Noise prediction system and method of ice maker, ice maker and refrigeration equipment

Abstract

The invention provides a noise prediction system and method for an ice maker, the ice maker and refrigeration equipment, and the system comprises a collection unit which comprises a noise sensor and is used for collecting environment noise data; the main control unit is used for preprocessing the environmental noise data, training a prediction model by using the preprocessed environmental noise data, predicting the current environmental noise change by using the trained prediction model, and generating an ice making mode adjusting instruction; and the execution unit comprises a fan control module and a compressor control module, and is used for executing the ice-making mode adjustment instruction and respectively controlling a fan and a compressor to carry out ice-making mode adjustment. The problems that an existing ice-making system lacks prediction of the noise change trend, consequently, system response lags, modes are frequently switched during short-term fluctuation, and energy consumption and equipment loss are increased are solved, the noise change trend is predicted through the autoregression model, the ice-making mode can be adaptively adjusted before environmental noise changes, and the noise change trend is predicted through the autoregression model. And the response speed and the adaptive capacity of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of noise prediction of ice machines, and in particular to a noise prediction system and method for ice machines, an ice machine, and refrigeration equipment. Background Art

[0002] As people's quality of life improves, they have higher and higher requirements for the user experience of household electrical appliances. As a common household appliance, the operating noise of the ice maker has a significant impact on the user experience. In a quiet environment, the excessive noise from the compressor and fan of the ice maker will disturb the user's daily work and rest. However, in a noisy environment, such as a family gathering or a large flow of people in a shopping mall, the noise has little impact on the user. At this time, the ice maker can be allowed to operate at a higher noise to improve work efficiency.

[0003] Existing technologies usually adjust the ice machine operation mode based on real-time noise monitoring, but lack the function of predicting noise change trends. There are the following problems: first, the system responds after the noise changes and cannot adapt to environmental needs in advance; second, it is sensitive to short-term fluctuations and may switch modes frequently, increasing energy consumption and equipment loss. Therefore, how to adjust the ice machine operation mode in advance through noise prediction technology and provide an intelligent, efficient, and low-noise solution has become a technical problem that needs to be solved urgently.

[0004] Currently, it is mainly based on real-time noise monitoring and can only make passive adjustments after the noise occurs. It lacks the ability to predict the trend of environmental noise, resulting in a delayed system response. When the environmental noise gradually decreases, the ice maker may still be in the high-efficiency ice-making mode, generating unnecessary noise interference.

[0005] Therefore, the prior art needs to be further developed. Summary of the invention

[0006] The object of the present invention is to overcome the above-mentioned technical deficiencies and provide an ice maker noise prediction system and method, an ice maker, and a refrigeration device to solve the technical problems that the ice-making system in the related art usually adjusts the ice maker operation mode based on real-time noise monitoring, lacks the function of predicting the noise change trend, resulting in a delayed system response, and frequently switches modes during short-term fluctuations, increasing energy consumption and equipment loss.

[0007] In order to achieve the above technical objectives, the present invention adopts the following technical solutions: According to a first aspect of the present invention, the present invention provides a noise prediction system for an ice maker, including a fan and a compressor, and further including: A collection unit, including a noise sensor, for collecting environmental noise data; A main control unit, which is in communication with the acquisition unit, is used to pre-process the environmental noise data, train a prediction model using the pre-processed environmental noise data, predict current environmental noise changes using the trained prediction model, and generate an ice-making mode adjustment instruction; The execution unit is connected to the main control unit for communication, and includes a fan control module and a compressor control module, and is used to execute the mode adjustment instruction and control the fan and the compressor to adjust the ice-making mode respectively.

[0008] Specifically, the main control unit has a built-in dynamic learning algorithm that can update the prediction model parameters in real time; The prediction model includes an autoregressive model.

[0009] Specifically, the fan control module controls the speed of the fan through pulse width modulation; The compressor control module controls the frequency of the compressor through frequency conversion.

[0010] Specifically, the noise prediction system of the ice maker further includes: The storage unit is used to store the collected environmental noise data, the prediction results of the prediction model, and the operating status of the fan and compressor for use in prediction model training and dynamic learning.

[0011] According to a second aspect of the present invention, there is provided an ice making machine, comprising: The noise prediction system of the ice making machine mentioned above.

[0012] According to a third aspect of the present invention, there is provided a refrigeration device, comprising: The ice machine mentioned above.

[0013] Specifically, the refrigeration equipment includes a refrigerator, a refrigerated display cabinet, and a fresh-keeping cabinet.

[0014] According to a fourth aspect of the present invention, a noise prediction method for an ice maker is provided, comprising: S100, collecting environmental noise data, and preprocessing the environmental noise data; S200, using the preprocessed environmental noise data to train a prediction model, and using the trained prediction model to predict changes in current environmental noise, and generate an ice-making mode adjustment instruction; S300: According to the ice-making mode adjustment instruction, respectively control the fan and the compressor to adjust the ice-making mode.

[0015] Specifically, the ice making mode includes: Silent mode, standard mode, high-efficiency ice-making mode.

[0016] Specifically, the method of using the trained prediction model to predict the change of the current environmental noise and generating an ice-making mode adjustment instruction includes: The prediction model includes an autoregressive model, which determines whether the current environmental noise data is less than a first preset noise threshold, and if so, generates a silent mode adjustment instruction; If not, determining whether the current environmental noise is less than a second preset noise threshold, and determining whether to generate a standard mode adjustment instruction according to the determination result; The second preset noise threshold is greater than the first preset noise threshold.

[0017] Specifically, determining whether to generate a standard mode adjustment instruction according to the judgment result includes: If the current environmental noise is less than the second preset noise threshold, determining to generate an adjustment instruction for the standard mode; If the current environmental noise is greater than or equal to the second preset noise threshold, it is determined to generate an adjustment instruction for the high-efficiency ice-making mode.

[0018] Specifically, the step of controlling the fan and the compressor to adjust the ice-making mode according to the ice-making mode adjustment instruction includes: If the ice-making mode is a silent mode, the speed of the fan is controlled to be within a first preset range, and the frequency of the compressor is controlled to be within a first preset frequency range; If the ice-making mode is the standard mode, the speed of the fan is controlled to be within a second preset range, and the frequency of the compressor is controlled to be within a second preset frequency range; If the ice-making mode is the high-efficiency ice-making mode, the rotation speed of the fan is controlled to be within a third preset range, and the frequency of the compressor is controlled to be within a third preset frequency range.

[0019] Specifically, the method further includes: The noise data collected by the noise sensor in real time is stored in the storage unit according to the preset interval time for updating the prediction model parameters.

[0020] Beneficial effects: The present invention provides a noise prediction system and method for an ice maker. A main control unit is used to preprocess collected environmental noise data, and a prediction model is trained using the preprocessed environmental noise data to predict the current environmental noise change and generate an ice making mode adjustment instruction. An execution unit executes the ice making mode adjustment instruction and controls a fan and a compressor to adjust the ice making mode respectively. This solves the problem that the current ice making system lacks prediction of noise change trends, resulting in a system response lag, and that energy consumption and equipment loss are increased due to frequent mode switching during short-term fluctuations. The present invention introduces an autoregressive model to predict noise change trends, and can adaptively adjust the ice making mode before environmental noise changes occur, further improving the response speed and adaptability of the system. Compared with traditional methods, the present invention can avoid the problem of delayed response, enter a low noise mode in a quiet environment in a timely manner, and quickly enter an efficient ice making mode in a noisy environment. It also greatly reduces the impact of short-term noise fluctuations on the system, effectively reduces the frequent switching rate of operating modes, ignores instantaneous noise changes, and switches modes only after the noise trend is stable, greatly reducing the mechanical wear of the fan and the compressor, and greatly reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Schematic diagram of the composition of the noise prediction system of the ice maker provided in a specific embodiment of the present invention; Figure 2 is a connection diagram of a noise prediction system for an ice maker provided in a specific embodiment of the present invention; Figure 3 is a flow chart of a noise prediction method for an ice maker provided in a specific embodiment of the present invention; Figure 4 is a working flow chart of a noise prediction system for an ice maker provided in a specific embodiment of the present invention; Figure 5 It is a schematic diagram of the overall operation process of the noise prediction method of the ice maker provided in the specific implementation manner of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] The present invention will be further described below in conjunction with the accompanying drawings and preferred embodiments.

[0024] Embodiment 1 According to an embodiment of the present invention, a noise prediction system for an ice maker is provided. Figure 1 and Figure 2 , including a fan and a compressor, the system further comprising: A collection unit, including a noise sensor, for collecting environmental noise data; A main control unit, which is in communication with the acquisition unit, is used to pre-process the environmental noise data, train a prediction model using the pre-processed environmental noise data, predict current environmental noise changes using the trained prediction model, and generate an ice-making mode adjustment instruction; The execution unit is connected to the main control unit for communication, and includes a fan control module and a compressor control module, and is used to execute the ice-making mode adjustment instruction and control the fan and the compressor to adjust the ice-making mode respectively.

[0025] It can be understood that the present invention utilizes a prediction model to predict the changing trend of environmental noise, so that the operating mode of the ice maker can be adjusted in advance. By modeling and updating historical noise data in real time, it can accurately predict short-term environmental noise changes. This trend prediction capability enables the ice maker to actively adapt to environmental needs rather than passively respond to current noise changes, thereby significantly improving the intelligence and adaptability of equipment operation, and solving the technical problems of the existing ice-making system lacking prediction of noise change trends, resulting in delayed system response, and frequent mode switching during short-term fluctuations, increasing energy consumption and equipment loss.

[0026] In some specific embodiments, the noise sensor is usually installed outside the ice maker to detect the environmental noise level (dB) in real time. The sampling frequency is 1Hz. The noise sensor can detect environmental noise in the range of 30dB-100dB and can adapt to different usage environments and the range of changes in general usage environment noise.

[0027] Specifically, the main control unit has a built-in dynamic learning algorithm that can update the prediction model parameters in real time; The prediction model includes an autoregressive model.

[0028] See also Figure 1In the noise prediction system of this embodiment, the main control unit (MCU) is the core computing module of the system, which is responsible for processing the noise data collected by the noise sensor, performing data preprocessing, autoregressive model training, model prediction and ice-making mode adjustment instruction generation. The main control unit has an embedded dynamic learning algorithm, which can update the prediction model parameters in real time. The dynamic learning algorithm is based on advanced machine learning principles, including an autoregressive (AR) learning algorithm, which can continuously analyze the newly acquired data and continuously adjust the various parameters in the autoregressive model to adapt to different noise environments, so as to better capture the dynamic characteristics of the noise data and greatly enhance the adaptability of the entire noise prediction system.

[0029] In some specific embodiments, in an autoregressive (AR) model, model parameters generally include the following categories: (1) Autoregressive coefficients. Autoregressive coefficients are the most important parameters in the AR model. They describe the linear relationship between current observations and past observations. These coefficients determine the dynamic characteristics of the time series, such as trend, seasonality, and periodicity. (2) Constant term: The constant term is an optional parameter in the AR model, which represents the mean or intercept of the time series, that is, the expected value when there is no influence of any lagged observations. (3) Variance of the white noise term. The variance of the white noise term is another important parameter in the AR model. It describes the magnitude of random fluctuations in the model that cannot be explained by the autoregressive part. The larger the variance of the white noise term, the greater the prediction error of the prediction model. (4) Lag order. Lag order is a key parameter of the AR model, which determines how many past observations are included in the model to predict the current value.

[0030] Furthermore, the autoregressive model in this embodiment adjusts the coefficients in the autoregressive model according to the time series characteristics of the environmental noise data. For example, if it is found that the environmental noise intensity presents a new periodic change within a certain time period, the algorithm will modify the correlation coefficients in the autoregressive model accordingly, so that the autoregressive model can more accurately reflect this change. This real-time update is a dynamic process. The algorithm will continuously optimize the parameters according to the real-time changes of the data to ensure that the prediction model always maintains a high accuracy.

[0031] Specifically, the fan control module controls the speed of the fan through pulse width modulation; The compressor control module controls the frequency of the compressor through frequency conversion.

[0032] See also Figure 1 In the noise prediction system of this embodiment, the fan control module is used to control the speed of the fan according to the adjustment instruction of the ice-making mode. The fan speed is controlled by PWM (pulse width modulation) technology. According to the switching requirements of the ice-making mode, the fan speed can be dynamically adjusted within the range of 30%-100%. The compressor control module is used to control the frequency of the compressor according to the adjustment instruction of the ice-making mode. The compressor adjusts the frequency by frequency conversion technology, and its frequency can be dynamically adjusted according to the operating mode or ice-making efficiency requirements, which further improves the intelligence and adaptability of the present invention.

[0033] Specifically, the noise prediction system of the ice maker further includes: The storage unit is used to store the collected environmental noise data, the prediction results of the prediction model, and the operating status of the fan and compressor for use in prediction model training and dynamic learning.

[0034] See also Figure 2 In the noise prediction system of this embodiment, the storage module is used to store historical noise data, prediction results and equipment operating status for model training and dynamic learning. During the operation of the ice maker, the environmental noise data is collected in real time by the noise sensor and then transmitted to the storage unit. At the same time, the prediction results of the prediction model and the operating status information of the fan and the compressor are also sent to the storage unit for storage at a certain time interval or event trigger mechanism (such as each time the fan speed is adjusted or the compressor is started / stopped). When the prediction model is trained or dynamically learned, the storage unit will provide the relevant data to the main control unit according to the demand, and the storage unit will also update the data. For example, when a new prediction result is generated or the operating status of the fan or the compressor changes, the storage unit will update the corresponding data record in time to ensure the timeliness and accuracy of the data, which can further improve the accuracy of the prediction model. The long-term stored operating status and noise data can provide a basis for optimizing the maintenance strategy of the ice maker, thereby extending the service life of the ice maker and improving the overall reliability of the ice maker.

[0035] See also Figure 2, the working process of the noise prediction system in this embodiment is explained below by a specific example: it includes a noise sensor, an MCU, a fan and compressor control module, and a storage module. The MCU is the core computing module of the system. The MCU communicates with the noise sensor, the fan and compressor control module, and the storage module respectively. The MCU receives the environmental noise data collected by the noise sensor, and then smoothes the environmental noise data to reduce the interference of short-term fluctuations that may be contained in the noise signal. Then, the prediction model is trained using the autoregressive dynamic learning algorithm embedded in the MCU, and the trained prediction model is used to predict the current real-time collected environmental noise data. According to the preset rules, an adjustment instruction for the ice-making mode is generated, and the adjustment instruction is transmitted to the fan and compressor control module to adjust the parameters of the relevant equipment, thereby realizing the switching of the ice-making mode. In this process, the storage module regularly saves the historical noise data, the prediction results, and the equipment operation status, so that the prediction model can be continuously trained and learned to improve the prediction accuracy.

[0036] It should be noted here that the present embodiment provides a noise prediction system for an ice maker, which uses a main control unit to preprocess the collected environmental noise data, and uses the preprocessed environmental noise data to train a prediction model, thereby predicting the current environmental noise change and generating an ice making mode adjustment instruction; the execution unit executes the ice making mode adjustment instruction, and controls the fan and the compressor to adjust the ice making mode respectively, thereby solving the problem that the current ice making system lacks prediction of the noise change trend, resulting in a system response lag, and due to frequent mode switching during short-term fluctuations, the energy consumption and equipment loss are increased, and the response speed and adaptability of the system are further improved. Compared with the traditional method, the present invention can avoid the problem of delayed response, enter the low noise mode in a quiet environment in time, and quickly enter the high-efficiency ice making mode in a noisy environment, which greatly reduces the impact of short-term noise fluctuations on the system, effectively reduces the frequent switching rate of the operating mode, ignores the instantaneous noise changes, and only switches the mode after the noise trend is stable, which greatly reduces the mechanical wear of the fan and the compressor, and greatly extends the service life of the equipment.

[0037] Embodiment 2 This embodiment provides an ice-making machine, including the noise prediction system for the ice-making machine described in the first embodiment.

[0038] Specifically, the noise prediction system of the ice maker includes a fan and a compressor, and the system also includes: an acquisition unit, including a noise sensor, for collecting environmental noise data; a main control unit, which is communicatively connected to the acquisition unit, and is used to preprocess the environmental noise data, train a prediction model using the preprocessed environmental noise data, predict the current environmental noise change using the trained prediction model, and generate an ice making mode adjustment instruction; an execution unit, which is communicatively connected to the main control unit, and includes a fan control module and a compressor control module, and is used to execute the ice making mode adjustment instruction, and respectively control the fan and the compressor to adjust the ice making mode.

[0039] It should be noted here that the present embodiment provides an ice-making machine, which adopts the above-mentioned noise prediction system of the ice-making machine to further improve the response speed and adaptability of the system. Compared with the traditional method, the ice-making machine in the present invention can avoid the problem of delayed response, enter the low-noise mode in a quiet environment in time, and quickly enter the high-efficiency ice-making mode in a noisy environment, which greatly reduces the impact of short-term noise fluctuations on the system, effectively reduces the frequent switching rate of operating modes, ignores instantaneous noise changes, and switches modes only after the noise trend stabilizes, which greatly reduces the mechanical wear of the fan and compressor and greatly extends the service life of the equipment.

[0040] Embodiment 3 This embodiment provides a refrigeration device, including the ice maker described in the second embodiment.

[0041] Specifically, the refrigeration equipment includes a refrigerator, a refrigerated display cabinet, and a fresh-keeping cabinet.

[0042] The refrigeration equipment of this embodiment is suitable for the above-mentioned ice-making machine, including a fan and a compressor, and also includes: a collection unit, including a noise sensor, for collecting environmental noise data; a main control unit, which is communicated with the collection unit and is used to pre-process the environmental noise data, train a prediction model using the pre-processed environmental noise data, predict the current environmental noise change using the trained prediction model, and generate an ice-making mode adjustment instruction; an execution unit, which is communicated with the main control unit and includes a fan control module and a compressor control module, for executing the ice-making mode adjustment instruction, and controlling the fan and the compressor to adjust the ice-making mode respectively.

[0043] It should be noted that the present embodiment provides a refrigeration equipment, which is applicable to the above-mentioned ice-making machine, and uses an autoregressive model to predict the noise change trend, so that the operation mode of the ice-making machine can be adjusted in advance. By modeling and updating the historical noise data in real time, the system can accurately predict the environmental noise changes in the short term. This trend prediction capability enables the ice-making machine to actively adapt to environmental needs rather than passively respond to current noise changes, thereby significantly improving the intelligence and adaptive ability of the operation of the refrigeration equipment. Since the ice-making machine adopts a noise prediction system, it can accurately predict the noise of the ice-making machine under different operating conditions. In refrigeration equipment (such as refrigerators, refrigerated display cabinets, fresh-keeping cabinets, etc.), when the noise prediction system of the ice-making machine works accurately, it can indirectly reflect the working efficiency of the ice-making machine and avoid unnecessary energy waste. In refrigeration equipment such as refrigerators, the optimization of the energy consumption of the ice-making machine helps to reduce the power consumption of the equipment as a whole, achieve energy-saving effects, and greatly expand the application scenarios of the present invention.

[0044] Embodiment 4 This embodiment provides a noise prediction method for an ice maker, including: S100, collecting environmental noise data, and preprocessing the environmental noise data; S200, using the preprocessed environmental noise data to train a prediction model, and using the trained prediction model to predict changes in current environmental noise, and generate an ice-making mode adjustment instruction; S300: According to the ice-making mode adjustment instruction, respectively control the fan and the compressor to adjust the ice-making mode.

[0045] It can be understood that by adopting the prediction model of environmental noise, it is possible to make short-term predictions on the changing trends of environmental noise and adjust the operating mode of the ice maker in advance, thereby solving the technical problem of delayed response of the existing ice-making system. By actively adapting to the changing trends of noise, the ice maker can quickly enter the silent mode in a quiet environment and switch to the efficient ice-making mode in a noisy environment, which further improves the accuracy of the prediction, reduces the energy consumption of the equipment, and greatly improves the intelligence, usability and reliability of the present invention.

[0046] See also Figure 3-Figure 5 The noise prediction method of the ice making machine in this embodiment includes: S100, collecting environmental noise data, and preprocessing the environmental noise data; In the noise prediction method of this embodiment, the noise sensor collects environmental noise data at a frequency of 1 Hz. Since the noise signal may contain short-term fluctuations, in order to reduce such interference, the environmental noise data is smoothed by moving mean filtering.

[0047] S200, using the preprocessed environmental noise data to train a prediction model, and using the trained prediction model to predict changes in current environmental noise, and generate an ice-making mode adjustment instruction; Specifically, the ice making mode includes: Silent mode, standard mode, high-efficiency ice-making mode.

[0048] Preferably, the present embodiment sets the ice-making mode to silent mode, standard mode, and high-efficiency ice-making mode. When the noise in the environment is small, that is, in a quiet environment, the silent mode is required to make ice. When the environmental noise increases and in an environment with a certain amount of noise, it is necessary to quickly switch to the standard mode for ice-making. When the environmental noise continues to increase, that is, in a very noisy environment, the high-efficiency ice-making mode can be quickly entered for ice-making, so that the ice maker can adaptively adjust the ice-making mode, which greatly improves the intelligence of the equipment operation and reduces energy consumption.

[0049] Specifically, the method of using the trained prediction model to predict the change of the current environmental noise and generating an ice-making mode adjustment instruction includes: The prediction model includes an autoregressive model, which determines whether the current environmental noise data is less than a first preset noise threshold, and if so, generates a silent mode adjustment instruction; If not, determining whether the current environmental noise is less than a second preset noise threshold, and determining whether to generate a standard mode adjustment instruction according to the determination result; The second preset noise threshold is greater than the first preset noise threshold.

[0050] Preferably, the prediction model in this embodiment can be preferably an autoregressive model. At the same time, the first preset noise threshold is preferably 40dB, and the second preset noise threshold is preferably 60dB. The above settings are set based on the noise distribution in the daily life environment, which can cover most usage scenarios. At the same time, the personalized needs of users in specific scenarios are also taken into account. Therefore, the decibel range in the design can be used as a variable, and the preset noise threshold can be customized through the user interface according to the actual needs of the user to meet the personalized needs of the user in a specific scenario.

[0051] Furthermore, if the current environmental noise data is less than 40dB, a silent mode adjustment instruction is generated; if the current environmental noise data is greater than or equal to 40dB, it is determined whether the current environmental noise is less than 60dB, and whether to generate a standard mode adjustment instruction is determined based on the judgment result, thereby achieving accurate prediction of environmental noise changes in the short term, allowing the ice maker to actively adapt to environmental requirements rather than passively responding to current noise changes, thereby significantly improving the intelligence and adaptability of the equipment operation, effectively improving the operating efficiency of the ice maker and reducing energy consumption, while meeting the needs of users for the operating status and noise control of the ice maker in different environments.

[0052] Specifically, determining whether to generate a standard mode adjustment instruction according to the judgment result includes: If the current environmental noise is less than the second preset noise threshold, determining to generate an adjustment instruction for the standard mode; If the current environmental noise is greater than or equal to the second preset noise threshold, it is determined to generate an adjustment instruction for the high-efficiency ice-making mode.

[0053] It can be understood that if the current ambient noise is less than 60dB, it is determined to generate an adjustment instruction for the standard mode; if the current ambient noise is greater than or equal to 60dB, it is determined to generate an adjustment instruction for the high-efficiency ice-making mode, which solves the technical problems of poor user experience and energy waste caused by the delayed response of the traditional ice-making system. It enters the low-noise mode, i.e., the silent mode, in a quiet environment in time, enters the standard mode in a certain noise environment, and quickly enters the high-efficiency ice-making mode in a noisy environment, which greatly improves the response speed and adaptability of the ice-making system of the present invention.

[0054] S300: According to the ice-making mode adjustment instruction, respectively control the fan and the compressor to adjust the ice-making mode.

[0055] Specifically, the step of controlling the fan and the compressor to adjust the ice-making mode according to the ice-making mode adjustment instruction includes: If the ice-making mode is a silent mode, the speed of the fan is controlled to be within a first preset range, and the frequency of the compressor is controlled to be within a first preset frequency range; If the ice-making mode is the standard mode, the speed of the fan is controlled to be within a second preset range, and the frequency of the compressor is controlled to be within a second preset frequency range; If the ice-making mode is the high-efficiency ice-making mode, the rotation speed of the fan is controlled to be within a third preset range, and the frequency of the compressor is controlled to be within a third preset frequency range.

[0056] Preferably, in this embodiment, the first preset range is set to 30%-50% of the maximum speed of the fan, the second preset range is set to 50%-70% of the maximum speed of the fan, the third preset range is set to 80%-100% of the maximum speed of the fan, the first preset frequency range is set to 20Hz-30Hz, the second preset frequency range is set to 40Hz-50Hz, and the first preset frequency range is set to 60Hz-70Hz. The above settings are based on the design parameters of the equipment and the actual operation requirements. The hardware specifications of ice makers of different models may be different, and the maximum and minimum frequencies / speeds that can be operated may be inconsistent. Therefore, the adjustment range is described using relative values. The present invention does not further limit the specific values ​​of the above preset parameters. For example, if the maximum speed of the fan is 2000RPM, the silent mode corresponds to 600-1000RPM. This can adapt to different models of equipment while ensuring the balance between noise control and the working performance of the ice maker system. The system automatically completes the adjustment according to the percentage.

[0057] Further, in some specific embodiments, if the ice-making mode is a silent mode, the speed of the fan is controlled to be 30%-50% of the maximum speed, and the frequency of the compressor is controlled to be 20Hz-30Hz; If the ice-making mode is the standard mode, the fan speed is controlled at 50%-70% of the maximum speed, and the compressor frequency is controlled at 40Hz-50Hz; if the ice-making mode is the high-efficiency ice-making mode, the fan speed is controlled at 80%-100% of the maximum speed, and the compressor frequency is controlled at 60Hz-70Hz. The precise control of the fan speed and the compressor frequency in different ice-making modes has obvious energy-saving effects. The precise control of the ice-making mode avoids energy waste when high-efficiency ice-making is not required. The appropriate ice-making mode can be selected according to different usage environments to control noise, which greatly optimizes and improves the applicability of the ice maker.

[0058] Specifically, the method further includes: The noise data collected by the noise sensor in real time is stored in the storage unit according to the preset interval time for updating the prediction model parameters.

[0059] In some specific embodiments, the noise sensor collects noise data in real time, which ensures continuous monitoring of the noise conditions of the ice maker and its surrounding environment. The data is stored in the storage unit according to the preset interval time. The preset interval time can be set to collect data every 5 minutes. While ensuring data integrity, storage and computing resources can be reasonably used. The parameter update of the prediction model (such as the autoregressive model) is based on the newly collected data. The incremental learning method can be used, that is, the parameters of the model are fine-tuned each time using new data instead of retraining the entire model. For example, for the autoregressive coefficient in the autoregressive model, the value of the coefficient is adjusted according to the statistics (such as mean, variance, etc.) calculated from the new noise data. This incremental learning method can save computing resources and enable the model to quickly adapt to changes in the noise characteristics of the ice maker. By collecting noise data in real time and updating the prediction model parameters, the model can capture these changes in time, so that the prediction model can better adapt to different environmental conditions, extend the service life of the ice maker, and more accurately predict the environmental noise prediction and select a reasonable ice-making mode, which greatly reduces the excessive wear of the ice maker components.

[0060] See also Figure 4 and Figure 5 The following takes the establishment of an autoregressive model as an example to illustrate the working process of the present invention: Step 1: Data collection and preprocessing (1) Noise data collection: The noise sensor collects environmental noise data at a frequency of 1 Hz and records it as a time series. , (2) Data smoothing: The noise signal may contain short-term fluctuations. To reduce this interference, it is processed through moving mean filtering: ; Among them, t represents the current time point, and w represents the window size of the moving mean filter.

[0061] Step 2: Autoregressive model training and prediction (1) Definition of autoregressive model: Noise prediction is based on the autoregressive model (AR model), and its mathematical form is: ; in, is the autoregressive coefficient, which indicates the weight of each historical point on the current value. is the noise prediction error, p is the order of the AR model, indicating how many historical data points are used for prediction, and t represents the current time point.

[0062] (2) Model training: Use historical noise data to train the AR model and determine the autoregressive coefficients , the data matrix form is: ; Among them, Y represents the target vector of historical noise values, that is, the actual observed value of the noise data sequence, The input matrix is ​​the historical noise value, is the regression coefficient vector, Represents the prediction error.

[0063] It can be solved by the least squares method , the specific method is: ; (3) Short-term prediction: Based on the trained Predicting future noise values : Step 3: Switch to ice making mode (1) Based on the prediction results , the system switches to ice-making mode in advance: Silent Mode: ; Standard Mode: ; Efficient ice making mode: ; Step 4: Adjust ice making mode parameters Silent mode: Reduce the fan speed to 30%-50% of the maximum speed, and reduce the compressor operating frequency to the minimum (20Hz to 30Hz); Standard mode: fan speed drops to 50%-70% of maximum speed, compressor frequency is medium (40Hz-50Hz); High-efficiency ice-making mode: fan speed is 80%-100% of the maximum speed, and the compressor frequency is maximum (60Hz to 70Hz); Step 5: Dynamic Learning and Optimization First, the system regularly adds the latest noise data to historical data to update the AR model. Second, it uses sliding window technology to retain the most recent K data points to improve the real-time and adaptability of the model.

[0064] The accuracy of AR model training is judged through relevant error analysis. The specific process is as follows: 1. Residual analysis evaluation During the training process of the AR model, the predicted value of the model is calculated and the actual noise value The residual between To evaluate the training accuracy: ; ; in, is the root mean square error; 2. Goodness of fit (R²) evaluation The coefficient of determination R² is used to assess the model's fit to historical noise data: ; 3. Real-time prediction error evaluation During the actual model training process, the predicted value is verified by the noise data collected in real time, and the prediction error is measured by the following indicators: Mean absolute error (MAE): ; 4. Dynamic window optimization In order to improve the real-time and adaptability of the model, the system uses sliding window technology to dynamically update the training data. The choice of window length k affects the prediction accuracy and real-time performance of the model. By testing the MSE and MAE under different k values ​​(such as k=50, 100, 150), the window length that minimizes the error index is selected while taking real-time into account.

[0065] 5. Accuracy threshold setting In actual applications, the system will dynamically determine whether the accuracy meets the requirements based on whether the model's prediction error meets the set threshold. For example, if MSE<0.05, R²>0.8, and MAE<1dB in real-time evaluation, the model training accuracy can be considered to meet the requirements.

[0066] It should be noted here that the present embodiment provides a noise prediction method for an ice maker, wherein the main control unit is used to preprocess the collected environmental noise data, and the preprocessed environmental noise data is used to train a prediction model, thereby predicting the current environmental noise change and generating an ice making mode adjustment instruction; the execution unit executes the ice making mode adjustment instruction, and controls the fan and the compressor to adjust the ice making mode respectively, thereby solving the technical problems that the current ice making system lacks prediction of the noise change trend, resulting in a system response lag, and frequently switches modes during short-term fluctuations, increasing energy consumption and equipment loss. The present invention introduces an autoregressive model to predict the noise change trend, and can adaptively adjust the ice making mode before the environmental noise changes, thereby further improving the response speed and adaptability of the system. Compared with the traditional method, the present invention can avoid the problem of delayed response, enter the low noise mode in a quiet environment in time, and quickly enter the high-efficiency ice making mode in a noisy environment, and also greatly reduce the impact of short-term noise fluctuations on the system, effectively reduce the frequent switching rate of the operating mode, ignore the instantaneous noise changes, and only switch the mode after the noise trend is stable, thereby greatly reducing the mechanical wear of the fan and the compressor, and greatly reducing energy consumption.

[0067] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0069] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0070] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0071] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A noise prediction system for an ice machine, comprising a fan and a compressor, characterized in that: Also includes: A collection unit, including a noise sensor, for collecting environmental noise data; A main control unit, which is in communication with the acquisition unit, is used to pre-process the environmental noise data, train a prediction model using the pre-processed environmental noise data, predict current environmental noise changes using the trained prediction model, and generate an ice-making mode adjustment instruction; The execution unit is connected to the main control unit for communication, and includes a fan control module and a compressor control module, and is used to execute the ice-making mode adjustment instruction and control the fan and the compressor to adjust the ice-making mode respectively.

2. The noise prediction system for an ice-making machine according to claim 1, characterized in that: The main control unit has a built-in dynamic learning algorithm that can update the prediction model parameters in real time; The prediction model includes an autoregressive model.

3. The noise prediction system for an ice-making machine according to claim 1, characterized in that: The fan control module controls the speed of the fan through pulse width modulation; The compressor control module controls the frequency of the compressor through frequency conversion.

4. The noise prediction system for an ice-making machine according to claim 1, characterized in that: The noise prediction system of the ice making machine also includes: The storage unit is used to store the collected environmental noise data, the prediction results of the prediction model, and the operating status of the fan and compressor for use in prediction model training and dynamic learning.

5. An ice making machine, characterized in that: include: The noise prediction system for an ice-making machine according to any one of claims 1 to 4.

6. A refrigeration device, characterized in that: include: The ice making machine of claim 5.

7. The refrigeration equipment according to claim 6, characterized in that The refrigeration equipment includes a refrigerator, a refrigerated display cabinet, and a fresh-keeping cabinet.

8. A noise prediction method for an ice machine, characterized in that: include: S100, collecting environmental noise data, and preprocessing the environmental noise data; S200, using the preprocessed environmental noise data to train a prediction model, and using the trained prediction model to predict changes in current environmental noise, and generate an ice-making mode adjustment instruction; S300: According to the ice-making mode adjustment instruction, respectively control the fan and the compressor to adjust the ice-making mode.

9. The noise prediction method of an ice-making machine according to claim 8, characterized in that: The ice making mode includes: Silent mode, standard mode, high-efficiency ice-making mode.

10. The noise prediction method of an ice-making machine according to claim 9, characterized in that: The method of using the trained prediction model to predict the change of the current environmental noise and generating an ice-making mode adjustment instruction includes: The prediction model includes an autoregressive model, which determines whether the current environmental noise data is less than a first preset noise threshold, and if so, generates a silent mode adjustment instruction; If not, determining whether the current environmental noise is less than a second preset noise threshold, and determining whether to generate a standard mode adjustment instruction according to the determination result; The second preset noise threshold is greater than the first preset noise threshold.

11. The noise prediction method of an ice-making machine according to claim 10, characterized in that: The step of determining whether to generate a standard mode adjustment instruction according to the judgment result includes: If the current environmental noise is less than the second preset noise threshold, determining to generate an adjustment instruction for the standard mode; If the current environmental noise is greater than or equal to the second preset noise threshold, it is determined to generate an adjustment instruction for the high-efficiency ice-making mode.

12. The ice machine noise prediction method according to claim 11, characterized in that: The step of controlling the fan and the compressor to adjust the ice-making mode according to the ice-making mode adjustment instruction comprises: If the ice-making mode is a silent mode, the speed of the fan is controlled to be within a first preset range, and the frequency of the compressor is controlled to be within a first preset frequency range; If the ice-making mode is the standard mode, the speed of the fan is controlled to be within a second preset range, and the frequency of the compressor is controlled to be within a second preset frequency range; If the ice-making mode is the high-efficiency ice-making mode, the rotation speed of the fan is controlled to be within a third preset range, and the frequency of the compressor is controlled to be within a third preset frequency range.

13. The noise prediction method of an ice-making machine according to claim 8, characterized in that: The method further comprises: The noise data collected by the noise sensor in real time is stored in the storage unit according to the preset interval time for updating the prediction model parameters.

Images