Intelligent ice maker control system and method based on temperature sensor

Abstract

The application discloses a kind of intelligent ice maker control system and method based on temperature sensor, belong to the technical field of ice maker, it includes S100, test phase: temperature sensor is set in and outside the ice maker, detect the internal temperature and ambient temperature of ice maker, according to the state switching action of ice maker, state switching label is set, temperature variation curve is established, the state of current ice maker is detected, according to current time, state switching label is added to temperature variation curve, S200, training model: neural network model is established, and neural network model is trained using temperature variation curve, S300, application phase: set the highest limit of internal temperature, when ice maker generates state switching action, temperature variation prediction curve is output using neural network model and the length of time of shutdown is calculated, according to the length of time of shutdown, pause refrigeration, the application has the effect that can keep the internal temperature of ice maker enough low and not let ice melt simultaneously can also save energy.

Description

Technical Field

[0001] This invention relates to the field of ice makers, and in particular to an intelligent ice maker control system and method based on a temperature sensor. Background Technology

[0002] Currently, ice makers are essentially intelligent "water-to-ice" machines, relying on a refrigeration cycle to produce ice. Through the coordinated work of components such as a compressor, condenser, and evaporator, water is cooled into ice, which is then automatically removed and collected. The entire ice-making process includes water supply and circulation, ice formation, ice removal, ice detachment, and automatic water replenishment, forming an ice-making cycle. First, water enters the storage tank and is pumped to a distribution head, where it is evenly sprayed onto the surface of the low-temperature evaporator, gradually freezing into ice at 0°C. Unfrozen water flows back to the storage tank for circulation, and the ice layer gradually thickens until the set thickness is reached. Once the ice layer is sufficiently thick, the system switches to hot gas defrosting mode, where high-temperature refrigerant vapor flows through the evaporator, slightly melting the surface of the ice. The melted water film lubricates the ice, allowing it to slide into the ice storage tank by gravity, while preventing wet ice from being discharged. When the water level drops, the inlet valve automatically opens to replenish water and maintain a stable water level. Ice makers typically have a temperature sensor installed inside. The temperature sensor detects the internal temperature of the ice maker and transmits it to the ice maker's temperature control system. The temperature control system then adjusts the start / stop and power of the refrigeration system based on the current internal temperature.

[0003] The existing technical solutions mentioned above have the following drawbacks: Since ice preservation also requires low temperatures, the internal temperature of the ice maker will remain low after ice is made. However, if the temperature is controlled by the refrigeration system, it will waste electricity. Now, there is a need for a method that can keep the internal temperature of the ice maker low enough to prevent the ice from melting while also saving energy. Summary of the Invention

[0004] In order to maintain a low enough internal temperature in the ice maker to prevent the ice from melting while also saving energy, this application provides an intelligent ice maker control system and method based on a temperature sensor.

[0005] On the one hand, the intelligent ice maker control method based on a temperature sensor provided in this application adopts the following technical solution: A method for controlling an intelligent ice maker based on a temperature sensor includes the following steps: S100, Testing Phase: Temperature sensors are installed both inside and outside the ice maker. The temperature sensors detect the internal temperature of the ice maker and the ambient temperature in real time and record the data according to the detection time. Status switching labels are set according to the status switching actions of the ice maker. A temperature change curve is established using time as the x-axis and internal and ambient temperatures; The system detects the current status of the ice maker. When a status change action occurs, it queries the corresponding status change tag based on the status change action. If a status change tag is found, the ice maker stops cooling and adds the status change tag to the temperature change curve based on the current time. S200, Training Model: Establish a neural network model, extract the line segment between two adjacent state switching labels in the temperature change curve as the test line segment, and associate the state switching label corresponding to the start of the test line segment with the test line segment. Use the test line segment associated with each state switching label to train the neural network model. The neural network model is used to calculate the temperature change prediction curve of the internal temperature after each state switching label. S300, Application Stage: Set the maximum internal temperature limit; When the ice maker performs a state switching action, it calls the corresponding state switching tag according to the state switching action. If the state switching tag is found, the queried state switching tag, the current internal temperature and the ambient temperature are imported into the neural network model. The neural network model outputs a temperature change prediction curve, determines the location of the highest internal temperature limit in the temperature change prediction curve and marks it as the start point, and calculates the time from the start of the temperature change prediction curve to the start point as the shutdown duration. The ice maker's cooling function is paused and a timer is started. Once the timer reaches the pause duration, the ice maker's cooling function is restarted.

[0006] By adopting the above solution, after the ice maker finishes making ice and every time the cabinet door is opened or closed, the system will start calculating how long it will take for the temperature to approach the melting temperature of the ice after the ice maker stops cooling, and will pause the cooling system. When the estimated temperature rises to the temperature that will melt the ice, the cooling will be restarted. This ensures that the internal temperature of the ice maker will not allow the ice to melt and also saves electricity.

[0007] Preferably, step "S300, Practical Application" further includes the following steps: Set the maximum pause time; The evaluation time is obtained by subtracting the calculated time from the longest stagnation time. If the assessment time is not negative, the ice maker's cooling will be paused and a timer will be started. The ice maker's cooling will be restarted when the timer reaches the shutdown duration.

[0008] By adopting the above solution, the ice maker can be prevented from being turned on and off in a short period of time.

[0009] Preferably, the step of "setting a state switching label according to the state switching action of the ice maker" includes the following steps: The status switching labels include ice making finished, door open, and door closed; The step "detect the current status of the ice maker" also includes the following steps: The system detects the opening and closing of the ice maker's door and the working status of the ice-making system. It determines whether the state switching action is the end of ice making by checking the working status of the ice-making system, and whether the state switching action is the opening and closing of the door by checking whether the door is open or closed.

[0010] By adopting the above solution, the current status of the ice maker can be determined by the status of the cabinet door and the ice-making system.

[0011] Preferably, the following steps are also included: When the ice maker stops cooling and then restarts cooling, it checks whether the current internal temperature is higher than the maximum internal temperature limit. If the current internal temperature is higher than the maximum internal temperature limit, the internal temperature and time since the ice maker last switched states are used to correct the neural network model.

[0012] By adopting the above scheme, if the refrigeration system of the ice maker restarts and finds that the current temperature is different from the prediction, the neural network model will be corrected.

[0013] Preferably, the following steps are also included: Set the comparison interval and temperature change limits; After each comparison interval, the temperature change value is obtained by subtracting the current ambient temperature from the ambient temperature before the comparison interval and taking the absolute value. If the temperature change exceeds the temperature change limit, control of the ice maker's refrigeration system will be suspended, and the temperature change value will be displayed.

[0014] If the ambient temperature changes significantly in a short period of time, the control of the refrigeration system using this system may be inaccurate. Therefore, the system control will be temporarily stopped until the ambient temperature stabilizes.

[0015] On the other hand, the intelligent ice maker control system based on a temperature sensor provided in this application adopts the following technical solution: A temperature sensor-based intelligent ice maker control system includes a temperature detection module, a status detection module, a data storage module, a curve generation module, a model training module, a duration calculation module, and a refrigeration control module. The temperature detection module includes temperature sensors installed inside and outside the ice maker. The temperature sensors detect the internal temperature and ambient temperature of the ice maker in real time. The temperature detection module records the internal temperature and ambient temperature according to the detection time and transmits them to the data storage module. The state detection module sets a state switching tag according to the state switching action of the ice maker, detects the current state of the ice maker, and when a state switching action occurs, it queries the corresponding state switching tag according to the state switching action and transmits the state switching tag to the curve generation module and the duration calculation module. The data storage module receives and stores data; The curve generation module calls the internal temperature and ambient temperature stored in the data storage module, and uses time as the x-axis to establish a temperature change curve using the internal temperature and ambient temperature. When a state switching tag is received, the tag is added to the temperature change curve according to the current time, and the temperature change curve is transmitted to the data storage module. The model training module establishes a neural network model, calls the temperature change curve stored in the data storage module, extracts the line segment between two adjacent state switching labels in the temperature change curve as a test line segment, and associates the state switching label corresponding to the start of the test line segment with the test line segment. The neural network model is trained using the test line segment associated with each state switching label. The neural network model is used to calculate the temperature change prediction curve of the internal temperature after each state switching label. The neural network model is then transmitted to the duration calculation module. The duration calculation module has a preset maximum internal temperature limit. When the duration calculation module receives a state switching tag, it calls the latest internal temperature and ambient temperature stored in the data storage module, imports the state switching tag, the current internal temperature and ambient temperature into the neural network model, the neural network model outputs a temperature change prediction curve, determines the location of the maximum internal temperature limit in the temperature change prediction curve and marks it as the start point, calculates the time from the start of the temperature change prediction curve to the start point as the shutdown duration, and transmits the shutdown duration to the refrigeration control module. The refrigeration control module receives the shutdown duration and then controls the refrigeration of the ice maker to pause and starts timing. When the shutdown duration is reached, the refrigeration of the ice maker is restarted.

[0016] By adopting the above solution, after the ice maker finishes making ice and every time the cabinet door is opened or closed, the system will start calculating how long it will take for the temperature to approach the melting temperature of the ice after the ice maker stops cooling, and will pause the cooling system. When the estimated temperature rises to the temperature that will melt the ice, the cooling will be restarted. This ensures that the internal temperature of the ice maker will not allow the ice to melt and also saves electricity.

[0017] Preferably, the refrigeration control module has a preset maximum pause time. After receiving the downtime, the refrigeration control module subtracts the calculated time from the maximum pause time to obtain the evaluation time. If the evaluation time is not negative, the refrigeration of the ice maker is paused and the timer is started. When the timer reaches the downtime, the refrigeration of the ice maker is started.

[0018] By adopting the above solution, the ice maker can be prevented from being turned on and off in a short period of time.

[0019] Preferably, the status switching labels include ice making finished, door open, and door closed. The status detection module detects the door opening and closing of the ice maker and the working status of the ice making system. It determines whether the status switching action is ice making finished by the working status of the ice making system, and determines whether the status switching action is door opening or door closing by the door opening and closing.

[0020] By adopting the above solution, the current status of the ice maker can be determined by the status of the cabinet door and the ice-making system.

[0021] Preferably, it also includes a fault detection module, which detects the status of the refrigeration control module. When the refrigeration control module ends a control cycle, it calls the current internal temperature stored in the data storage module to determine whether the current internal temperature is higher than the maximum internal temperature limit. If the current internal temperature is higher than the maximum internal temperature limit, the internal temperature and time since the last state switching action of the ice maker are used to correct the neural network model.

[0022] By adopting the above scheme, if the refrigeration system of the ice maker restarts and finds that the current temperature is different from the prediction, the neural network model will be corrected.

[0023] Preferably, it also includes an environmental assessment module, which has preset comparison interval time and temperature change limit. It calls the ambient temperature stored in the data storage module. After each comparison interval, it uses the absolute value of the difference between the current ambient temperature and the ambient temperature before the comparison interval to obtain the temperature change value. If the temperature change value is greater than the temperature change limit, it pauses the control of the ice maker refrigeration system and displays the temperature change value.

[0024] If the ambient temperature changes significantly in a short period of time, the control of the refrigeration system using this system may be inaccurate. Therefore, the system control will be temporarily stopped until the ambient temperature stabilizes.

[0025] In summary, the present invention has the following beneficial effects: 1. The system can automatically control the refrigeration system to stop and start, ensuring that the internal temperature of the ice maker does not melt the ice and saving electricity.

[0026] 2. The longest dwell time can prevent the ice maker from being turned on and off in a short period of time. Attached Figure Description

[0027] Figure 1 This is an overall system block diagram of Embodiment 2 of this application.

[0028] Explanation of reference numerals in the attached figures: 1. Temperature detection module; 2. Status detection module; 3. Data storage module; 4. Curve generation module; 5. Model training module; 6. Duration calculation module; 7. Cooling control module; 8. Fault detection module; 9. Environmental assessment module. Detailed Implementation

[0029] Example 1: This application discloses a smart ice maker control method based on a temperature sensor, the specific steps of which are as follows: S100, Testing Phase: Temperature sensors are installed both inside and outside the ice maker. The temperature sensors detect the internal temperature of the ice maker and the ambient temperature in real time and record the data according to the detection time. Status switching labels are set according to the status switching actions of the ice maker. The status switching labels include ice making finished, door open, and door closed.

[0030] A temperature change curve is established using time as the x-axis and internal and ambient temperatures.

[0031] The system monitors the opening and closing of the ice maker's door and the operating status of the ice-making system. The operating status of the ice-making system determines whether a status transition action indicates the end of ice making, and the opening and closing of the door determines whether the status transition action is door opening or door closing. When a status transition action occurs, the system queries the corresponding status transition tag. If a status transition tag is found, the ice maker stops cooling, and the status transition tag is added to the temperature change curve based on the current time. The current status of the ice maker can be determined by monitoring the door status and the ice-making system.

[0032] S200, Training Model: Establish a neural network model, extract the line segment between two adjacent state switching labels in the temperature change curve as the test line segment, and associate the state switching label corresponding to the start of the test line segment with the test line segment. Use the test line segment associated with each state switching label to train the neural network model. The neural network model is used to calculate the temperature change prediction curve of the internal temperature after each state switching label.

[0033] S300, Application Phase: Set the maximum internal temperature limit and the longest dwell time.

[0034] When the ice maker initiates a state switching action, it queries the corresponding state switching tag based on the state switching action. If a state switching tag is found, the queried state switching tag, the current internal temperature, and the ambient temperature are imported into the neural network model. The neural network model outputs a temperature change prediction curve, determines the location of the highest internal temperature limit in the temperature change prediction curve, marks it as the start point, and calculates the time from the start of the temperature change prediction curve to the start point as the shutdown duration.

[0035] The evaluation time is obtained by subtracting the calculated time from the longest stagnation time.

[0036] If the estimated time is not negative, the ice maker's cooling will be paused and a timer will be started. The ice maker will resume cooling once the estimated downtime has elapsed. This maximum pause time prevents the ice maker from being turned on and off in short intervals.

[0037] S400 Fault Detection: When the ice maker's cooling is paused and then restarted, determine whether the current internal temperature is higher than the maximum internal temperature limit.

[0038] If the current internal temperature is higher than the maximum internal temperature limit, the neural network model will be corrected using the internal temperature and time since the ice maker last switched states. If the ice maker's refrigeration system restarts and finds that the current temperature differs from the prediction, the neural network model will be corrected.

[0039] S500, Ambient Temperature Assessment: Set the comparison interval and temperature change limits.

[0040] At each comparison interval, the temperature change is obtained by subtracting the current ambient temperature from the ambient temperature before the comparison interval and taking the absolute value.

[0041] If the temperature change exceeds the temperature change limit, control of the ice maker's refrigeration system will be suspended, and the temperature change value will be displayed. If the ambient temperature changes significantly in a short period of time, the control of the refrigeration system using this system may be inaccurate; therefore, system control will be temporarily suspended until the ambient temperature stabilizes.

[0042] The implementation principle of the intelligent ice maker control method based on temperature sensor in this application embodiment is as follows: after the ice maker finishes making ice and each time the cabinet door is opened and closed, the system will start calculating how long it will take for the temperature to approach the melting temperature of the ice after the ice maker stops cooling, and will pause the operation of the cooling system. When the estimated temperature rises to the temperature that will melt the ice, the cooling will be restarted. This can ensure that the internal temperature of the ice maker will not allow the ice to melt and can also save electricity.

[0043] Example 2: This application discloses an intelligent ice maker control system based on a temperature sensor, such as... Figure 1 As shown, it includes a temperature detection module 1, a status detection module 2, a data storage module 3, a curve generation module 4, a model training module 5, a duration calculation module 6, a cooling control module 7, a fault detection module 8, and an environmental assessment module 9.

[0044] The temperature detection module 1 includes temperature sensors installed inside and outside the ice maker. The temperature sensors detect the internal temperature and ambient temperature of the ice maker in real time. The temperature detection module 1 records the internal temperature and ambient temperature according to the detection time and transmits them to the data storage module 3. The data storage module 3 receives and stores the data.

[0045] The status detection module 2 sets status switching tags based on the ice maker's status switching actions. These tags include "ice making finished," "door open," and "door closed." The module detects the ice maker's door opening / closing and the ice-making system's operating status. It determines whether the status switching action is "ice making finished" based on the ice-making system's operating status and whether it's "door open" or "door closed" based on the door's opening / closing status. When a status switching action occurs, the module queries the corresponding status switching tag and transmits it to the curve generation module 4 and the duration calculation module 6. The current status of the ice maker can be determined by the door status and the ice-making system's status.

[0046] The curve generation module 4 calls the internal temperature and ambient temperature stored in the data storage module 3, and uses time as the x-axis to establish a temperature change curve using the internal temperature and ambient temperature. When a state switching tag is received, the tag is added to the temperature change curve according to the current time, and the temperature change curve is transmitted to the data storage module 3.

[0047] Model training module 5 establishes a neural network model, calls the temperature change curve stored in data storage module 3, extracts the line segment between two adjacent state switching labels in the temperature change curve as a test line segment, and associates the state switching label corresponding to the start of the test line segment with the test line segment. The neural network model is trained using the test line segment associated with each state switching label. The neural network model is used to calculate the temperature change prediction curve of the internal temperature after each state switching label, and the neural network model is transmitted to duration calculation module 6.

[0048] The duration calculation module 6 has a preset maximum internal temperature limit. When the duration calculation module 6 receives a state switching tag, it calls the latest internal temperature and ambient temperature stored in the data storage module 3, imports the state switching tag, the current internal temperature and ambient temperature into the neural network model, the neural network model outputs a temperature change prediction curve, determines the location of the maximum internal temperature limit in the temperature change prediction curve and marks it as the start point, calculates the time from the start of the temperature change prediction curve to the start point as the shutdown duration, and transmits the shutdown duration to the refrigeration control module 7.

[0049] The refrigeration control module 7 has a preset maximum standby time. After receiving the downtime, the refrigeration control module 7 subtracts the calculated time from the maximum standby time to obtain the evaluation time. If the evaluation time is not negative, the refrigeration of the ice maker is paused and the timer is started. When the timer reaches the downtime, the refrigeration of the ice maker is started.

[0050] The fault detection module 8 monitors the status of the cooling control module 7. When the cooling control module 7 ends a control cycle, it retrieves the current internal temperature stored in the data storage module 3 and determines whether the current internal temperature is higher than the maximum internal temperature limit. If the current internal temperature is higher than the maximum internal temperature limit, the neural network model is corrected using the internal temperature and time since the last state switch of the ice maker. If the ice maker's cooling system restarts and finds that the current temperature differs from the prediction, the neural network model will be corrected.

[0051] The environmental assessment module 9 has preset comparison intervals and temperature change limits. It calls the ambient temperature stored in the data storage module 3. After each comparison interval, it subtracts the current ambient temperature from the ambient temperature before the comparison interval and takes the absolute value to obtain the temperature change value. If the temperature change value is greater than the temperature change limit, it pauses control of the ice maker's refrigeration system and displays the temperature change value. If the ambient temperature changes significantly in a short period of time, the control of the refrigeration system using this system may be inaccurate. Therefore, it will temporarily stop system control and wait for the ambient temperature to stabilize.

[0052] The embodiments described herein are preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape, and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A control method for an intelligent ice maker based on a temperature sensor, characterized in that, Includes the following steps: S100, Testing Phase: Temperature sensors are installed both inside and outside the ice maker. The temperature sensors detect the internal temperature of the ice maker and the ambient temperature in real time and record the data according to the detection time. Status switching labels are set according to the status switching actions of the ice maker. A temperature change curve is established using time as the x-axis and internal and ambient temperatures; The system detects the current status of the ice maker. When a status change action occurs, it queries the corresponding status change tag based on the status change action. If a status change tag is found, the ice maker stops cooling and adds the status change tag to the temperature change curve based on the current time. S200, Training Model: Establish a neural network model, extract the line segment between two adjacent state switching labels in the temperature change curve as the test line segment, and associate the state switching label corresponding to the start of the test line segment with the test line segment. Use the test line segment associated with each state switching label to train the neural network model. The neural network model is used to calculate the temperature change prediction curve of the internal temperature after each state switching label. S300, Application Stage: Set the maximum internal temperature limit; When the ice maker performs a state switching action, it calls the corresponding state switching tag according to the state switching action. If the state switching tag is found, the queried state switching tag, the current internal temperature and the ambient temperature are imported into the neural network model. The neural network model outputs a temperature change prediction curve, determines the location of the highest internal temperature limit in the temperature change prediction curve and marks it as the start point, and calculates the time from the start of the temperature change prediction curve to the start point as the shutdown duration. The ice maker's cooling function is paused and a timer is started. Once the timer reaches the pause duration, the ice maker's cooling function is restarted.

2. The intelligent ice maker control method based on a temperature sensor according to claim 1, characterized in that, The relevant step "S300, Practical Application" also includes the following steps: Set the maximum pause time; The evaluation time is obtained by subtracting the calculated time from the longest stagnation time. If the assessment time is not negative, the ice maker's cooling will be paused and a timer will be started. The ice maker's cooling will be restarted when the timer reaches the shutdown duration.

3. The intelligent ice maker control method based on a temperature sensor according to claim 1, characterized in that, The step following "setting state switching labels according to the state switching action of the ice maker" includes the following steps: The status switching labels include ice making finished, door open, and door closed; The step "detect the current status of the ice maker" also includes the following steps: The system detects the opening and closing of the ice maker's door and the working status of the ice-making system. It determines whether the state switching action is the end of ice making by checking the working status of the ice-making system, and whether the state switching action is the opening and closing of the door by checking whether the door is open or closed.

4. The intelligent ice maker control method based on a temperature sensor according to claim 1, characterized in that, It also includes the following steps: When the ice maker stops cooling and then restarts cooling, it checks whether the current internal temperature is higher than the maximum internal temperature limit. If the current internal temperature is higher than the maximum internal temperature limit, the internal temperature and time since the ice maker last switched states are used to correct the neural network model.

5. The intelligent ice maker control method based on a temperature sensor according to claim 1, characterized in that, It also includes the following steps: Set the comparison interval and temperature change limits; After each comparison interval, the temperature change value is obtained by subtracting the current ambient temperature from the ambient temperature before the comparison interval and taking the absolute value. If the temperature change exceeds the temperature change limit, control of the ice maker's refrigeration system will be suspended, and the temperature change value will be displayed.

6. A smart ice maker control system based on a temperature sensor, characterized in that: It includes a temperature detection module (1), a status detection module (2), a data storage module (3), a curve generation module (4), a model training module (5), a duration calculation module (6), and a cooling control module (7); The temperature detection module (1) includes a temperature sensor installed inside and outside the ice maker. The temperature sensor detects the internal temperature and ambient temperature of the ice maker in real time. The temperature detection module (1) records the internal temperature and ambient temperature according to the detection time and transmits them to the data storage module (3). The state detection module (2) sets a state switching tag according to the state switching action of the ice maker, detects the current state of the ice maker, and when a state switching action occurs, it queries the current corresponding state switching tag according to the state switching action and transmits the state switching tag to the curve generation module (4) and the duration calculation module (6). The data storage module (3) receives and stores data; The curve generation module (4) calls the internal temperature and ambient temperature stored in the data storage module (3), and uses time as the x-axis to establish a temperature change curve using the internal temperature and ambient temperature. When a state switching tag is received, the tag is added to the temperature change curve according to the current time, and the temperature change curve is transmitted to the data storage module (3). The model training module (5) establishes a neural network model, calls the temperature change curve stored in the data storage module (3), extracts the line segment between two adjacent state switching labels in the temperature change curve as a test line segment, and associates the state switching label corresponding to the start of the test line segment with the test line segment. The test line segment associated with each state switching label is used to train the neural network model. The neural network model is used to calculate the temperature change prediction curve of the internal temperature after each state switching label. The neural network model is transmitted to the duration calculation module (6). The duration calculation module (6) has a preset maximum internal temperature limit. When the duration calculation module (6) receives the state switching tag, it calls the latest internal temperature and ambient temperature stored in the data storage module (3), imports the state switching tag, the current internal temperature and ambient temperature into the neural network model, outputs the temperature change prediction curve, determines the location of the maximum internal temperature limit in the temperature change prediction curve and marks it as the start point, calculates the time from the start of the temperature change prediction curve to the start point as the shutdown duration, and transmits the shutdown duration to the refrigeration control module (7). The refrigeration control module (7) receives the shutdown duration and controls to pause the refrigeration of the ice maker and starts timing. When the shutdown duration is reached, the refrigeration of the ice maker is started.

7. The intelligent ice maker control system based on a temperature sensor according to claim 6, characterized in that: The refrigeration control module (7) has a preset maximum stagnation time. After receiving the downtime, the refrigeration control module (7) subtracts the calculated time from the maximum stagnation time to obtain the evaluation time. If the evaluation time is not negative, the refrigeration of the ice maker is paused and the timer is started. When the timer reaches the downtime, the refrigeration of the ice maker is started.

8. The intelligent ice maker control system based on a temperature sensor according to claim 6, characterized in that: The status switching labels include ice making end, door open, and door closed. The status detection module (2) detects the door opening and closing of the ice maker and the working status of the ice making system. It determines whether the status switching action is ice making end by checking the working status of the ice making system and whether the status switching action is door opening and door closing by checking the door opening and closing.

9. The intelligent ice maker control system based on a temperature sensor according to claim 6, characterized in that: It also includes a fault detection module (8), which detects the state of the refrigeration control module (7). When the refrigeration control module (7) ends a control cycle, it calls the current internal temperature stored in the data storage module (3) to determine whether the current internal temperature is higher than the maximum internal temperature limit. If the current internal temperature is higher than the maximum internal temperature limit, the internal temperature and time after the last state switching action of the ice maker are used to correct the neural network model.

10. A smart ice maker control system based on a temperature sensor according to claim 6, characterized in that: It also includes an environmental assessment module (9), which has preset comparison interval time and temperature change limit. It calls the ambient temperature stored in the data storage module (3). After each comparison interval, it uses the absolute value of the difference between the current ambient temperature and the ambient temperature before the comparison interval to obtain the temperature change value. If the temperature change value is greater than the temperature change limit, it pauses the control of the ice maker refrigeration system and displays the temperature change value.

Images