into refrigeration equipment.

[0050] The first approach involves converting the target mapping model into a decision tree, and then further converting the decision tree into code or an executable program that can be directly run on the microcontroller. This code or executable program is then embedded into the control system, which makes local decisions based on the collected key feature parameters. The second approach involves directly porting the target mapping model. A large target mapping model is stored in the control system's memory, and the control system runs the model and performs local calculations based on the collected key feature parameters. The third approach involves directly porting the target mapping model to an edge computing device. This is suitable for lightweight target mapping models. The control system sends the key feature parameters to the edge computing device, which uses these parameters to perform calculations and returns the optimal modulation scheme to the control system. This approach emphasizes online, continuous learning and optimization, rather than offline, fixed model deployment, and possesses strong environmental adaptability and long-term optimization potential.

[0051] In summary, by acquiring multiple sets of sample operating data of the compressor system under different operating conditions and modulation methods, and selecting modulation methods under different operating conditions based on the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content, the optimal modulation strategies under different target operating conditions are initially obtained. To further determine which parameters have a significant impact on the optimal modulation strategy, the target sample operating data corresponding to the target operating conditions and the compressor's electrical calibration parameters are integrated to construct a multidimensional feature dataset. Through correlation analysis of each parameter in the multidimensional feature dataset and the optimal modulation strategy, the intrinsic relationship and degree of influence between each parameter and the optimal modulation strategy are explored. The system identifies the top few key feature parameters with the highest correlation, then uses these key feature parameters to train a target mapping model. Finally, the target mapping model is embedded into the control system of the refrigeration equipment. In this way, the control system of the refrigeration equipment can obtain the optimal modulation strategy of the compressor based on the current operating conditions of the refrigeration equipment and the acquired key feature parameters, controlling the compressor to operate in two-phase modulation mode or three-phase modulation mode. Through the above method, the limitations of traditional methods that rely on fixed rules, single models or manual experience to determine the compressor modulation mode are overcome. The modulation strategy achieves dual adaptation to the differences in the compressor itself and real-time operating conditions, enhancing the overall adaptive capability and long-term operational reliability of the system.

[0052] The methods of this application will be explained in detail below through some specific examples.

[0053] Reference Figure 6 As shown, this example implements a modulation strategy to dynamically optimize the compressor's body parameters and real-time operating conditions in real time.

[0054] First, experiments were conducted on various types and models of compressors. During the experiments, key variables such as compressor speed, load, and modulation method were actively controlled, covering their typical operating range. Real-time three-phase output current and system output power were simultaneously acquired and recorded. Through in-depth analysis of the three-phase current waveforms, the total harmonic distortion rate was calculated and the main harmonic components were identified. Simultaneously, the output power was accurately evaluated to determine system power loss. Based on the dual optimization objectives of "minimizing system power loss" and "minimizing output current harmonic content," the optimal modulation method should be prioritized under specific operating conditions with different speed and load combinations, thus establishing a preliminary mapping relationship between operating conditions and modulation strategies.

[0055] Subsequently, all relevant parameters obtained during the experiment were integrated to construct a multidimensional feature dataset. This dataset not only includes control and state variables such as operating speed, real-time power, phase current amplitude, carrier frequency, and whether over-modulation was enabled, but also covers key electrical and mechanical parameters of the compressor itself, such as phase resistance, D-axis and Q-axis inductance, back electromotive force coefficient, and moment of inertia. Statistical analysis of this data was conducted to uncover the intrinsic correlation and influence between each parameter and the optimal modulation method, identifying key feature parameters.

[0056] Next, considering the actual computing power limitations of the microcontroller in the final deployment platform, the most influential subset of core features was selected from the above parameters. Using this subset of features and the labeled optimal modulation scheme results, a machine learning algorithm suitable for embedded environments, such as random forest, was employed for model training. This process aims to learn a complex nonlinear mapping model from multi-dimensional input parameters to the optimal modulation strategy, whose output is the modulation scheme decision for the current real-time operating conditions.

[0057] Finally, the optimal model with strong generalization ability and high prediction accuracy is selected from the trained models, and its structure is transformed into a logically clear and efficient decision tree. This decision tree model is then translated into code that can be directly run in the microcontroller and integrated into the compressor control system. As a result, the system can dynamically and automatically switch to the optimal modulation mode for the current operating condition based on real-time collected key parameters such as speed and load.

[0058] This method overcomes the limitations of traditional methods that rely on fixed rules, single models, or manual experience, achieving dual self-adaptation of the modulation strategy to both compressor inherent differences and real-time operating conditions. The equipment can automatically select the most suitable modulation mode based on compressor parameters and real-time operating conditions, ensuring the compressor always operates within a high-efficiency and stable range. While pursuing energy conservation, it also guarantees the waveform quality and stability of the output three-phase current, avoiding power quality problems that may be introduced due to modulation mode switching. This method reduces the need for manual intervention and enhances the overall system's adaptive capability and long-term operational reliability.

[0059] On the other hand, different adjustments can be made based on the above methods: An implementation scheme based on a simplified physical model and online optimization is proposed: a simplified energy consumption and harmonic analysis model of the compressor is established, and the optimal solution under the current operating conditions is found through online calculation. This scheme eliminates the need for offline data acquisition and model training phases. Its advantages lie in its physical interpretability and its ability to adapt to operating conditions not present in the training data.

[0060] An online self-learning scheme based on reinforcement learning treats the choice of modulation method as a decision problem and the compressor system as the environment, designing the state, action, and reward functions for reinforcement learning. A lightweight reinforcement learning algorithm runs on a microcontroller or an edge computing device communicating with it. This scheme focuses on online, continuous learning and optimization, rather than offline, fixed model deployment. Its advantages lie in its strong environmental adaptability and long-term optimization potential.

[0061] Based on the optimization method of the compressor modulation mode in the above embodiments, the following presents various embodiments of the controller, refrigeration equipment, computer-readable storage medium, and computer program product of this application.

[0062] like Figure 7 As shown, Figure 7 This is a schematic diagram of a controller for executing an optimization method for modulating a compressor, according to an embodiment of this application. The controller 100 implemented in this application includes: a processor 110, a memory 120, and a computer program stored in the memory 120 and executable on the processor 110, wherein... Figure 7 The example uses a processor 110 and a memory 120.

[0063] Processor 110 and memory 120 can be connected via a bus or other means. Figure 7 Taking the example of a connection between China and Israel via a bus.

[0064] Memory 120, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 120 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 120 may optionally include remotely located memories 120 relative to processor 110, which can be connected to controller 100 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0065] Those skilled in the art will understand that Figure 7 The device structure shown does not constitute a limitation on the controller 100 and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0066] exist Figure 7In the controller 100 shown, the processor 110 can be used to call the control program stored in the memory 120, thereby implementing the above-described method for optimizing the modulation mode of the compressor. Specifically, the non-transient software program and instructions required to implement the method for optimizing the modulation mode of the compressor in the above embodiment are stored in the memory 120. When executed by the processor 110, the method for optimizing the modulation mode of the compressor in the above embodiment is executed.

[0067] It is worth noting that, since the controller 100 of this application embodiment is capable of executing the compressor modulation mode optimization method of any of the above embodiments, the specific implementation method and technical effects of the controller 100 of this application embodiment can be referred to the specific implementation method and technical effects of the compressor modulation mode optimization method of any of the above embodiments.

[0068] Furthermore, one embodiment of this application also provides an electronic device that includes the controller described in the above embodiment.

[0069] It is worth noting that, since the electronic device of this application embodiment includes the controller of the above embodiment, and the controller of the above embodiment is capable of executing the compressor modulation mode optimization method of any of the above embodiments, the specific implementation method and technical effect of the refrigeration device of this application embodiment can refer to the specific implementation method and technical effect of the compressor modulation mode optimization method of any of the above embodiments.

[0070] Furthermore, one embodiment of this application also provides a refrigeration device, including a compressor and a control system; the control system is used to receive the optimal modulation strategy of the compressor obtained by the method described above, and control the compressor to operate in a two-phase modulation mode or a three-phase modulation mode according to the optimal modulation strategy of the compressor.

[0071] Furthermore, one embodiment of this application provides a computer-readable storage medium storing computer-executable instructions for performing the above-described method for optimizing the modulation mode of a compressor. Exemplarily, the method steps of the above-described method for optimizing the modulation mode of a compressor are performed.

[0072] It is worth noting that, since the computer-readable storage medium of this application embodiment can execute the compressor modulation mode optimization method of any of the above embodiments, the specific implementation method and technical effects of the computer-readable storage medium of this application embodiment can refer to the specific implementation method and technical effects of the compressor modulation mode optimization method of any of the above embodiments.

[0073] Furthermore, one embodiment of this application also provides a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium and executes the computer program or computer instructions, causing the computer device to perform the aforementioned method for optimizing the modulation mode of a compressor. Exemplarily, the method steps of the above-described method for optimizing the modulation mode of a compressor are executed.

[0074] It is worth noting that, since the computer program product of this application embodiment can execute the compressor modulation mode optimization method of any of the above embodiments, the specific implementation method and technical effect of the computer program product of this application embodiment can refer to the specific implementation method and technical effect of the compressor modulation mode optimization method of any of the above embodiments.

[0075] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network nodes. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0077] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed systems, instruments, and methods can be implemented in other ways. For example, the instrument embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between instruments or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0079] It should also be understood that the various implementation methods provided in this application can be combined arbitrarily to achieve different technical effects.

[0080] The above is a detailed description of the preferred embodiments of this application. However, this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for optimizing the modulation mode of a compressor, characterized in that, include: The system of the compressor is subjected to multiple sets of sample operating data under different operating conditions and different modulation methods. The sample operating data includes system input power, system output power and three-phase output current of the compressor. The modulation methods include two-phase modulation and three-phase modulation. The system power loss is determined based on the system input power and the system output power, the output current harmonic content is determined based on the three-phase output current, and the modulation method under different operating conditions is screened with the dual optimization objectives of minimizing the system power loss and minimizing the output current harmonic content, so as to obtain the correspondence between the target operating condition and the optimal modulation strategy. A multidimensional feature dataset is constructed based on the target sample operation data corresponding to the target operating condition and the electrical calibration parameters of the compressor. The correlation between each parameter in the multidimensional feature dataset and the corresponding optimal modulation strategy is determined, and the top few parameters with the highest correlation are determined as key feature parameters. Using the target operating condition and the key feature parameters as input parameters and the optimal modulation strategy as output parameters, a preset mapping model is trained to obtain a target mapping model, which is then embedded into the control system of the refrigeration equipment.

2. The method according to claim 1, characterized in that, The acquisition of multiple sets of sample operating data of the compressor system under different operating conditions and different modulation modes includes at least one of the following: Based on multiple preset operating conditions and the corresponding modulation methods, the compressor is set with operating parameters in sequence, the compressor is controlled to run under the operating conditions corresponding to the operating parameters, and sample operating data under each preset operating condition is obtained to obtain multiple sets of sample operating data. The sample operating data corresponds to the modulation method of the preset operating condition. The compressor's operating parameters and modulation methods under multiple actual operating conditions during actual operation are obtained, and the actual operating data under each actual operating condition is obtained as sample operating data to obtain multiple sets of sample operating data and modulation methods corresponding to the sample operating data.

3. The method according to claim 1, characterized in that, The sample operating data also includes at least one of the following: compressor speed, real-time power, phase current amplitude, carrier frequency, and whether modulation has been enabled; the compressor's electrical calibration parameters include at least one of the following: phase resistance, D-axis and Q-axis inductance, back electromotive force coefficient, and moment of inertia.

4. The method according to claim 1, characterized in that, The step of determining the harmonic content of the output current based on the three-phase output current includes: The phase output current of the compressor is obtained within a preset number of cycles, and the three-phase output current is obtained by averaging the phase output current according to the three-phase division. The three-phase output current is subjected to a fast Fourier transform to obtain the harmonic current of each phase output current; the harmonic current includes several odd harmonic currents other than the fundamental current. The total harmonic content is determined based on the amplitude of the harmonic current.

5. The method according to claim 4, characterized in that, The specific optimization objective for minimizing the harmonic content of the output current is as follows: The percentage of the total harmonic content of the output current of each phase to the fundamental current amplitude of the output current of each phase is determined to obtain the harmonic distortion rate of the output current of each phase. The optimization objective is to ensure that the harmonic distortion rate of at least one phase output current meets a preset first distortion rate range and / or that the overall harmonic distortion rate of the three-phase output current meets a preset second distortion rate range.

6. The method according to claim 5, characterized in that, The selection of modulation methods under different operating conditions based on the dual optimization objectives of minimizing system power loss and minimizing output current harmonic content includes: Construct a candidate set of operating conditions; each candidate set of operating conditions includes one or more sets of candidate data under the same operating condition and different modulation methods, and the candidate data consists of two elements: the system power loss and the harmonic distortion rate; Minimizing both system power loss and harmonic distortion rate are set as the objectives of Pareto screening. Pareto screening is performed on the candidate data within the same set of candidate operating conditions to obtain at least one set of target candidate data within the same set of candidate operating conditions. Determine the target operating condition corresponding to each group of target candidate data in the target operating condition candidate set, and take the modulation method corresponding to the target operating condition as the optimal modulation method for the target operating condition.

7. The method according to claim 1, characterized in that, The step of determining the correlation between each parameter in the multidimensional feature dataset and the corresponding optimal modulation strategy, and identifying the top few parameters with the highest correlation as key feature parameters, includes: Determine the correlation coefficients between each parameter in the multidimensional feature dataset under the same target operating condition and the optimal modulation scheme of the target operating condition; The screening range is determined based on the maximum and / or minimum values ​​of the correlation coefficients. All parameters whose correlation coefficients fall within the screening range are taken as key feature parameters under the target working conditions, thereby determining the key feature parameters corresponding to different target working conditions.

8. The method according to claim 1, characterized in that, The step of training a preset mapping model to obtain a target mapping model includes: The preset mapping model is trained using different algorithms to obtain multiple candidate mapping models; The target mapping model is obtained by filtering the candidate mapping models according to their generalization ability and prediction accuracy.

9. The method according to claim 1, characterized in that, The control system for embedding the target mapping model into the refrigeration equipment includes: The target mapping model is converted into a decision tree; the input of the decision tree is the current operating condition of the refrigeration equipment and the acquired key feature parameters, and the output is the optimal modulation strategy of the compressor. The decision tree is converted into executable code or an executable program to be embedded into the control system. Alternatively, the target mapping model can be ported to the storage space of the control system; Alternatively, the target mapping model can be ported to the edge computing device of the control system, wherein the control system is used to send the current operating condition of the refrigeration equipment and the acquired key feature parameters to the edge computing device, and to receive the optimal modulation strategy of the compressor returned by the edge computing device.

10. A controller, characterized in that, The method includes at least one processor and a memory for communicatively connecting to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in any one of claims 1 to 9.

11. An electronic device, characterized in that, Includes the controller as described in claim 10.

12. A refrigeration device, characterized in that, The system includes a compressor and a control system; the control system is configured to receive the optimal modulation strategy of the compressor obtained by the method as described in any one of claims 1 to 9, and control the compressor to operate in a two-phase modulation mode or a three-phase modulation mode according to the optimal modulation strategy of the compressor.

Images