Refrigerator air door fault detection and adjustment method, device and equipment and medium

Abstract

The invention relates to a refrigerator air door fault detection and adjustment method and device, equipment and a medium, and the method comprises the steps: obtaining air door state data based on a polymorphic sensor, determining a fault type according to the air door state data based on a trained abnormal state algorithm model, and carrying out the fault detection and adjustment according to the fault type. If the fault type is a mechanical wear type, determining a wear prediction depth; and according to the wear prediction depth, the fault adjusting mechanism is controlled to carry out temporary adjusting operation, and first sound-light alarm operation is executed. According to the method, the air door state data is intelligently analyzed, the fault type is quickly and accurately recognized, the abrasion prediction depth is determined, automatic adjustment of the fault adjusting mechanism is achieved according to the prediction result, the fault is temporarily solved, meanwhile, an audible and visual alarm is triggered to remind a user, and therefore the timeliness and accuracy of fault detection and adjustment are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of refrigerator damper fault detection and adjustment, and in particular to a refrigerator damper fault detection and adjustment method, device, equipment and medium. Background Art

[0002] At present, the refrigerator damper refers to the device that controls the flow of cold air in the refrigerator. It needs to be opened and closed frequently according to the temperature in the refrigerator and the refrigeration demand. The long-term high-frequency rotation will cause certain mechanical wear. This mechanical wear failure is difficult to detect in the early stage. Usually, only when the refrigeration effect of the refrigerator is significantly reduced or other problems occur in the refrigerator, the user will realize that the refrigerator has a fault and the refrigeration effect is poor. Long-term operation can easily cause the food stored in the refrigerator to deteriorate. Summary of the invention

[0003] In order to solve the problem that traditional refrigerator damper fault detection and adjustment methods cannot timely predict and adjust mechanical wear resulting in poor refrigeration effect or even food spoilage, the present application provides a refrigerator damper fault detection and adjustment method, device, equipment and medium.

[0004] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A refrigerator damper fault detection and adjustment method is applied to a fault adjustment mechanism located at a hinge between the refrigerator damper and a refrigerator casing, and the refrigerator damper fault detection and adjustment method comprises: Based on the multi-state sensor, the damper status data is obtained, and the damper status data at least includes opening and closing status data, opening and closing frequency data, refrigeration chamber temperature data, fan noise level data and vibration intensity data; Based on the trained abnormal state algorithm model, the fault type is determined according to the damper state data, and the fault type at least includes a mechanical wear type, wherein the mechanical wear type is a damper fault caused by wear at a hinge between the refrigerator damper and the refrigerator casing; If the fault type is a mechanical wear type, determining a predicted wear depth; According to the predicted wear depth, the fault adjustment mechanism is controlled to perform a temporary adjustment operation and execute a first sound and light alarm operation.

[0005] By adopting the above technical solution and integrating advanced multi-state sensors, it is possible to obtain various state data of the damper in real time, such as the open and closed state, frequency, refrigerator compartment temperature, fan noise and vibration intensity. The collection of these data helps to monitor the working state of the refrigerator more accurately. Then, using the trained abnormal state algorithm model, these data can be intelligently analyzed to quickly and accurately identify the type of fault, especially for mechanical wear faults. The method further includes determining the wear prediction depth, and automatically adjusting the fault adjustment mechanism according to the prediction results to temporarily solve the fault, while triggering an audible and visual alarm to remind the user, thereby significantly improving the timeliness and accuracy of fault detection and adjustment, and effectively avoiding the risk of reduced refrigeration efficiency and food spoilage due to mechanical wear.

[0006] In a preferred example, the present application may be further configured as follows: the step of determining the fault type according to the damper state data based on the trained abnormal state algorithm model includes: Standardizing the damper state data to generate standard scale data that conforms to the trained abnormal state algorithm model; Extracting key features from each of the standard scale data, and determining a type threshold corresponding to the key features; Based on the trained abnormal state algorithm model, comparing the type threshold and the key feature to determine the corresponding abnormal comparison value; Combining the abnormal comparison values ​​into an abnormal set, and determining the probability of abnormal occurrence according to the abnormal set; Obtain historical abnormal event information, and determine the fault type based on the abnormal occurrence probability and the historical abnormal event information.

[0007] By adopting the above technical solution, the refrigerator damper fault type can be accurately determined by standardizing damper status data, extracting key features, comparing abnormal thresholds, combining abnormal sets, and combining historical abnormal event information, thereby improving the reliability and efficiency of fault detection.

[0008] In a preferred example, the present application may be further configured as follows: if the fault type is a mechanical wear type, the step of determining the predicted wear depth includes: In the abnormality set corresponding to the mechanical wear type, a key comparison value is selected between each of the abnormal comparison values; Inputting the key comparison value into a trained depth prediction model; The wear prediction depth is determined according to the result output by the depth prediction model.

[0009] By adopting the above technical solution, the technology selects key comparison values ​​from the abnormal set of mechanical wear types and inputs them into the deep prediction model, thereby achieving accurate prediction of the mechanical wear depth of the refrigerator damper, providing a basis for timely adjustment and maintenance.

[0010] In a preferred example, the present application may be further configured as follows: after the step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth and executing the first sound and light alarm operation, the method further includes: Determine a preset time period and a preset point in the preset time period; Reacquiring a plurality of damper status data according to the preset points within the preset time period; Substituting the multiple re-acquired damper status data into the trained abnormal state algorithm model to determine whether the fault type reappears, and if so, checking the defects of the trained abnormal state algorithm model; If not, the abnormal set corresponding to the predicted wear depth is recorded as the historical abnormal event information, and the key comparison value corresponding to the predicted wear depth is determined as the matching identifier of the historical abnormal event information.

[0011] By adopting the above technical solution, the technology re-acquires the damper status data within the preset time period and point, and substitutes it into the abnormal status algorithm model to determine whether the fault reoccurs. If it does, the model defects are checked, otherwise the relevant data is recorded as historical abnormal event information for continuous optimization and improvement of the model.

[0012] In a preferred example, the present application may be further configured as follows: the step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth includes: Acquire a mechanical adjustment type, where the mechanical adjustment type includes at least a single-slot fixed adjustment type and a variable diameter adjustment type; If the mechanical adjustment type is a single slot fixed adjustment type, determining a wear threshold; Determine whether the predicted wear depth is greater than the wear threshold, if not, perform a second sound and light alarm operation, if yes, determine the maximum adjustment parameter of the memory alloy expansion and contraction; If the mechanical adjustment type is a variable diameter adjustment type, determining the memory alloy expansion and contraction adjustment parameter according to the predicted wear depth; According to the maximum adjustment parameter of the memory alloy expansion and contraction or the adjustment parameter of the memory alloy expansion and contraction, the fault adjustment mechanism is controlled to perform a temporary adjustment operation.

[0013] By adopting the above technical solution, the technology obtains the mechanical adjustment type and controls the fault adjustment mechanism to perform corresponding temporary adjustment operations, such as single-slot fixed adjustment or hinged head telescopic adjustment, according to the predicted wear depth and the set threshold or parameter, so as to optimize the damper performance and extend the service life.

[0014] In a preferred example, the present application may be further configured as follows: the step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the maximum adjustment parameter of the memory alloy expansion and contraction or the memory alloy expansion and contraction adjustment parameter includes: Determining temperature control data according to the maximum adjustment parameter of the memory alloy expansion and contraction or the adjustment parameter of the memory alloy expansion and contraction; Determining the temperature control point of the memory alloy according to the temperature control data; The memory alloy is heated according to the temperature control point of the memory alloy to complete the temporary adjustment operation of the fault adjustment mechanism.

[0015] By adopting the above technical solution, the technology determines the expansion and contraction adjustment parameters of the memory alloy, calculates the temperature control data and temperature control points accordingly, and accurately heats the memory alloy, thereby realizing temporary adjustment operation of the fault adjustment mechanism to repair or alleviate the mechanical wear problem of the refrigerator damper.

[0016] The second object of the invention is achieved by the following technical solutions: A refrigerator damper fault detection and adjustment device comprises a fault adjustment mechanism located at a hinge between the refrigerator damper and a refrigerator casing, and the refrigerator damper fault detection and adjustment device further comprises: An acquisition module, used for acquiring damper status data based on a polymorphic sensor, wherein the damper status data at least includes opening and closing status data, opening and closing frequency data, refrigerating chamber temperature data, fan noise level data and vibration intensity data; a first determination module, configured to determine a fault type according to the damper state data based on a trained abnormal state algorithm model, wherein the fault type at least includes a mechanical wear type, wherein the mechanical wear type is a damper fault condition caused by wear at a hinge between the refrigerator damper and the refrigerator casing; A second determination module, configured to determine a predicted wear depth if the fault type is a mechanical wear type; An execution module is used to control the fault adjustment mechanism to perform a temporary adjustment operation and execute a first sound and light alarm operation according to the predicted wear depth.

[0017] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned refrigerator damper fault detection and adjustment method are implemented.

[0018] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned refrigerator damper fault detection and adjustment method are implemented.

[0019] In summary, the present application includes at least one of the following beneficial technical effects: 1. By integrating advanced multi-state sensors, it is possible to obtain multiple state data of the damper in real time, such as open and closed state, frequency, refrigerator compartment temperature, fan noise and vibration intensity. The collection of these data helps to monitor the working state of the refrigerator more accurately. Then, using the trained abnormal state algorithm model, these data can be intelligently analyzed to quickly and accurately identify the type of fault, especially for mechanical wear faults. The method further includes determining the wear prediction depth, and automatically adjusting the fault adjustment mechanism according to the prediction results to temporarily solve the fault, while triggering an audible and visual alarm to remind the user, thereby significantly improving the timeliness and accuracy of fault detection and adjustment, and effectively avoiding the risk of reduced refrigeration efficiency and food spoilage due to mechanical wear. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a refrigerator damper fault detection and adjustment method in one embodiment of the present application.

[0021] Figure 2 is a flowchart for implementing step S20 in a refrigerator damper fault detection and adjustment method in one embodiment of the present application; Figure 3 is a flowchart for implementing step S30 in a refrigerator damper fault detection and adjustment method in one embodiment of the present application; Figure 4 is another implementation flow chart of a refrigerator damper fault detection and adjustment method in one embodiment of the present application; Figure 5 is a flowchart for implementing step S40 in a refrigerator damper fault detection and adjustment method in one embodiment of the present application; Figure 6 It is a flowchart for implementing step S405 in a refrigerator damper fault detection and adjustment method in one embodiment of the present application; Figure 7 It is a partial structural diagram of a fault adjustment mechanism in one embodiment of the present application; Figure 8It is a partial structural diagram of a fault adjustment mechanism in another embodiment of the present application; Fig. 9 This is a principle block diagram of a refrigerator damper fault detection and adjustment device in one embodiment of the present application; Fig.10 It is a schematic diagram of a device in an embodiment of the present application.

[0022] Description of reference numerals: 1. Refrigerator casing; 2. Refrigerator damper; 3. Fault adjustment mechanism; 311. Limiting groove; 312. Limiting joint; 313. First memory alloy elastic member; 321. Reducer joint; 322. Second memory alloy elastic member; 323. Elastic component; 324. Slider. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses a refrigerator damper fault detection and adjustment method, which specifically includes the following steps: A refrigerator damper fault detection and adjustment method is applied to a fault adjustment mechanism located at a hinge between the refrigerator damper and a refrigerator casing. The refrigerator damper fault detection and adjustment method comprises: S10, based on the multi-state sensor, obtaining the damper status data, the damper status data at least including the opening and closing status data, the opening and closing frequency data, the refrigerating chamber temperature data, the fan noise level data and the vibration intensity data; In this embodiment, the polymorphic sensor is a sensor that can detect and respond to a variety of different physical quantities. It can collect multiple types of data at the same time, providing the system with more comprehensive monitoring capabilities. The damper status data refers to a series of data about the working status of the refrigerator damper collected by the sensor, which is crucial for evaluating the performance of the damper and diagnosing potential problems. The open and closed status data records the switch status of the damper, that is, whether the damper is in the open or closed position. The open and close frequency data records the number of times the damper is opened and closed within a certain period of time, reflecting the frequency of use of the damper. The refrigerator temperature data provides temperature information inside the refrigerator and is a key indicator for evaluating the refrigeration effect of the refrigerator. The fan noise level data measures the noise level generated by the refrigerator fan during operation, which can reflect whether the working status of the fan is normal. The vibration intensity data measures the vibration amplitude generated by the damper during operation. Excessive vibration may indicate wear or failure of mechanical components. For example, a polymorphic sensor may detect the open and closed state and vibration intensity of the damper at the same time. If the sensor detects that the damper is frequently opened and closed (high opening and closing frequency data) and is accompanied by abnormal vibration (high vibration intensity data), this may indicate that the hinge of the damper is worn or damaged. As a key component of the smart refrigerator system, the polymorphic sensor can fully capture the real-time status of the damper, including its opening and closing status, frequency, temperature of the refrigerator compartment, noise level of the fan, and vibration intensity. These data together constitute the damper status data, which provides an important basis for refrigerator fault detection and preventive maintenance. With this data, the system can promptly detect and warn of potential mechanical wear or other faults, thereby ensuring the continuous and stable operation of the refrigerator.

[0025] S20, based on the trained abnormal state algorithm model, determine the fault type according to the damper state data, the fault type at least including the mechanical wear type, wherein the mechanical wear type is the damper fault caused by the wear of the hinge between the refrigerator damper and the refrigerator casing; In this embodiment, the abnormal state algorithm model is an intelligent analysis tool that can identify abnormal patterns that are significantly different from the normal state by learning the data patterns under normal working conditions, thereby helping to diagnose system faults. The fault type refers to the different fault categories that may exist in the refrigerator damper after analyzing the damper state data according to the abnormal state algorithm model. The mechanical wear type is one of the fault types, which specifically refers to the situation where the components are gradually worn out and the function is degraded due to the continuous use and friction of the hinge between the refrigerator damper and the refrigerator casing. For example, if the abnormal state algorithm model detects that the vibration intensity data of the damper is abnormally high, and the opening and closing frequency data shows that the number of damper switches is abnormally frequent, this may indicate that the hinge of the damper is experiencing mechanical wear. The abnormal state algorithm model can accurately identify the fault type of the refrigerator damper by analyzing the damper state data, among which the mechanical wear type is a type of special concern, which involves the wear and tear of the hinge between the damper and the casing due to long-term use. When the model detects signals that are inconsistent with normal working conditions, such as abnormal vibration intensity or frequent switching actions, it can predict and warn the user of possible mechanical wear problems on the damper, so that appropriate maintenance or repair measures can be taken to avoid further failures.

[0026] Preferably, the training of the abnormal state algorithm model usually requires data under normal state to build the model, and then use this model to identify abnormal data inconsistent with the normal state. The data required for the training process mainly include: data under normal state: these data are used to build the algorithm model, which can be historical data or data collected from a normally operating system. For example, if it is an abnormality detection of a refrigerator damper, the data under normal state may include the normal opening and closing state of the damper, frequency, refrigerator temperature, fan noise level and vibration intensity, etc.; labeled data: although unsupervised learning may not require labeled data, in some cases, using some labeled normal and abnormal data to train the model can improve the accuracy of detection. These data can help the algorithm better understand the difference between normal and abnormal. Diversified data: In order to make the model more robust, the training data should contain a variety of normal state conditions to cover all possible normal operating modes. Time series data: If the state of the system changes over time, then time series data can be used to train the model so that it can identify abnormal changes in state over time. During the training process, algorithms that may be used include autoencoders, deep support vector data descriptions (Deep SVDD), long short-term memory networks (LSTM), etc. These algorithms can be either unsupervised or supervised, depending on the availability of data and the requirements of the problem. For example, autoencoders can be used for unsupervised learning to identify anomalies by reconstructing errors, while supervised algorithms learn to distinguish between normal and abnormal data points by training the model to identify them. In practical applications, some techniques may also be combined, such as adjusting the sliding window size, choosing the appropriate label position, setting the threshold, etc. to optimize the detection effect of the model.

[0027] S30, if the fault type is a mechanical wear type, determining a predicted wear depth; In this embodiment, the wear prediction depth refers to the distance or depth at which the wear level of a mechanical device reaches a critical point that may affect normal function or cause a failure, predicted by analyzing and evaluating the wear of the mechanical device. For example, in the fault detection of a refrigerator damper, if the sensor detects abnormal vibration intensity and noise level of the damper, this may indicate wear at the damper hinge. The wear prediction depth will analyze this data to predict the amount of wear at the damper hinge, such as predicting that the damper may need to be replaced when the wear depth reaches 2 mm. When the fault detection of the refrigerator damper determines that the fault type is a mechanical wear type, the wear prediction depth will predict the degree of wear at the damper hinge based on the current wear data, such as vibration and noise levels. This prediction provides a quantified wear value, such as predicting that the wear depth reaches 2 mm, which helps technicians assess whether immediate repairs or replacement of parts are needed to prevent damper failures from causing a decrease in refrigerator refrigeration effect.

[0028] S40, controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth, and executing a first sound and light alarm operation.

[0029] In this embodiment, the temporary adjustment operation refers to a short-term measure taken to restore or maintain the normal operation of the equipment when it is confirmed that the mechanical equipment has a wear problem but has not yet reached the level of replacement or overhaul. The first sound and light alarm operation refers to immediately reminding the operator or maintenance personnel of the potential problem through sound and / or visual signals when the equipment is abnormal or faulty. For example, in the refrigerator damper fault detection system, if the wear prediction depth shows that the wear at the hinge has not exceeded the safety threshold, the control system may automatically adjust the opening and closing force or angle of the damper to reduce wear and maintain the normal operation of the damper. At the same time, the system will trigger an sound and light alarm, such as an alarm sound and a flashing warning light, to notify the maintenance personnel to conduct inspections and necessary maintenance. In the refrigerator damper fault detection system, once the presence of mechanical wear is determined by sensors and algorithm models, the system will automatically perform temporary adjustment operations, such as fine-tuning the opening and closing force or angle of the damper to alleviate wear and maintain the normal function of the damper. At the same time, to ensure that the problem is handled in a timely manner, the system will perform the first sound and light alarm operation, alerting maintenance personnel to the situation through alarm sounds and warning lights so that they can respond quickly and take further inspection and maintenance measures to prevent further development of the fault.

[0030] In summary, by integrating advanced multi-state sensors, it is possible to obtain multiple state data of the damper in real time, such as open and closed state, frequency, refrigerator compartment temperature, fan noise and vibration intensity. The collection of these data helps to monitor the working state of the refrigerator more accurately. Then, using the trained abnormal state algorithm model, these data can be intelligently analyzed to quickly and accurately identify the type of fault, especially for mechanical wear faults. The method further includes determining the wear prediction depth, and automatically adjusting the fault adjustment mechanism according to the prediction results to temporarily solve the fault, while triggering an audible and visual alarm to remind the user, thereby significantly improving the timeliness and accuracy of fault detection and adjustment, and effectively avoiding the risk of reduced refrigeration efficiency and food spoilage due to mechanical wear.

[0031] In one embodiment, if Figure 2 As shown, in step S20, that is, the step of determining the fault type according to the damper state data based on the trained abnormal state algorithm model, includes: S201, standardizing the damper state data to generate standard scale data that conforms to the trained abnormal state algorithm model; In this embodiment, standard scale data refers to adjusting the original data to a scale with specific statistical properties through mathematical transformation, usually to have zero mean and unit variance, so as to eliminate the dimensional influence between different variables and accelerate the convergence speed of the algorithm. For example, in the standardization process of refrigerator damper status data, the opening and closing frequency data, the refrigeration room temperature data, etc. may be standardized so that the distribution mean of these data is close to 0 and the standard deviation is close to 1. Before the damper status data is input into the abnormal state algorithm model, it is necessary to perform standardization to generate standard scale data. This step ensures that data from different sources and different dimensions can be compared and analyzed on the same scale, such as adjusting the vibration intensity and noise level of the damper to a distribution with a mean of 0 and a standard deviation of 1. Doing so not only helps to improve the training efficiency and prediction accuracy of the model, but also avoids the model performance deviation caused by inconsistent data scales. Through this standardization process, the algorithm model can more accurately learn and identify the normal and abnormal states of the damper, thereby more effectively performing fault detection and prediction.

[0032] S202, extracting key features from each standard scale data, and determining type thresholds corresponding to the key features; In this embodiment, the key feature refers to a data attribute that can significantly affect the model prediction results or play a decisive role in identifying problems in data analysis. The type threshold refers to a numerical standard used to distinguish different categories or states. When the feature value reaches or exceeds this threshold, it can be considered that the system has entered a specific state or category. For example, in the refrigerator damper status data, the standard scale data of vibration intensity may have a key feature, such as "peak vibration frequency". If this frequency exceeds the set type threshold, such as 1.5 times the standard deviation, it may indicate that the damper has abnormal vibration. In the data analysis process of refrigerator damper fault detection, it is first necessary to extract key features from various standard scale data, such as "peak vibration frequency" in vibration intensity data. These key features are crucial to identifying whether the damper is working properly. Subsequently, it is necessary to determine the type threshold of these key features, such as setting the type threshold of "peak vibration frequency" to 1.5 times the standard deviation. When the actual measured vibration frequency exceeds this threshold, the system will identify possible abnormalities and trigger corresponding alarms or adjustment measures. This method helps to diagnose problems quickly and accurately, thereby improving the maintenance efficiency and reliability of refrigerator dampers.

[0033] S203, based on the trained abnormal state algorithm model, comparing the type threshold and the key features to determine the corresponding abnormal comparison value; In this embodiment, the abnormal comparison value refers to the difference or ratio obtained by comparing the actual measured value of the key feature with the preset type threshold value, which is used to quantify the degree of abnormality. For example, in the state monitoring of the refrigerator damper, if the key feature is the vibration frequency of the damper, and the type threshold is set to the upper limit of the normal vibration frequency, then the abnormal comparison value can be the specific value of the actual vibration frequency exceeding this upper limit, such as the actual vibration frequency is 5Hz higher than the threshold. When using the trained abnormal state algorithm model for fault detection, we will extract the key features in the damper state data, such as the vibration frequency, and compare it with the preset type threshold. The abnormal comparison value is the result of this comparison. It can be a specific value or ratio that exceeds the threshold, which helps us quantify the degree of abnormality. For example, if the normal vibration frequency threshold of the damper is set to 50Hz, and the actual measured vibration frequency is 55Hz, then the abnormal comparison value is 5Hz. This value indicates that the vibration frequency of the damper exceeds the normal range, which may indicate a certain abnormal state and requires further inspection or maintenance. In this way, the abnormal state algorithm model can effectively identify and warn potential mechanical problems, thereby improving the operating reliability and efficiency of the refrigerator.

[0034] S204, combining the various abnormal comparison values ​​into an abnormal set, and determining the probability of abnormal occurrence according to the abnormal set; In this embodiment, the abnormal set refers to the abnormal comparison values ​​of different key features gathered together to form a set for comprehensive evaluation of the abnormal state of the system. The probability of abnormal occurrence refers to the possibility or frequency of abnormal state occurrence obtained by statistical or model analysis based on the data in the abnormal set. For example, if the abnormal comparison values ​​of the refrigerator damper include vibration frequency exceeding the threshold of 5Hz and noise level exceeding the threshold of 3dB, these abnormal comparison values ​​are combined into an abnormal set. Then, by analyzing historical data and the current abnormal set, the abnormal probability of damper failure is predicted to be 10%. In the fault detection system of the refrigerator damper, by monitoring key features such as vibration frequency and noise level, we can obtain respective abnormal comparison values. Combining these abnormal comparison values, an abnormal set is formed, which reflects the overall abnormal degree of the damper state. Using this abnormal set, combined with the trained abnormal state algorithm model, we can calculate the probability of abnormal occurrence. For example, if the model analysis shows that the current abnormal set has similarities with historical fault data, it may predict a 10% probability of abnormal occurrence. This probability value provides us with a quantitative risk assessment to help us decide whether preventive maintenance measures are needed to avoid potential failures and related risks.

[0035] S205: Obtain historical abnormal event information, and determine the fault type according to the abnormality occurrence probability and the historical abnormal event information.

[0036] In this embodiment, historical abnormal event information refers to detailed data and reports about abnormal conditions of the system or equipment recorded in the past, including the characteristics of the abnormality, the time of occurrence, and the processing results. For example, the historical abnormal event information may record the event that the vibration frequency of a certain model of refrigerator damper increased abnormally due to wear at the hinge last year, as well as the processing process and results of the event. By analyzing the historical abnormal event information and combining it with the currently monitored abnormal occurrence probability, we can more accurately determine the type of fault. For example, if the current monitoring shows that the vibration frequency of the damper has a high abnormal contrast value, and the historical data shows that the damper hinge wear fault has occurred under similar circumstances, then we can infer that the fault type pointed to by the current abnormal occurrence probability may be mechanical wear. This method of comprehensively considering historical data and real-time monitoring results can improve the accuracy of fault prediction and the pertinence of maintenance work, thereby improving the reliability and maintenance efficiency of the entire system.

[0037] In summary, by standardizing the damper status data, extracting key features, comparing abnormal thresholds, combining abnormal sets, and combining historical abnormal event information, the refrigerator damper fault type can be accurately determined, and the reliability and efficiency of fault detection can be improved.

[0038] In one embodiment, if Figure 3 As shown, in step S30, that is, if the fault type is a mechanical wear type, the step of determining the predicted wear depth includes: S301, in an abnormality set corresponding to a mechanical wear type, selecting a key comparison value between various abnormal comparison values; In this embodiment, the key comparison value refers to the abnormal comparison value that best represents or most sensitively reflects the wear state in the abnormal set of mechanical wear types, and it has the most significant indicative effect on the fault type. For example, in the abnormal set of mechanical wear types, if the abnormal comparison value of vibration frequency is most relevant to historical wear events, the comparison value of vibration frequency can be considered as a key comparison value. When analyzing the abnormal set of mechanical wear types, we will identify the most critical indicators from each abnormal comparison value. For example, if the abnormal comparison value of the vibration frequency of the damper shows the highest predictive accuracy in past wear events, then this comparison value will be selected as the key comparison value. By paying attention to this key comparison value, we can monitor the wear state of the damper more accurately and identify potential fault risks in a timely manner. This method can not only improve the efficiency of fault detection, but also help the maintenance team focus resources and attention on the features that are most likely to indicate problems, thereby more effectively planning maintenance and replacement work.

[0039] Preferably, there is no unified standard process for determining which abnormal comparison values ​​are key comparison values, because different application scenarios and data sets may require different methods and strategies. However, the following steps can usually be followed to identify key comparison values: Exploratory analysis of the data through data description and graphical methods (such as box plots, scatter plots) to identify possible outliers. For example, a box plot can be used to identify values ​​that exceed the quartile limits. For example, if the historical data of the vibration frequency shows that when its abnormal comparison value exceeds three times the standard deviation of the normal range, the probability of damper failure increases significantly, then this value can be used as a key comparison value and the corresponding threshold can be set. In this way, a set of processes suitable for specific application scenarios can be gradually established to determine the key comparison value.

[0040] S302, inputting the key comparison value into the trained depth prediction model; In this embodiment, the trained deep prediction model refers to a deep learning network that has been learned and optimized through a large amount of data and can make accurate predictions on new input data. For example, a deep prediction model may be trained to predict the remaining service life of the damper or the time of failure based on key comparison values ​​such as the vibration frequency and noise level of the refrigerator damper. In the fault detection system of the refrigerator damper, once the key comparison values ​​are extracted from the abnormal set, these values ​​will be provided as input data to the trained deep prediction model. This model uses its deep neural network structure to analyze the complex relationship between the key comparison values ​​and the historical fault data to predict the health status and potential failure risk of the damper. For example, if the model receives an input with a vibration frequency outside the normal range, it may predict the probability of the damper failing in the future, and issue corresponding maintenance recommendations or alarms accordingly. This method can significantly improve the accuracy and timeliness of fault prediction, help the maintenance team plan maintenance work more effectively, and reduce unexpected downtime.

[0041] S303: Determine the predicted wear depth according to the output result of the depth prediction model.

[0042] In this embodiment, the deep prediction model uses its deep learning algorithm to output prediction results about the wear status of the damper by analyzing the key comparative values ​​of the input, such as the vibration frequency and noise level of the damper. These results include information such as the possible degree of wear and the predicted remaining service life. Based on the output of the model, we can determine the predicted wear depth, that is, the predicted amount of wear at the damper hinge or the probability of wear reaching a certain depth, thereby providing a decision basis for whether repair or replacement is needed. For example, if the model predicts that the wear depth at the damper hinge is about to reach a critical value, this will trigger timely maintenance measures to avoid potential failures and related operational risks.

[0043] In summary, this technology achieves accurate prediction of the mechanical wear depth of refrigerator dampers by selecting key comparison values ​​from the abnormal set of mechanical wear types and inputting them into the deep prediction model, providing a basis for timely adjustment and maintenance.

[0044] In one embodiment, if Figure 4 As shown, after step S40, that is, after the step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth and executing the first sound and light alarm operation, the method includes: S50, determining a preset time period and a preset point in the preset time period; In this embodiment, the preset time period refers to a time range set for a specific purpose when performing data analysis or prediction, which can be a past, present or future time period. The preset point refers to a key time point or threshold point set according to a certain standard or rule within the preset time period, which is used to evaluate, monitor or trigger a specific operation. For example, in the maintenance system of the refrigerator damper, the preset time period can be the next quarter, and the preset point can be the first working day of each month in the quarter, and these dates are used to check and record the status of the damper. In the fault prediction and management process of the refrigerator damper, we first determine a preset time period, such as the next quarter, to evaluate the operating status of the damper and predict potential maintenance needs. Within this time period, we will also set a series of preset points, such as specific dates of each month, as key time nodes for checking the performance of the damper. By collecting and analyzing data at these preset points, we can more accurately monitor the state changes of the damper, identify any abnormal signs in a timely manner, and take preventive maintenance measures when necessary to ensure the efficient operation of the damper and the entire refrigeration system.

[0045] S60, acquiring multiple damper status data again according to preset points within a preset time period; In this embodiment, the preset time period refers to a time range set for a specific purpose when performing data analysis or prediction, which can be a past, present or future time period. The preset point refers to a key time point or threshold point set according to a certain standard or rule within the preset time period, which is used to evaluate, monitor or trigger a specific operation. For example, in the maintenance system of the refrigerator damper, the preset time period can be the next quarter, and the preset point can be the first working day of each month in the quarter, and these dates are used to check and record the status of the damper. In the fault prediction and management process of the refrigerator damper, we first determine a preset time period, such as the next quarter, to evaluate the operating status of the damper and predict potential maintenance needs. Within this time period, we will also set a series of preset points, such as specific dates of each month, as key time nodes for checking the performance of the damper. By collecting and analyzing data at these preset points, we can more accurately monitor the state changes of the damper, identify any abnormal signs in a timely manner, and take preventive maintenance measures when necessary to ensure the efficient operation of the damper and the entire refrigeration system.

[0046] S70, substituting the plurality of re-acquired damper status data into the trained abnormal state algorithm model to determine whether the fault type reappears, and if so, checking the defects of the trained abnormal state algorithm model; In this embodiment, the latest collected damper status data is input into the trained abnormal state algorithm model, which can monitor and evaluate the current state of the damper in real time. If the model recognizes the fault type again, this may indicate that there is a persistent or new abnormality in the damper. In this case, it is crucial to verify the accuracy and effectiveness of the model. Verifying the model may involve analyzing the defects of the model, such as whether misjudgment is caused by insufficient data, improper feature selection, or insufficient model generalization ability. Through this verification, the model can be further optimized to improve the accuracy and reliability of its predictions. By continuously monitoring and analyzing the status data of the refrigerator damper, we are able to use the well-trained abnormal state algorithm model to evaluate the health of the damper in real time. The model uses deep learning technology to identify and predict potential failure modes. When the model detects the fault type again, this triggers a feedback loop that prompts us to re-examine the performance of the model. We identify possible limitations or defects in the model by analyzing the difference between the model's prediction results and the actual situation. Then, we can adjust and retrain the model to improve its accuracy in predicting future faults. This self-optimization process not only enhances the robustness of the model, but also improves the technical effect of the entire fault detection system, ensuring the continuous and stable operation of the refrigerator damper.

[0047] Preferably, the following methods or indicators are usually used when checking model defects: Accuracy: It indicates the proportion of samples correctly predicted by the model to the total number of samples, which is applicable to classification problems. Precision and Recall: Precision is the proportion of samples predicted by the model to be positive that are actually positive, and Recall is the proportion of samples that are correctly predicted to be positive among all samples that are actually positive. F1 Score: The harmonic mean of precision and recall, which is used to comprehensively consider the performance of both. AUC-ROC curve and AUC value: The AUC-ROC curve represents the relationship between the true positive rate and false positive rate of the model under different thresholds. The AUC value evaluates the performance of the model under different thresholds. The closer the AUC value is, the better the model performance is.

[0048] S80: If not, record the anomaly set corresponding to the predicted wear depth as historical anomaly occurrence event information, and determine the key comparison value corresponding to the predicted wear depth as a matching identifier of the historical anomaly occurrence event information.

[0049] In this embodiment, the matching mark refers to a characteristic value used to identify and record a specific abnormal event or state, which serves as a reference point in historical data for comparison with future monitoring data. For example, in the maintenance record of the refrigerator damper, if a specific vibration frequency abnormal comparison value is closely related to the historical damper failure, this vibration frequency value can be recorded as a matching mark. In the fault detection system of the refrigerator damper, if the wear prediction depth determined by the deep prediction model does not exceed the preset threshold, it is considered that no fault has occurred at present. At this time, the system will record the abnormal set corresponding to the wear prediction depth as part of the historical abnormal event information. At the same time, the system will determine one or more key comparison values, such as the abnormal comparison value of the vibration frequency, as the matching mark of this historical event. These matching marks will be used as a reference in the future monitoring process to help the system quickly identify and compare the similarities between new monitoring data and historical abnormal events, thereby improving the response speed and accuracy of fault detection.

[0050] In summary, this technology reacquires the damper status data within the preset time period and points, and substitutes it into the abnormal status algorithm model to determine whether the fault reoccurs. If it does, the model defects are checked, otherwise the relevant data is recorded as historical abnormal event information for continuous optimization and improvement of the model.

[0051] In one embodiment, if Figure 7As shown, in step S40, that is, in the step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth, specifically, the fault adjustment mechanism 3 is located at the hinge of the refrigerator casing 1 and the refrigerator damper 2, and includes a limiting groove 311 located on the refrigerator casing 1, a limiting joint 312 located on the refrigerator damper 2, and a first memory alloy elastic member 313 located on the inner side of the refrigerator damper, one end of the first memory alloy elastic member 313 is connected to the refrigerator damper 2, and the other end is connected to the limiting joint 312, the first memory alloy elastic member 313 expands and contracts due to temperature changes, thereby driving the limiting joint 312 to movably plug and cooperate with the limiting groove 311, and making the limiting joint 312 rotatably set in the limiting groove 311, thereby temporarily supporting the hinge of the refrigerator casing 1 and the refrigerator damper 2 to prevent the damper failure from causing the refrigeration effect to deteriorate.

[0052] In another embodiment, if Figure 8 As shown, the fault adjustment mechanism 3 is located at the hinge of the refrigerator casing 1 and the refrigerator damper 2, and includes a reducer 321 located on the refrigerator damper, a second memory alloy elastic member 322 located on the inner side of the refrigerator damper, and an elastic component 323 with one end connected to the inner side of the reducer 321, and a slider 324 connected to the other end of the elastic component 323 and slidably matched with the reducer. One end of the second memory alloy elastic member 323 is connected to the refrigerator damper 2, and the other end is connected to the reducer 321. The second memory alloy elastic member 323 expands and contracts due to temperature changes, thereby driving the reducer 321 to expand and contract. The elastic component 324 located on the inner side of the reducer 321 and in compression deformation will slide out against the slider, thereby temporarily supporting the hinge of the refrigerator casing 1 and the refrigerator damper 2, thereby preventing the damper from failing and causing the refrigeration effect to deteriorate.

[0053] In the above embodiments, the technical effect is reflected in that the innovative design of the fault adjustment mechanism effectively solves the problem of failure of the refrigerator damper caused by mechanical wear and ensures the stability of the refrigerator refrigeration effect. Specifically, the fault adjustment mechanism is arranged at the hinge of the refrigerator casing and the damper, and the temperature-sensitive characteristics of the memory alloy elastic member are used to realize automatic adjustment of the opening and closing state of the damper. Under temperature changes, the memory alloy elastic member will expand and contract, driving the limit joint or the reducer to move accordingly, and through cooperation with the limit groove or the slider, temporary support for the hinge is realized. This design can respond quickly and make adjustments when the damper fails, preventing the abnormal opening and closing of the damper from affecting the refrigeration effect, and also provides a time window for maintenance. In addition, the design of the fault adjustment mechanism cleverly utilizes the interaction between material properties and mechanical structure, does not require complex electronic control, and has the advantages of simple structure, fast response, low cost and high reliability.

[0054] like Figure 5 As shown, the step S40 further includes: S401, obtaining a mechanical adjustment type, where the mechanical adjustment type at least includes a single-slot fixed adjustment type and a variable diameter adjustment type; In this embodiment, the single-slot fixed adjustment type refers to the use of a mechanical structure with a single limit slot for adjustment, and the fixed adjustment is achieved by changing the position of the limit joint in the limit slot. The variable diameter adjustment type refers to adjusting the matching relationship between the mechanical component and other components by changing the diameter or size of the mechanical component, which usually involves a reducer and a corresponding elastic component to achieve adjustment. For example, in the single-slot fixed adjustment type, the limit joint of the refrigerator damper can slide in a limit slot, and the opening and closing angle of the damper can be changed by adjusting its position in the slot. In the variable diameter adjustment type, the reducer on the damper can be extended and retracted as needed to adapt to the matching requirements of different sizes, such as realizing the extension and retraction of the reducer by a memory alloy elastic part driven by temperature changes. In the field of mechanical adjustment, obtaining the mechanical adjustment type is a key step to achieve precise control. The single-slot fixed adjustment type adjusts the opening and closing angle of the refrigerator damper by sliding the limit joint in the limit slot, providing a simple and direct adjustment method. In contrast, the variable diameter adjustment type allows more complex adjustments through the cooperation of the reducer and the elastic component to adapt to different working conditions and environmental changes. Both types of adjustment provide flexibility and adaptability to the mechanical system, ensuring that the equipment can be precisely adjusted as needed to meet the requirements of different application scenarios.

[0055] S402, if the mechanical adjustment type is a single slot fixed adjustment type, determining a wear threshold; In this embodiment, the wear threshold refers to the maximum amount of wear allowed for the mechanical equipment under normal operating conditions. Exceeding this value may cause performance degradation or failure. For example, in the single-slot fixed adjustment type of the refrigerator damper, the wear threshold can be set to 10% of the limit groove depth, that is, when the wear depth exceeds 10% of the limit groove depth, repair or replacement is required. During the maintenance of the refrigerator damper, if the mechanical adjustment type is a single-slot fixed adjustment type, the system will determine a wear threshold based on historical data and performance standards. This threshold is a key indicator for measuring the degree of wear at the damper hinge. For example, when the wear depth exceeds 10% of the limit groove depth, it indicates that the damper has approached or reached the critical point of performance degradation. At this time, the system will trigger a maintenance alarm, prompting necessary inspections and repairs. This method helps to detect potential problems in advance, avoid the reduction of refrigerator refrigeration effect or more serious failures due to excessive wear, and ensure the reliability of the equipment and extend its service life.

[0056] S403, judging whether the predicted wear depth is greater than the wear threshold, if not, executing the second sound and light alarm operation, if yes, determining the maximum adjustment parameter of the memory alloy expansion and contraction; In this embodiment, the second sound and light alarm operation refers to an alarm measure taken when the system determines that the current predicted wear depth does not exceed the set wear threshold, but there is a potential risk, and reminds the relevant personnel to pay attention through sound and / or visual signals. For example, in the maintenance system of the refrigerator damper, if the predicted wear depth does not exceed the wear threshold of 10%, but has reached 5%, the system may perform a second sound and light alarm operation, such as issuing a lower frequency alarm sound and flashing a slower warning light, to prompt the maintenance personnel to pay attention. In the fault prediction and adjustment process of the refrigerator damper, the system will continuously monitor the predicted wear depth and compare it with the wear threshold. If the predicted wear depth does not exceed the set threshold, but has reached a level that requires attention, the system will perform a second sound and light alarm operation to remind the maintenance personnel to review the status of the damper. This alarm operation may include issuing a warning sound or activating a warning light to ensure that the problem is evaluated and handled in a timely manner to prevent potential wear problems from developing into more serious faults. If the predicted wear depth exceeds the threshold, the system will further determine the maximum adjustment parameter of the memory alloy expansion and contraction to make necessary mechanical adjustments to ensure the normal operation of the damper and the refrigeration effect of the refrigerator.

[0057] S404, if the mechanical adjustment type is a variable diameter adjustment type, determining the memory alloy expansion and contraction adjustment parameter according to the predicted wear depth; In this embodiment, the memory alloy expansion and contraction adjustment parameter refers to a specific value used to control the expansion and contraction degree of the memory alloy elastic member in response to temperature changes. These parameters determine the amplitude and range of the mechanical adjustment. For example, in a fault adjustment mechanism of a variable diameter adjustment type, if the wear prediction depth indicates that there is a certain degree of wear at the damper hinge, the system may set the memory alloy expansion and contraction adjustment parameter, such as a telescopic length of 2 mm, to ensure that the damper can properly adjust the opening and closing angle. In the fault adjustment mechanism of the refrigerator damper, when the mechanical adjustment type is determined to be a variable diameter adjustment type, the system will determine the memory alloy expansion and contraction adjustment parameter based on the wear prediction depth. These parameters are key inputs in the adjustment process, and they guide the expansion and contraction amount that the memory alloy elastic member should achieve under specific temperature changes. For example, if the predicted depth shows that the degree of wear at the damper hinge needs to be compensated by increasing the tension of the damper, the system may set the memory alloy expansion and contraction length to 2 mm to achieve precise adjustment of the damper opening and closing angle. In this way, even if wear occurs at the damper hinge, the correct opening and closing state of the refrigerator damper can be maintained, maintaining the refrigeration efficiency and overall performance of the refrigerator.

[0058] S405, controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the maximum adjustment parameter of the memory alloy expansion and contraction or the memory alloy expansion and contraction adjustment parameter.

[0059] In this embodiment, the temporary adjustment operation refers to an operation of temporarily maintaining the normal operation of the equipment by adjusting the relative position or state of the mechanical parts when an abnormality is detected in the mechanical equipment but a serious failure has not yet occurred.

[0060] In summary, this technology obtains the type of mechanical adjustment and controls the fault adjustment mechanism to perform corresponding temporary adjustment operations, such as single-slot fixed adjustment or hinged head telescopic adjustment, according to the predicted wear depth and the set threshold or parameter, to optimize the damper performance and extend the service life. In the fault detection and adjustment system of the refrigerator damper, according to the real-time monitored predicted wear depth, the system automatically calculates and determines the adjustment parameters of the memory alloy telescopic adjustment. These parameters guide the memory alloy elastic parts to perform precise telescopic expansion to meet the current mechanical adjustment needs. For example, if the degree of wear at the damper hinge needs to be compensated by increasing the tension of the damper, the fault adjustment mechanism will control the elastic parts to perform corresponding telescopic expansion and contraction according to the set memory alloy telescopic adjustment parameters, and perform temporary adjustment operations. This operation can quickly respond to and adapt to changes caused by mechanical wear, temporarily restore or maintain the correct opening and closing state of the damper, thereby effectively preventing the decline of the refrigeration effect and buying time for the final repair or replacement of parts.

[0061] In one embodiment, if Figure 6As shown, in step S405, that is, according to the maximum adjustment parameter of the memory alloy expansion and contraction or the memory alloy expansion and contraction adjustment parameter, the step of controlling the fault adjustment mechanism to perform a temporary adjustment operation includes: S4051, determining temperature control data according to the maximum adjustment parameter of the memory alloy expansion and contraction or the memory alloy expansion and contraction adjustment parameter; In this embodiment, the temperature control data refers to the specific parameters used to control and adjust the temperature change in the system, including the set value, range of change and control accuracy of the temperature, so as to ensure that the memory alloy achieves the expected expansion and contraction effect at a specific temperature. For example, in the refrigerator damper fault adjustment mechanism, if the memory alloy needs to achieve maximum expansion and contraction at 35°C to adjust the damper, then 35°C is a key temperature control data point. In the refrigerator damper fault adjustment mechanism, the maximum adjustment parameter of the memory alloy expansion and contraction or the expansion and contraction adjustment parameter determined according to the real-time wear condition will be used to determine the temperature control data. These data include the starting temperature at which the memory alloy begins to respond to the temperature change, the temperature at which the maximum expansion and contraction is reached, and the accuracy of the temperature control. For example, the system may be set to fully expand and contract the memory alloy elastic member to adjust the damper to the optimal opening when the ambient temperature reaches 35°C. By accurately controlling these temperature control data, the fault adjustment mechanism can ensure that the memory alloy plays the greatest adjustment role at the correct temperature, thereby achieving accurate control of the damper opening and closing state, maintaining the refrigerator's refrigeration efficiency and extending the service life of the damper.

[0062] S4052. Determine the temperature control point of the memory alloy according to the temperature control data; In this embodiment, the temperature control point in this context refers to the arrangement point of the temperature control sensor at a specific position on or around the memory alloy, which is used to monitor and control the actual temperature passing through the memory alloy to ensure that the material is evenly heated at these points. For example, if three temperature control points are arranged on the memory alloy in the refrigerator damper fault adjustment mechanism, these points may be located at one end, the middle and the other end of the memory alloy elastic member to ensure the temperature uniformity over the entire length. In the design of the refrigerator damper fault adjustment mechanism, the temperature control point is a key monitoring and control element. The sensors at these points are responsible for real-time monitoring of the temperature distribution of the memory alloy to ensure that the material is evenly heated over the entire length or width. For example, by arranging sensors at both ends and the middle of the memory alloy elastic member, the heating process can be accurately controlled so that the memory alloy reaches a predetermined temperature condition at each point, thereby triggering its phase change characteristics and achieving precise telescopic adjustment. This uniform temperature control is essential to avoid uneven deformation of the material and improve the performance of the entire adjustment mechanism.

[0063] S4053, heating the memory alloy according to the temperature control point of the memory alloy to complete the temporary adjustment operation of the fault adjustment mechanism.

[0064] In this embodiment, by heating the temperature control points precisely arranged on the memory alloy, the technology can achieve precise temperature management of the temperature control points of the memory alloy, thereby controlling the phase change behavior of the memory alloy. The working principle is based on the superelasticity and shape memory effect of the memory alloy material, that is, under a specific temperature stimulus, the memory alloy can return to its original shape or reach a predetermined deformation state. In the fault adjustment mechanism, the heating elements (such as heating wires or thermistors) at these points heat the memory alloy according to a predetermined program, so that it is evenly heated at different points and activates its shape memory function. When the memory alloy reaches its transformation temperature, it will push the fault adjustment mechanism to produce a predetermined mechanical movement, such as stretching or contracting, and then fine-tune the opening and closing state of the refrigerator damper. This adjustment can temporarily compensate for the gap at the hinge caused by wear or damage, ensuring the sealing of the damper and the refrigeration efficiency of the refrigerator. In this way, the memory alloy temperature control point not only provides a precise and dynamic adjustment method, but also enhances the adaptability and reliability of the entire system, extends the maintenance cycle of the equipment, and reduces downtime.

[0065] In summary, this technology determines the expansion and contraction adjustment parameters of the memory alloy, calculates the temperature control data and temperature control points accordingly, and accurately heats the memory alloy, thereby achieving temporary adjustment operation of the fault adjustment mechanism to repair or alleviate the mechanical wear problem of the refrigerator damper.

[0066] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0067] In one embodiment, a refrigerator damper fault detection and adjustment device is provided, and the refrigerator damper fault detection and adjustment device corresponds to the refrigerator damper fault detection and adjustment method in the above embodiment. Fig. 9 As shown, the refrigerator damper fault detection and adjustment device includes a fault adjustment mechanism located at the hinge between the refrigerator damper and the refrigerator casing, and also includes an acquisition module, a first determination module, a second determination module and an execution module. The functional modules are described in detail as follows: An acquisition module, used for acquiring damper status data based on a polymorphic sensor, wherein the damper status data at least includes opening and closing status data, opening and closing frequency data, refrigerating chamber temperature data, fan noise level data and vibration intensity data; a first determination module, configured to determine a fault type according to the damper state data based on a trained abnormal state algorithm model, wherein the fault type at least includes a mechanical wear type, wherein the mechanical wear type is a damper fault condition caused by wear at a hinge between the refrigerator damper and the refrigerator casing; A second determination module, configured to determine a predicted wear depth if the fault type is a mechanical wear type; An execution module is used to control the fault adjustment mechanism to perform a temporary adjustment operation and execute a first sound and light alarm operation according to the predicted wear depth.

[0068] Optionally, the first determining module includes: A generating unit, used for standardizing the damper state data to generate standard scale data conforming to the trained abnormal state algorithm model; An extraction unit, used to extract key features from each of the standard scale data, and determine a type threshold corresponding to the key feature; A comparison unit, configured to compare the type threshold and the key feature based on a trained abnormal state algorithm model to determine a corresponding abnormal comparison value; A first determining unit, configured to combine the abnormal comparison values ​​into an abnormal set, and determine the probability of abnormal occurrence according to the abnormal set; A second determination unit is used to obtain historical abnormal event information, and determine the fault type according to the abnormality occurrence probability and the historical abnormal event information; Optionally, the second determining module includes: A selection unit, configured to select a key comparison value from among the abnormal comparison values ​​in the abnormal set corresponding to the mechanical wear type; An input unit, used to input the key comparison value into a trained depth prediction model; A third determination unit, configured to determine a predicted wear depth according to a result output by the depth prediction model; Optionally, the refrigerator damper fault detection and adjustment device further includes: A third determining module is used to determine a preset time period and a preset point in the preset time period; A second acquisition module is used to acquire a plurality of damper status data again according to the preset points within the preset time period; A judgment module, used for substituting the multiple re-acquired damper status data into the trained abnormal state algorithm model to judge whether the fault type reappears, and if so, checking the defects of the trained abnormal state algorithm model; A recording module, for recording, if not, the abnormal set corresponding to the wear prediction depth as the historical abnormal event information, and determining the key comparison value corresponding to the wear prediction depth as the matching identifier of the historical abnormal event information; Optionally, the execution module includes: An acquisition unit, used for acquiring a mechanical adjustment type, wherein the mechanical adjustment type at least includes a single-slot fixed adjustment type and a variable diameter adjustment type; a fourth determining unit, configured to determine a wear threshold if the mechanical adjustment type is a single-slot fixed adjustment type; A judging unit, used for judging whether the predicted wear depth is greater than the wear threshold, and if not, performing a second sound and light alarm operation, and if so, determining a maximum adjustment parameter of the memory alloy expansion and contraction; a fifth determining unit, configured to determine a memory alloy expansion and contraction adjustment parameter according to the predicted wear depth if the mechanical adjustment type is a variable diameter adjustment type; A control unit, used for controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the maximum adjustment parameter of the memory alloy expansion and contraction or the memory alloy expansion and contraction adjustment parameter; Optionally, the control unit includes: A first determination subunit, used to determine temperature control data according to the maximum adjustment parameter of the memory alloy expansion and contraction or the adjustment parameter of the memory alloy expansion and contraction; A second determination subunit is used to determine the temperature control point of the memory alloy according to the temperature control data; The heating subunit is used to heat the memory alloy according to the temperature control point of the memory alloy to complete the temporary adjustment operation of the fault adjustment mechanism.

[0069] The specific definition of a refrigerator damper fault detection and adjustment device can be found in the above definition of a refrigerator damper fault detection and adjustment method, which will not be repeated here. Each module in the above refrigerator damper fault detection and adjustment device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0070] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a refrigerator damper fault detection and adjustment method is implemented.

[0071] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: S10, based on the multi-state sensor, obtaining the damper status data, the damper status data at least including the opening and closing status data, the opening and closing frequency data, the refrigerating chamber temperature data, the fan noise level data and the vibration intensity data; S20, based on the trained abnormal state algorithm model, determine the fault type according to the damper state data, the fault type at least including the mechanical wear type, wherein the mechanical wear type is the damper fault caused by the wear of the hinge between the refrigerator damper and the refrigerator casing; S30, if the fault type is a mechanical wear type, determining a predicted wear depth; S40, controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth, and executing a first sound and light alarm operation.

[0072] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: S10, based on the multi-state sensor, obtaining the damper status data, the damper status data at least including the opening and closing status data, the opening and closing frequency data, the refrigerating chamber temperature data, the fan noise level data and the vibration intensity data; S20, based on the trained abnormal state algorithm model, determine the fault type according to the damper state data, the fault type at least including the mechanical wear type, wherein the mechanical wear type is the damper fault caused by the wear of the hinge between the refrigerator damper and the refrigerator casing; S30, if the fault type is a mechanical wear type, determining a predicted wear depth; S40, controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth, and executing a first sound and light alarm operation.

[0073] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0074] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0075] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A refrigerator damper fault detection and adjustment method, characterized in that: Applied to a fault adjustment mechanism located at a hinge between a refrigerator damper and a refrigerator casing, the refrigerator damper fault detection and adjustment method comprises: Based on the multi-state sensor, the damper status data is obtained, wherein the damper status data at least includes opening and closing status data, opening and closing frequency data, refrigeration chamber temperature data, fan noise level data and vibration intensity data; Based on the trained abnormal state algorithm model, the fault type is determined according to the damper state data, and the fault type at least includes a mechanical wear type, wherein the mechanical wear type is a damper fault caused by wear at a hinge between the refrigerator damper and the refrigerator casing; If the fault type is a mechanical wear type, determining a predicted wear depth; According to the predicted wear depth, the fault adjustment mechanism is controlled to perform a temporary adjustment operation and execute a first sound and light alarm operation.

2. A refrigerator damper fault detection and adjustment method according to claim 1, characterized in that: The step of determining the fault type according to the damper state data based on the trained abnormal state algorithm model includes: Standardizing the damper state data to generate standard scale data that conforms to the trained abnormal state algorithm model; Extracting key features from each of the standard scale data, and determining a type threshold corresponding to the key features; Based on the trained abnormal state algorithm model, comparing the type threshold and the key feature to determine the corresponding abnormal comparison value; Combining the abnormal comparison values ​​into an abnormal set, and determining the probability of abnormal occurrence according to the abnormal set; Obtain historical abnormal event information, and determine the fault type based on the abnormal occurrence probability and the historical abnormal event information.

3. A refrigerator damper fault detection and adjustment method according to claim 2, characterized in that: If the fault type is a mechanical wear type, the step of determining the predicted wear depth includes: In the abnormality set corresponding to the mechanical wear type, a key comparison value is selected between each of the abnormal comparison values; Inputting the key comparison value into a trained depth prediction model; The wear prediction depth is determined according to the result output by the depth prediction model.

4. A refrigerator damper fault detection and adjustment method according to claim 3, characterized in that: After the step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth and executing a first sound and light alarm operation, the method further comprises: Determine a preset time period and a preset point in the preset time period; Reacquiring a plurality of damper status data according to the preset points within the preset time period; Substituting the multiple re-acquired damper status data into the trained abnormal state algorithm model to determine whether the fault type reappears, and if so, checking the defects of the trained abnormal state algorithm model; If not, the abnormal set corresponding to the predicted wear depth is recorded as the historical abnormal event information, and the key comparison value corresponding to the predicted wear depth is determined as the matching identifier of the historical abnormal event information.

5. A refrigerator damper fault detection and adjustment method according to claim 1, characterized in that: The step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the predicted wear depth includes: Acquire a mechanical adjustment type, where the mechanical adjustment type includes at least a single-slot fixed adjustment type and a variable diameter adjustment type; If the mechanical adjustment type is a single slot fixed adjustment type, determining a wear threshold; Determine whether the predicted wear depth is greater than the wear threshold, if not, perform a second sound and light alarm operation, if yes, determine the maximum adjustment parameter of the memory alloy expansion and contraction; If the mechanical adjustment type is a variable diameter adjustment type, determining the memory alloy expansion and contraction adjustment parameter according to the predicted wear depth; According to the maximum adjustment parameter of the memory alloy expansion and contraction or the adjustment parameter of the memory alloy expansion and contraction, the fault adjustment mechanism is controlled to perform a temporary adjustment operation.

6. A refrigerator damper fault detection and adjustment method according to claim 5, characterized in that: The step of controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the maximum adjustment parameter of the memory alloy expansion and contraction or the memory alloy expansion and contraction adjustment parameter comprises: Determining temperature control data according to the maximum adjustment parameter of the memory alloy expansion and contraction or the adjustment parameter of the memory alloy expansion and contraction; Determining the temperature control point of the memory alloy according to the temperature control data; The memory alloy is heated according to the temperature control point of the memory alloy to complete the temporary adjustment operation of the fault adjustment mechanism.

7. A refrigerator damper fault detection and adjustment device, characterized in that: The refrigerator comprises a fault adjustment mechanism located at a hinge between the refrigerator damper and the refrigerator casing, and the refrigerator damper fault detection and adjustment device further comprises: An acquisition module, used for acquiring damper status data based on a polymorphic sensor, wherein the damper status data at least includes opening and closing status data, opening and closing frequency data, refrigerating chamber temperature data, fan noise level data and vibration intensity data; a first determination module, configured to determine a fault type according to the damper state data based on a trained abnormal state algorithm model, wherein the fault type at least includes a mechanical wear type, wherein the mechanical wear type is a damper fault condition caused by wear at a hinge between the refrigerator damper and the refrigerator casing; A second determination module, configured to determine a predicted wear depth if the fault type is a mechanical wear type; An execution module is used to control the fault adjustment mechanism to perform a temporary adjustment operation and execute a first sound and light alarm operation according to the predicted wear depth.

8. A refrigerator damper fault detection and adjustment device according to claim 7, characterized in that: The first determining module comprises: A generating unit, used for standardizing the damper state data to generate standard scale data conforming to the trained abnormal state algorithm model; An extraction unit, used to extract key features from each of the standard scale data, and determine a type threshold corresponding to the key feature; A comparison unit, configured to compare the type threshold and the key feature based on a trained abnormal state algorithm model to determine a corresponding abnormal comparison value; A first determining unit, configured to combine the abnormal comparison values ​​into an abnormal set, and determine the probability of abnormal occurrence according to the abnormal set; A second determination unit is used to obtain historical abnormal event information, and determine the fault type according to the abnormality occurrence probability and the historical abnormal event information; The second determining module comprises: A selection unit, configured to select a key comparison value from among the abnormal comparison values ​​in the abnormal set corresponding to the mechanical wear type; An input unit, used to input the key comparison value into a trained depth prediction model; A third determination unit, configured to determine a predicted wear depth according to a result output by the depth prediction model; The refrigerator damper fault detection and adjustment device further comprises: A third determination module is used to determine a preset time period and a preset point in the preset time period; A second acquisition module is used to acquire a plurality of damper status data again according to the preset points within the preset time period; A judgment module, used for substituting the multiple re-acquired damper status data into the trained abnormal state algorithm model to judge whether the fault type reappears, and if so, checking the defects of the trained abnormal state algorithm model; A recording module, for recording, if not, the abnormal set corresponding to the wear prediction depth as the historical abnormal event information, and determining the key comparison value corresponding to the wear prediction depth as the matching identifier of the historical abnormal event information; The execution module includes: An acquisition unit, used for acquiring a mechanical adjustment type, wherein the mechanical adjustment type at least includes a single-slot fixed adjustment type and a variable diameter adjustment type; a fourth determining unit, configured to determine a wear threshold if the mechanical adjustment type is a single-slot fixed adjustment type; A judging unit, used for judging whether the predicted wear depth is greater than the wear threshold, and if not, performing a second sound and light alarm operation, and if so, determining a maximum adjustment parameter of the memory alloy expansion and contraction; a fifth determining unit, configured to determine a memory alloy expansion and contraction adjustment parameter according to the predicted wear depth if the mechanical adjustment type is a variable diameter adjustment type; A control unit, used for controlling the fault adjustment mechanism to perform a temporary adjustment operation according to the maximum adjustment parameter of the memory alloy expansion and contraction or the memory alloy expansion and contraction adjustment parameter; The control unit comprises: A first determination subunit, configured to determine temperature control data according to the maximum adjustment parameter of the memory alloy expansion and contraction or the adjustment parameter of the memory alloy expansion and contraction; A second determination subunit is used to determine the temperature control point of the memory alloy according to the temperature control data; The heating subunit is used to heat the memory alloy according to the temperature control point of the memory alloy to complete the temporary adjustment operation of the fault adjustment mechanism.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a refrigerator damper fault detection and adjustment method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a refrigerator damper fault detection and adjustment method as described in any one of claims 1 to 6 are implemented.

Images