An AI-based intelligent control method, system, and storage medium for an ice maker.

Abstract

This invention relates to the field of intelligent control technology and discloses an AI-based intelligent control method, system, and storage medium for an ice maker. The method includes: real-time acquisition of water storage status data, AI dynamic analysis of water storage demand, dynamic adjustment of refrigeration path and ice-making parameters, optimized control of the ice-making process, and early warning and self-repair for abnormal states. The system includes a multi-source sensor module, a data acquisition and preprocessing module, an AI analysis and decision-making module, a dynamic priority scheduling algorithm, a control execution module, and a human-machine interaction module. The storage medium includes a real-time control thread, a data storage thread, and a remote upgrade interface. By dynamically analyzing water storage demand through AI, the system can adjust the water storage temperature in real time according to actual usage needs, avoiding the temperature fluctuation problem caused by traditional ice makers relying on fixed temperature settings. This significantly improves the stability of the water storage temperature, thereby ensuring the quality of the drinking water and ice produced by the ice maker.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to an intelligent control method, system, and storage medium for an ice maker based on AI analysis. Background Technology

[0002] As people's living standards improve and their pursuit of a healthy lifestyle increases, they are paying more and more attention to various aspects of their diet. Among these, drinking water, as the foundation of diet, is of utmost importance. Ice makers, as an indispensable household appliance, primarily provide convenient drinking water services, including room temperature water, cold water, and ice cubes. Traditional ice makers mostly use a refrigeration system to directly cool the water in the tank to produce cold water, and then further generate ice cubes through an ice-making module.

[0003] A search revealed Chinese patent CN118794177A, which discloses an intelligent control method and device for an ice maker, as well as the ice maker itself. By implementing this invention, when a user demand for the ice maker is detected, the system can automatically collect water storage information from the hot water component and determine whether the stored water has been heated to a first supply temperature. If so, it generates a control command corresponding to the user demand and then executes equipment control on the ice maker according to the control command. The collection of water storage information and the comparison with the first supply temperature ensure that the current water storage in the hot water component meets the subsequent water supply requirements during equipment control operations, improving the accuracy of the current water supply. After the current water storage reaches the first supply temperature, it helps improve the cleanliness of the drinking water / ice cubes output by the ice maker. Furthermore, this equipment control operation can also achieve intelligent adjustment of the refrigeration path.

[0004] However, the water temperature management of the aforementioned ice makers typically relies on fixed temperature settings, which cannot be dynamically adjusted according to actual usage needs. This results in significant fluctuations in the water temperature, affecting the quality of the drinking water and ice produced by the ice maker. Furthermore, traditional ice makers lack real-time monitoring and intelligent analysis of the water storage status during the ice-making process, easily leading to ice-making starting before the water temperature reaches the ideal state, thus affecting the shape and cleanliness of the ice. Based on this, the present invention designs an AI-based intelligent control method, system, and storage medium for ice makers to solve the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent control method, system, and storage medium for ice makers based on AI analysis, which solves the problem in the prior art that it is impossible to adjust according to actual usage needs.

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

[0007] An AI-based intelligent control method, system, and storage medium for an ice maker, comprising:

[0008] Step S1: Real-time collection of water storage status data. The water temperature data in the storage tank is collected by a temperature sensor at a frequency of once per second. The water level in the storage tank is monitored by a water level sensor, and the trigger threshold is set to a minimum water level of 100 mm. The water quality parameters are detected by a turbidity sensor, and the cleaning mode is triggered when the turbidity reaches 50 NTU.

[0009] Step S2: AI dynamically analyzes water storage demand. The real-time collected data on water temperature, water level, and water quality are input into a prediction model based on a long short-term memory network. The model has 3 nodes in the input layer and 64 nodes in the hidden layer. The output layer is a classification label for water storage demand, which includes immediate ice making, delayed ice making, and cleaning priority.

[0010] Step S3: Dynamically adjust the cooling path and ice-making parameters. When the AI ​​determines that ice is to be made immediately, start the dual-stage compression cooling system to reduce the water storage temperature from the initial temperature of 20 degrees Celsius to the target temperature of 4 degrees Celsius. When the AI ​​determines that ice is to be made in a delayed manner, start the energy-saving mode to maintain the water storage temperature at 8 degrees Celsius. When the AI ​​determines that cleaning is the priority, activate the ultraviolet sterilization module and start the drain pump to change the water.

[0011] Step S4: Optimize and control the ice-making process. Use a fuzzy PID algorithm to adjust the blade speed of the ice-making module and dynamically adjust the cutting frequency based on feedback data from the ice thickness sensor. Adjust the ice-making cycle according to the ambient temperature. Shorten the ice-making cycle when the ambient temperature is above 25 degrees Celsius and extend the ice-making cycle when the ambient temperature is below 15 degrees Celsius.

[0012] Preferably, the system also includes step S5, which is an abnormal state warning and self-repair. The compressor's operating status is monitored by a vibration sensor. When the vibration amplitude reaches 0.5g, an early warning is triggered. If the water temperature does not drop by 2 degrees Celsius within 5 minutes after the cooling starts, it is determined that there is a refrigerant leak and a system shutdown command is triggered.

[0013] Preferably, in step S2, the training process of the Long Short-Term Memory network prediction model is as follows:

[0014] Step S201: Collect water storage temperature, water level and water quality data at 15-minute intervals for at least the past year, along with corresponding water storage demand labels, as a training dataset.

[0015] Step S202: Divide the training dataset into a training set, a validation set, and a test set, with proportions of 70%, 15%, and 15%, respectively.

[0016] Step S203: The loss function adopted is the cross-entropy loss function, which is used to measure the difference between the classification label predicted by the model and the actual label.

[0017] Step S204: During the training process, when the loss value on the validation set no longer decreases within 5 consecutive training cycles, training is stopped early to prevent overfitting.

[0018] Preferably, in step S2, the two-stage compression refrigeration system includes:

[0019] There are two sets of compressors: a high-pressure compressor and a low-pressure compressor. The high-pressure compressor has a discharge capacity of 10 m³ / h, and the low-pressure compressor has a discharge capacity of 8 m³ / h.

[0020] There are two sets of condensers, a high-pressure condenser and a low-pressure condenser, with condensation areas of 5m² and 4m², respectively.

[0021] There are two sets of evaporators, a high-pressure evaporator and a low-pressure evaporator, with evaporation areas of 3m² and 2m², respectively.

[0022] The refrigerant used in the two-stage compression refrigeration system is R410A. The charge amount is precisely calculated and adjusted according to the system design and actual operation to ensure the efficient operation of the refrigeration system.

[0023] Preferably, in step S4, the specific parameters of the fuzzy PID algorithm are set as follows: the initial value of the proportional coefficient is 0.6, which is dynamically adjusted according to the deviation of the ice thickness, with a maximum of no more than 1.2; the initial value of the integral coefficient is 0.1, which is used to eliminate the steady-state error of the ice thickness, and is adjusted according to the cumulative amount of deviation, with a maximum of no more than 0.3; the initial value of the derivative coefficient is 0.05, which is used to predict the changing trend of the ice thickness, and is adjusted according to the rate of change of the deviation, with a maximum of no more than 0.1.

[0024] Preferably, an AI-based intelligent control system for an ice maker includes the following modules:

[0025] Module S1 is a multi-source sensor module, including a temperature sensor group containing a water tank temperature sensor and an ambient temperature sensor; it also includes a water quality monitoring module that integrates a turbidity sensor and a pH sensor.

[0026] Module S2, the data acquisition and preprocessing module, uses a microcontroller for data acquisition with a sampling frequency of 1 kHz; data preprocessing includes Kalman filtering and median filtering.

[0027] Module S3, the AI ​​analysis and decision-making module, is a long short-term memory network model deployed on edge computing devices, with an inference latency of no more than 50 milliseconds.

[0028] Module S4, a dynamic priority scheduling algorithm, adjusts the cooling strategy according to user preset preferences.

[0029] Module S5 is the control and execution module, the refrigeration system drive circuit, which uses PWM voltage regulation technology to control the compressor speed; the mechanical actuator includes a blade assembly driven by a stepper motor and a drainage passage controlled by a solenoid valve.

[0030] Module S6 is a human-computer interaction module with a touchscreen display of real-time data and operation interface; it supports voice command recognition with a response time of no more than 0.5 seconds.

[0031] Preferably, in module S4, the dynamic priority scheduling algorithm further includes the following parameters: according to the user's preset preferences, the cooling strategy is divided into three modes: high efficiency priority, low energy consumption priority, and fast cooling priority; in the high efficiency priority mode, the energy efficiency ratio of the cooling system is not less than 3.5; in the low energy consumption priority mode, the energy consumption of the cooling system is reduced by not less than 20%.

[0032] Preferably, in module S5, the refrigeration system drive circuit uses PWM voltage regulation technology to control the compressor speed, the frequency of the PWM signal is 20kHz, and the duty cycle adjustment range is 10%-90%; the response time of the drain passage controlled by the solenoid valve does not exceed 50ms, so as to improve the accuracy of the solenoid valve.

[0033] Preferably, an AI-based intelligent control storage medium for an ice maker includes the following program code:

[0034] Program S1 is a real-time control thread with the highest priority set as the real-time operating system task level and a scheduling cycle of 1ms. It includes a fuzzy PID control instruction set for adjusting the compressor speed and blade cutting frequency.

[0035] Program S2 is a data storage thread that uses a circular buffer mechanism with a buffer size of 1MB and a data persistence period of 60 minutes. The stored content includes raw sensor data and control logs.

[0036] Program S3 is a remote upgrade interface that supports HTTPS protocol for communication with OTA servers and a firmware differential upgrade algorithm. Firmware verification uses the SHA-256 hash algorithm, and it automatically rolls back to the previous stable version when the upgrade fails.

[0037] Preferably, in program S2, the sensor raw data and control logs further include a log hierarchical storage strategy, with the operating status log being saved for 30 days and stored in CSV format; abnormal alarm logs being permanently stored, encrypted, and uploaded to the cloud; and a log retrieval function supporting time range queries and keyword filtering.

[0038] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0039] 1. This invention uses AI to dynamically analyze water storage demand and adjust the water storage temperature in real time according to actual usage needs. This avoids the temperature fluctuation problem caused by traditional ice makers relying on fixed temperature settings. During periods of high demand, the system quickly cools to the target temperature; during periods of low demand, it maintains an energy-saving mode, significantly improving the stability of the water storage temperature and thus ensuring the quality of the drinking water and ice produced by the ice maker.

[0040] 2. This invention uses multiple sensors, including those for temperature, water level, turbidity, pH value, and vibration, to collect real-time status data from the water storage tank and compressor. This data is then analyzed intelligently using a long short-term memory network model. This multi-dimensional real-time monitoring and dynamic decision-making mechanism effectively prevents ice making from starting before the water temperature reaches the ideal level, thus significantly improving the shape and cleanliness of the ice.

[0041] 3. This invention employs a two-stage compression refrigeration system, in which the high-pressure compressor and the low-pressure compressor work together, along with an optimized condenser and evaporator, significantly improving refrigeration efficiency. In high-efficiency priority mode, the system also dynamically adjusts the refrigeration path and ice-making parameters, enabling rapid cooling during high demand and reduced energy consumption during low demand, thus achieving a balance between high efficiency and energy saving. Attached Figure Description

[0042] Figure 1 This is a flowchart of the intelligent control method for an ice maker according to the present invention;

[0043] Figure 2 This is a flowchart of the training process for the Long Short-Term Memory Network prediction model of the present invention;

[0044] Figure 3 This is a schematic diagram of the two-stage compression refrigeration system of the present invention;

[0045] Figure 4 This is a schematic diagram of the fuzzy PID algorithm of the present invention;

[0046] Figure 5 This is a structural diagram of the intelligent control system module for the ice maker of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Example 1; please refer to Figures 1-5A smart control method for an ice maker based on AI analysis includes: Step S1, real-time collection of water storage status data, including collecting water temperature data in the storage tank via a temperature sensor at a frequency of once per second; monitoring the water level in the storage tank via a water level sensor, with a trigger threshold set to a minimum water level of 100 mm; detecting water quality parameters via a turbidity sensor, triggering a cleaning mode when the turbidity reaches 50 NTU; Step S2, AI dynamically analyzing water storage demand, inputting the real-time collected water temperature, water level, and water quality data into a prediction model based on a long short-term memory network, with 3 nodes in the input layer and 64 nodes in the hidden layer, and the output layer being a classification label for water storage demand, including immediate ice making, delayed ice making, and cleaning priority; Step S3 Step S3: Dynamically adjust the cooling path and ice-making parameters. When the AI ​​determines immediate ice making, it activates the dual-stage compression refrigeration system to lower the water storage temperature from the initial temperature of 20 degrees Celsius to the target temperature of 4 degrees Celsius. When the AI ​​determines delayed ice making, it activates the energy-saving mode to maintain the water storage temperature at 8 degrees Celsius. When the AI ​​determines cleaning priority, it activates the ultraviolet sterilization module and simultaneously starts the drain pump to change the water. Step S4: Optimize and control the ice-making process. Use a fuzzy PID algorithm to adjust the blade speed of the ice-making module and dynamically adjust the cutting frequency based on feedback data from the ice thickness sensor. Adjust the ice-making cycle according to the ambient temperature. Shorten the ice-making cycle when the ambient temperature is above 25 degrees Celsius and extend the ice-making cycle when the ambient temperature is below 15 degrees Celsius. Step S5: Abnormal state warning and self-repair. Monitor the compressor's operating status through a vibration sensor. Trigger an alarm when the vibration amplitude reaches 0.5g. If the water temperature does not drop by 2 degrees Celsius within 5 minutes after the cooling starts, it is determined to be a refrigerant leak and triggers a system shutdown command.

[0049] In step S2, the training process of the Long Short-Term Memory Network prediction model is as follows: Step S201, collect water storage temperature, water level, and water quality data at 15-minute intervals for at least the past year, along with corresponding water storage demand labels, as the training dataset; Step S202, divide the training dataset into a training set, a validation set, and a test set, with proportions of 70%, 15%, and 15%, respectively; Step S203, use the cross-entropy loss function to measure the difference between the classification labels predicted by the model and the actual labels; Step S204, during the training process, stop training early when the loss value on the validation set no longer decreases within 5 consecutive training cycles to prevent overfitting.

[0050] In step S2, the two-stage compression refrigeration system includes: two sets of compressors, namely a high-pressure compressor and a low-pressure compressor, with a discharge capacity of 10 m³ / h for the high-pressure compressor and 8 m³ / h for the low-pressure compressor; two sets of condensers, namely a high-pressure condenser and a low-pressure condenser, with condensing areas of 5 m² and 4 m², respectively; and two sets of evaporators, namely a high-pressure evaporator and a low-pressure evaporator, with evaporating areas of 3 m² and 2 m², respectively. The refrigerant used in the two-stage compression refrigeration system is R410A, and its charge amount is precisely calculated and adjusted according to the system design and actual operation to ensure the efficient operation of the refrigeration system.

[0051] In step S4, the specific parameters of the fuzzy PID algorithm are set as follows: the initial value of the proportional coefficient is 0.6, which is dynamically adjusted according to the deviation of the ice thickness, with a maximum of 1.2; the initial value of the integral coefficient is 0.1, which is used to eliminate the steady-state error of the ice thickness, and is adjusted according to the cumulative amount of deviation, with a maximum of 0.3; the initial value of the derivative coefficient is 0.05, which is used to predict the changing trend of the ice thickness, and is adjusted according to the rate of change of deviation, with a maximum of 0.1.

[0052] The working principle of this invention is as follows: The system collects key parameters in the water storage tank in real time through a multi-source sensor module, including water temperature, water level, turbidity, and pH value, while simultaneously monitoring ambient temperature and compressor vibration. The sensor data is collected once per second to ensure real-time performance and accuracy. After data acquisition, the microcontroller performs preprocessing, employing Kalman filtering and median filtering techniques to eliminate noise interference and ensure the quality of the data input to the AI ​​analysis module. For example, when the turbidity sensor detects a turbidity level of 50 NTU, the system triggers a cleaning mode, activating the ultraviolet sterilization module and drain pump for automatic water replacement.

[0053] The collected data on water storage temperature, water level, and water quality were input into a prediction model based on a long short-term memory network. This model learns the dynamic changes in water storage demand by training on historical data. The model has 3 nodes in the input layer, 64 nodes in the hidden layer, and the output layer contains the classification labels for water storage demand. The model optimizes prediction accuracy using a cross-entropy loss function and stops training when the validation set loss value no longer decreases for 5 consecutive cycles to prevent overfitting.

[0054] Example 2; please refer to Figures 1-5In this embodiment of the invention, an AI-based intelligent control system for an ice maker includes the following modules: Module S1, a multi-source sensor module, including a temperature sensor group comprising a water tank temperature sensor and an ambient temperature sensor; it also includes a water quality monitoring module integrating a turbidity sensor and a pH sensor; Module S2, a data acquisition and preprocessing module, employing a microcontroller for data acquisition at a sampling frequency of 1 kHz; data preprocessing includes Kalman filtering and median filtering; Module S3, an AI analysis and decision-making module, deploying a long short-term memory network model on an edge computing device with an inference latency not exceeding 50 milliseconds; Module S4, a dynamic priority scheduling algorithm, adjusting the refrigeration strategy according to user preset preferences; Module S5, a control execution module, including a refrigeration system drive circuit, employing PWM voltage regulation technology to control the compressor speed; a mechanical actuator, including a stepper motor-driven blade assembly and a drainage path controlled by a solenoid valve; Module S6, a human-machine interaction module, displaying real-time data and an operation interface on a touchscreen; supporting voice command recognition with a response time not exceeding 0.5 seconds.

[0055] In module S4, the dynamic priority scheduling algorithm also includes the following parameters: based on user preset preferences, the cooling strategy is divided into three modes: high efficiency priority, low energy consumption priority, and rapid cooling priority; in the high efficiency priority mode, the energy efficiency ratio of the cooling system is not less than 3.5; in the low energy consumption priority mode, the energy consumption of the cooling system is reduced by not less than 20%. In module S5, the cooling system drive circuit uses PWM voltage regulation technology to control the compressor speed. The frequency of the PWM signal is 20kHz, and the duty cycle adjustment range is 10%-90%; the response time of the drain passage controlled by the solenoid valve does not exceed 50ms to improve the accuracy of the solenoid valve.

[0056] An AI-based intelligent control storage medium for an ice maker includes the following program code: Program S1, a real-time control thread with priority set to the highest task level of the real-time operating system and a scheduling cycle of 1ms; it contains a fuzzy PID control instruction set for adjusting compressor speed and blade cutting frequency; Program S2, a data storage thread employing a circular buffer mechanism with a buffer size of 1MB and a data persistence period of 60 minutes, storing raw sensor data and control logs; Program S3, a remote upgrade interface supporting HTTPS protocol communication with OTA servers and a firmware differential upgrade algorithm; firmware verification uses the SHA-256 hash algorithm, automatically rolling back to the previous stable version in case of upgrade failure. In Program S2, the raw sensor data and control logs further include a hierarchical log storage strategy: operating status logs are stored for 30 days in CSV format; abnormal alarm logs are permanently stored, encrypted, and uploaded to the cloud; and a log retrieval function supports time range queries and keyword filtering.

[0057] The working principle of this invention is as follows: Based on the AI ​​analysis results, the system dynamically adjusts the refrigeration path and ice-making parameters. In the immediate ice-making mode, when the AI ​​determines "immediate ice-making," a two-stage compression refrigeration system is activated. The system includes a high-pressure compressor (discharge capacity 10 m³ / h) and a low-pressure compressor (discharge capacity 8 m³ / h), along with a high-pressure condenser (5 m²), a low-pressure condenser (4 m²), a high-pressure evaporator (3 m²), and a low-pressure evaporator (2 m²), using R410A as the refrigerant. The system lowers the water storage temperature from an initial temperature of 20°C to a target temperature of 4°C to meet the rapid ice-making requirement. In the delayed ice-making mode, when the AI ​​determines "delayed ice-making," the system activates an energy-saving mode to maintain the water storage temperature at 8°C, reducing energy consumption. In the cleaning priority mode, when water quality parameters (such as turbidity) reach a threshold, the system prioritizes the cleaning mode, activating the ultraviolet sterilization module and simultaneously starting the drain pump to replace the water, ensuring that the water quality in the storage tank meets the standards.

[0058] During the ice-making process, the system employs a fuzzy PID algorithm to optimize ice-making parameters, including ice thickness control: Ice thickness is monitored in real-time by an ice thickness sensor, dynamically adjusting blade speed and cutting frequency. In the fuzzy PID algorithm, the initial value of the proportional coefficient is 0.6 (maximum not exceeding 1.2), the initial value of the integral coefficient is 0.1 (maximum not exceeding 0.3), and the initial value of the derivative coefficient is 0.05 (maximum not exceeding 0.1), ensuring uniform ice thickness and a reasonable cutting frequency. The system also features ambient temperature adaptation: dynamically adjusting the ice-making cycle based on the ambient temperature. When the ambient temperature is above 25℃, the ice-making cycle is shortened to improve cooling efficiency; when the ambient temperature is below 15℃, the ice-making cycle is extended to reduce energy consumption.

[0059] Example 3; please refer to Figures 1-5 In this embodiment of the invention, a specific application of an ice maker is provided: multi-source data acquisition, an ice maker is deployed in the back kitchen of a restaurant, its sensor module (module S1) collects data at a frequency of 1kHz, the water tank temperature sensor (±0.2℃ accuracy) monitors the water temperature from the initial 25℃ to the target 4℃, the water level sensor trigger threshold is set to 100mm, and water is automatically replenished when the water level is below the threshold, the turbidity sensor detects the water quality in real time, and triggers the cleaning mode when the NTU value exceeds 50, the vibration sensor monitors the operation of the compressor, and a 0.5g amplitude warning threshold is set to prevent mechanical failure.

[0060] AI dynamic decision-making: The edge computing device (module S3) runs an LSTM prediction model (3 nodes in the input layer and 64 nodes in the hidden layer), outputting decision labels every 50ms. In the immediate ice-making mode, when demand surges during the dinner peak, the dual-stage compressor (10m³ / h high pressure + 8m³ / h low pressure exhaust volume) is activated, and the water temperature is reduced from 20℃ to 4℃ within 5 minutes. In the delayed ice-making mode, the water temperature is maintained at 8℃ during the low demand period at noon, the compressor speed is reduced by 40%, and energy consumption is reduced by 22%. In the cleaning priority mode, when the turbidity exceeds the standard, the ultraviolet sterilization module (wavelength 254nm) is activated and the drain pump (flow rate 3L / s) is started to complete the water change.

[0061] The system employs optimized control and a fuzzy PID algorithm (program S1) to dynamically adjust the blade speed (adjustable from 500 to 1200 rpm). When the ice thickness sensor detects a standard value of 8 mm, the proportional coefficient is adjusted to 0.8 and the integral coefficient to 0.15, achieving a cutting accuracy of ±0.3 mm. When the ambient temperature sensor detects 28°C, the ice-making cycle is shortened to 15 minutes per batch, resulting in a 35% increase in efficiency compared to the ambient temperature mode.

[0062] For abnormal handling and upgrades, when refrigerant leakage causes a temperature drop of less than 2°C in 5 minutes (step S5), the system automatically shuts down and pushes an alarm to the human-machine interface screen (module S6). The storage medium (program S3) completes the OTA upgrade via HTTPS protocol, uses SHA-256 verification to ensure firmware security, and rolls back to a stable version within 50ms if the upgrade fails.

[0063] The system modules work together and are dynamically prioritized (module S4). When the user selects the "high efficiency priority" mode, the two-stage condenser (5m² + 4m² area) works together, achieving an energy efficiency ratio of 3.8, which is 42% higher than that of a single-stage system. The PWM drive control (module S5) adjusts the compressor duty cycle (30%-85%) at a frequency of 20kHz, saving 18% energy compared to traditional relay control. The data persistence (program S2) uses a circular buffer to store 30 days of operating logs, and encrypted anomaly records are uploaded to the cloud, reducing the fault diagnosis response time to 2 minutes.

[0064] The working principle of this invention is as follows: the AI ​​prediction model reduces the number of refrigeration system start-ups and shutdowns by 62%, reducing annual electricity costs by approximately RMB 1,200 (calculated at RMB 0.8 / kWh); the vibration early warning mechanism reduces the compressor mechanical failure rate from 5% to 0.3%; the ultraviolet sterilization module, combined with real-time water exchange, increases the water quality compliance rate from 82% to 99.6%; and OTA remote upgrades reduce the frequency of on-site maintenance, reducing annual operation and maintenance costs by 45%.

[0065] Working Principle: The system uses a multi-source sensor module to collect key parameters in real time, such as water temperature, water level, turbidity, pH value, ambient temperature, and compressor vibration status, within the water storage tank. After preprocessing by the microcontroller using Kalman filtering and median filtering techniques, the data is input into the long short-term memory network model of the AI ​​analysis and decision-making module. This model learns the dynamic changes in water storage demand based on historical data and outputs water storage demand classification labels. Based on the AI ​​analysis results, the system dynamically adjusts the refrigeration path and ice-making parameters: In immediate ice-making mode, the two-stage compression refrigeration system is activated, using high-pressure and low-pressure compressors, condensers, evaporators, and R410A refrigerant to lower the water storage temperature from 20℃ to 4℃; in delayed ice-making mode, an energy-saving mode is activated to maintain the water storage temperature at 8℃; in cleaning-priority mode, the ultraviolet sterilization module is activated and the drain pump is started to replace the water. During the ice-making process, a fuzzy PID algorithm is used to optimize ice-making parameters. An ice thickness sensor monitors the ice thickness in real time, dynamically adjusting the blade speed and cutting frequency. Simultaneously, the ice-making cycle is dynamically adjusted based on ambient temperature: shortened above 25℃ and extended below 15℃, achieving efficient, energy-saving, and high-quality ice-making results. Furthermore, the system features abnormal condition warning and self-repair functions. A vibration sensor monitors the compressor's operating status, and if the water temperature is abnormal, a refrigerant leak is detected, and the system is shut down.

[0066] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent control method for an ice maker based on AI analysis, characterized in that, include: Step S1: Real-time collection of water storage status data. The water temperature data in the water storage tank is collected by a temperature sensor at a frequency of once per second; the water level in the water storage tank is monitored by a water level sensor, and the trigger threshold is set to a minimum water level of 100 mm; the water quality parameters are detected by a turbidity sensor, and the cleaning mode is triggered when the turbidity reaches 50 NTU. Step S2: AI dynamically analyzes water storage demand. The real-time collected water temperature, water level and water quality data are input into a prediction model based on a long short-term memory network. The model has 3 input layer nodes, 64 hidden layer nodes, and the output layer is the classification label of water storage demand. The classification labels include immediate ice making, delayed ice making and cleaning priority. Step S3: Dynamically adjust the cooling path and ice-making parameters. When the AI ​​determines that ice making is to be done immediately, start the dual-stage compression refrigeration system to reduce the water storage temperature from the initial temperature of 20 degrees Celsius to the target temperature of 4 degrees Celsius. When the AI ​​determines that ice making is to be done in a delayed manner, start the energy-saving mode to maintain the water storage temperature at 8 degrees Celsius. When the AI ​​determines that cleaning is the priority, activate the ultraviolet sterilization module and start the drain pump to change the water. Step S4: Optimize and control the ice-making process. Use a fuzzy PID algorithm to adjust the blade speed of the ice-making module and dynamically adjust the cutting frequency based on feedback data from the ice thickness sensor. Adjust the ice-making cycle according to the ambient temperature. Shorten the ice-making cycle when the ambient temperature is above 25 degrees Celsius and extend the ice-making cycle when the ambient temperature is below 15 degrees Celsius.

2. The intelligent control method for an ice maker based on AI analysis according to claim 1, characterized in that, It also includes step S5, abnormal state warning and self-repair, which monitors the compressor's operating status through a vibration sensor. When the vibration amplitude reaches 0.5g, an early warning is triggered. If the water temperature does not drop by 2 degrees Celsius within 5 minutes after the cooling starts, it is determined to be a refrigerant leak and a system shutdown command is triggered.

3. The intelligent control method for an ice maker based on AI analysis according to claim 1, characterized in that, In step S2, the training process of the Long Short-Term Memory network prediction model is as follows: Step S201: Collect water storage temperature, water level and water quality data at 15-minute intervals for at least the past year, as well as the corresponding water storage demand labels, as a training dataset. Step S202: Divide the training dataset into a training set, a validation set, and a test set, with proportions of 70%, 15%, and 15%, respectively. Step S203: The loss function adopted is the cross-entropy loss function, which is used to measure the difference between the classification label predicted by the model and the actual label; Step S204: During the training process, when the loss value on the validation set no longer decreases within 5 consecutive training cycles, training is stopped early to prevent overfitting.

4. The intelligent control method for an ice maker based on AI analysis according to claim 1, characterized in that, In step S2, the two-stage compression refrigeration system includes: There are two sets of compressors, namely a high-pressure compressor and a low-pressure compressor. The discharge capacity of the high-pressure compressor is 10 m³ / h, and the discharge capacity of the low-pressure compressor is 8 m³ / h. Two sets of condensers, a high-pressure condenser and a low-pressure condenser, with condensation areas of 5m² and 4m² respectively; Two sets of evaporators, a high-pressure evaporator and a low-pressure evaporator, with evaporation areas of 3m² and 2m² respectively; The refrigerant used in the two-stage compression refrigeration system is R410A. The charge amount is precisely calculated and adjusted according to the system design and actual operation to ensure the efficient operation of the refrigeration system.

5. The intelligent control method for an ice maker based on AI analysis according to claim 1, characterized in that, In step S4, the specific parameters of the fuzzy PID algorithm are set as follows: the initial value of the proportional coefficient is 0.6, which is dynamically adjusted according to the deviation of the ice thickness, with a maximum of 1.2; the initial value of the integral coefficient is 0.1, which is used to eliminate the steady-state error of the ice thickness, and is adjusted according to the cumulative amount of deviation, with a maximum of 0.3; the initial value of the derivative coefficient is 0.05, which is used to predict the changing trend of the ice thickness, and is adjusted according to the rate of change of the deviation, with a maximum of 0.

1.

6. An AI-based intelligent control system for an ice maker, used to implement the AI-based intelligent control method for an ice maker as described in any one of claims 1-5, characterized in that, The system includes the following modules: Module S1, a multi-source sensor module, includes a temperature sensor group, comprising a water tank temperature sensor and an ambient temperature sensor; it also includes a water quality monitoring module, integrating a turbidity sensor and a pH sensor. Module S2, the data acquisition and preprocessing module, uses a microcontroller for data acquisition with a sampling frequency of 1 kHz; data preprocessing includes Kalman filtering and median filtering. Module S3, the AI ​​analysis and decision-making module, is a long short-term memory network model deployed on an edge computing device with an inference latency of no more than 50 milliseconds; Module S4, dynamic priority scheduling algorithm, adjusts the cooling strategy according to user preset preferences; Module S5, control and execution module, refrigeration system drive circuit, uses PWM voltage regulation technology to control compressor speed; mechanical actuator, including stepper motor driven blade assembly and solenoid valve controlled drainage passage; Module S6 is a human-computer interaction module with a touchscreen display of real-time data and operation interface; it supports voice command recognition with a response time of no more than 0.5 seconds.

7. The AI-based intelligent control system for an ice maker according to claim 6, characterized in that, In module S4, the dynamic priority scheduling algorithm also includes the following parameters: according to the user's preset preferences, the cooling strategy is divided into three modes: high efficiency priority, low energy consumption priority, and fast cooling priority; in the high efficiency priority mode, the energy efficiency ratio of the cooling system is not less than 3.5; in the low energy consumption priority mode, the energy consumption of the cooling system is reduced by not less than 20%.

8. The intelligent control system for an ice maker based on AI analysis according to claim 6, characterized in that, In module S5, the refrigeration system drive circuit uses PWM voltage regulation technology to control the compressor speed. The frequency of the PWM signal is 20kHz, and the duty cycle adjustment range is 10%-90%. The response time of the drain passage controlled by the solenoid valve does not exceed 50ms to improve the accuracy of the solenoid valve.

9. A storage medium for intelligent control of an ice maker based on AI analysis, characterized in that, The storage medium is used to execute the AI-based intelligent control method for an ice maker according to any one of claims 1-5, and the storage medium includes the following program code: Program S1 is a real-time control thread with the highest priority set as the real-time operating system task level and a scheduling cycle of 1ms. It includes a fuzzy PID control instruction set for adjusting the compressor speed and blade cutting frequency. Program S2, the data storage thread, adopts a circular buffer mechanism with a buffer size of 1MB and a data persistence period of 60 minutes. The stored content includes raw sensor data and control logs. Program S3, remote upgrade interface, supports HTTPS protocol to communicate with OTA server, firmware differential upgrade algorithm; Firmware verification uses the SHA-256 hash algorithm, and automatically rolls back to the previous stable version when the upgrade fails.

10. The AI-based intelligent control storage medium for an ice maker according to claim 9, characterized in that, In program S2, the sensor raw data and control logs further include a log hierarchical storage strategy, with the operating status log being saved for 30 days in CSV format; abnormal alarm logs being permanently stored, encrypted, and uploaded to the cloud; and a log retrieval function supporting time range queries and keyword filtering.

Images