Fault judgment method and device, air conditioner and storage medium

Abstract

The application provides a fault judgment method and device, an air conditioner and a storage medium. The method is applied to the air conditioner. The method comprises the following steps: obtaining operation data of the air conditioner; inputting the operation data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample operation data and sample fault results; determining a fault handling parameter based on the fault prediction result and a pre-set corresponding relationship between the fault prediction result and the handling parameter; and adjusting an operation parameter of the air conditioner to the fault handling parameter. In this way, the air conditioner can be adjusted to different operation states according to different fault prediction results, so that the air conditioner can continue to operate in the mode set by the user in the case of air conditioner failure, and the occurrence rate of safety hazards can be reduced, and the user experience can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the air conditioning technical field, and particularly to a fault judgment method and device, an air conditioner and a storage medium. BACKGROUND

[0002] With the advent of the intelligent home appliance era, people's requirements for intelligent home appliances are increasing. In the process of using an air conditioner, various causes may lead to air conditioner failure. However, in the case of air conditioner failure, the air conditioner will continue to operate according to the user's set mode, which may cause safety hazards and reduce the user's experience. SUMMARY

[0003] The present application provides a fault judgment method, device, air conditioner and storage medium, which solves the defect that the air conditioner continues to run when it fails, thereby causing safety hazards and reducing the occurrence rate of safety hazards.

[0004] The present application provides a fault judgment method, which is applied to an air conditioner and includes the following steps:

[0005] Obtaining operation data of the air conditioner;

[0006] Inputting the operation data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample operation data and sample fault results;

[0007] Determining a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters;

[0008] Adjusting the operation parameter of the air conditioner to the fault handling parameter.

[0009] According to the fault judgment method provided by the present application, when the fault prediction result indicates that the fault level is the first fault level, the step of determining the fault handling parameter based on the fault prediction result and the pre-set correspondence between prediction results and handling parameters includes:

[0010] Determining a shutdown handling parameter based on the fault prediction result and the pre-set correspondence between prediction results and handling parameters, and taking the shutdown handling parameter as the fault handling parameter, wherein the shutdown handling parameter is a parameter for controlling the air conditioner to shut down and issuing an alarm;

[0011] The step of adjusting the operation parameter of the air conditioner to the fault handling parameter includes:

[0012] Adjusting the operation parameter of the air conditioner to the shutdown handling parameter.

[0013] According to the fault judgment method provided by the application, in the case that the fault prediction result indicates that the level of the fault is the second fault level, the step of determining the fault handling parameter based on the fault prediction result and the corresponding relationship between the prediction result and the handling parameter set in advance comprises:

[0014] The function suspension parameter is determined based on the fault prediction result and the corresponding relationship between the prediction result and the handling parameter set in advance, and the function suspension parameter is taken as the fault handling parameter.

[0015] The step of adjusting the running parameter of the air conditioner to the fault handling parameter comprises:

[0016] The running parameter of the air conditioner is adjusted to the function suspension parameter.

[0017] According to the fault judgment method provided by the application, the fault prediction model comprises a plurality of, the step of inputting the running data into the fault prediction model trained in advance to obtain the fault prediction result comprises:

[0018] The running data is input into each fault prediction model to obtain the corresponding fault prediction result.

[0019] The fault handling parameter comprises a plurality of, the step of adjusting the running parameter of the air conditioner to the fault handling parameter comprises:

[0020] According to the parameter priority set in advance, the fault handling parameter with the highest priority is determined.

[0021] The running parameter of the air conditioner is adjusted to the fault handling parameter with the highest priority.

[0022] According to the fault judgment method provided by the application, before the step of adjusting the running parameter of the air conditioner to the fault handling parameter, the method further comprises:

[0023] Based on the fault prediction result, the fault reminding information is generated.

[0024] The fault reminding information is sent to the application terminal, so that the application terminal plays and / or displays the fault reminding information.

[0025] According to the fault judgment method provided by the application, after the step of inputting the running data into the fault prediction model trained in advance to obtain the fault prediction result, the method further comprises:

[0026] The fault prediction result is sent to the server, so that the server determines the fault solution information based on the fault prediction result.

[0027] Receive the server sent the fault solution information, and send the fault solution information to the application terminal.

[0028] According to the fault prediction model provided by the application, the training method comprises:

[0029] Obtain the initial model, the sample running data and the sample fault result;

[0030] Input the sample running data into the initial model to obtain a prediction result;

[0031] Based on the difference between the prediction result and the sample fault result, the parameters of the initial model are adjusted until the initial model converges, and the fault prediction model is obtained.

[0032] The application further provides a fault judgment device, which is arranged in an air conditioner and comprises:

[0033] An acquisition module is configured to acquire running data of the air conditioner;

[0034] An input module is configured to input the running data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample running data and sample fault results;

[0035] A determination module is configured to determine a fault handling parameter based on the fault prediction result and a pre-set corresponding relationship between prediction results and handling parameters;

[0036] An adjustment module is configured to adjust the running parameter of the air conditioner to the fault handling parameter.

[0037] The application further provides an air conditioner comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the fault judgment method according to any one of the above.

[0038] The application further provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executable on a processor to implement the steps of the fault judgment method according to any one of the above.

[0039] The fault judgment method, device, air conditioner and storage medium provided by the application are applied to the air conditioner, and the method comprises the following steps: acquiring running data of the air conditioner, inputting the running data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample running data and sample fault results, determining a fault handling parameter based on the fault prediction result and a pre-set corresponding relationship between prediction results and handling parameters, and adjusting the running parameter of the air conditioner to the fault handling parameter.

[0040] In this way, the fault prediction result is obtained through the running data and the fault prediction model, and then according to the difference of the fault prediction result, the corresponding fault processing parameter is determined, and then the running parameter of the air conditioner is adjusted to the fault running parameter, that is, the air conditioner can be adjusted to different running states according to the difference of the fault prediction result, so that the situation that the air conditioner continues to run according to the mode set by the user in the case of air conditioner fault can be avoided, and the occurrence rate of safety hazards can be reduced, and the use experience of the user can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0042] Figure 1 is one of the flowcharts of the fault judgment method provided by the present application;

[0043] Figure 2 is the second flowchart of the fault judgment method provided by the present application;

[0044] Figure 3 is the structural schematic diagram of the fault judgment device provided by the present application;

[0045] Figure 4 is the structural schematic diagram of the air conditioner provided by the present application. DETAILED DESCRIPTION

[0046] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0047] In order to reduce the occurrence rate of safety hazards, the embodiments of the present application provide a fault judgment method, device, air conditioner, non-transitory computer readable storage medium and computer program product, which will be described below in combination with Figure 1 A fault judgment method provided by the embodiments of the present application is introduced.

[0048] As Figure 1 shown, the embodiments of the present application provide a fault judgment method, the method is applied to an air conditioner, and the method comprises:

[0049] S101, obtain running data of the air conditioner.

[0050] S102, input the running data into a pre-trained fault prediction model to obtain a fault prediction result.

[0051] In order to reduce the occurrence rate of safety hazards, the air conditioner can obtain running data of the air conditioner in real time. After obtaining the running data, the running data can be input into a pre-trained fault prediction model to obtain a fault prediction result. The fault prediction model is a model trained based on sample running data and sample fault results.

[0052] In an embodiment, the fault prediction model can include multiple types. After obtaining the running data, the running data can be input into each fault prediction model to obtain prediction results corresponding to the multiple fault prediction models. Each fault prediction model corresponds to a type of fault.

[0053] As an embodiment, the prediction result corresponding to the fault prediction model can be a result representing that the air conditioner has a fault, or a result representing that the air conditioner does not have a fault. In the case where the air conditioner does not have a fault, the running parameters of the air conditioner do not need to be changed.

[0054] In the case where the prediction result corresponding to the fault prediction model indicates that a fault occurs, the prediction result corresponding to the fault prediction model in which the fault occurs can be taken as the fault prediction result. That is, the fault prediction result can include a prediction result corresponding to at least one fault. The fault prediction result can be a result representing that the air conditioner has a fault.

[0055] S103, determine a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters.

[0056] S104, adjust the running parameters of the air conditioner to the fault handling parameter.

[0057] In the case where the fault prediction result is obtained, a fault handling parameter can be determined based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters. The running parameters of the air conditioner are adjusted to the fault handling parameter. In this way, in the case where the air conditioner has a fault, the running parameters of the air conditioner can be modified to the fault handling parameter, so as to change the running state of the air conditioner.

[0058] It can be seen that in the embodiment, the fault prediction result can be obtained by running data and a fault prediction model, and then according to the different fault prediction results, the corresponding fault handling parameters are determined, and then the running parameters of the air conditioner are adjusted to the fault running parameters, that is, the air conditioner can be adjusted to different running states according to the different fault prediction results, so that the situation that the air conditioner continues to run according to the mode set by the user in the case of air conditioner fault can be avoided, and the occurrence rate of safety hazards can be reduced, and the user experience can be improved.

[0059] As an embodiment of the present application, the fault prediction result can indicate the corresponding level of the fault, wherein the corresponding level of the fault is pre-set. The corresponding level of the fault includes a first fault level, a second fault level and a third fault level. The severity of the corresponding fault of the first fault level is higher than that of the second fault level, and the severity of the corresponding fault of the second fault level is higher than that of the third fault level.

[0060] In the case that the fault prediction result indicates that the level of the fault is the first fault level, the step of determining the fault handling parameter based on the fault prediction result and the pre-set corresponding relationship between the prediction result and the handling parameter includes:

[0061] Based on the fault prediction result and the pre-set corresponding relationship between the prediction result and the handling parameter, the shutdown handling parameter is determined as the fault handling parameter, wherein the shutdown handling parameter is a parameter for controlling the air conditioner to shut down and issuing an alarm.

[0062] In the case that the fault prediction result indicates that the level of the fault is the first fault level, it means that the severity of the fault of the air conditioner is high, and the air conditioner cannot continue to run. In this case, the fault handling parameter can be a shutdown handling parameter, which is a parameter for controlling the air conditioner to shut down and issuing an alarm.

[0063] The step of adjusting the running parameters of the air conditioner to the fault handling parameters can include:

[0064] The running parameters of the air conditioner are adjusted to the shutdown handling parameters. In this way, the air conditioner can be shut down, and the user can be reminded that the air conditioner cannot continue to run by issuing an alarm prompt sound, avoiding safety hazards caused by the first fault level corresponding to the fault.

[0065] For example, the fault prediction result is fan damage, the corresponding fault level of the fan damage is the first fault level, and according to the corresponding relationship between the fan damage and the pre-set prediction result and handling parameter, the shutdown handling parameter can be determined, and then the running parameters of the air conditioner can be adjusted to the shutdown handling parameter.

[0066] It can be seen that in the embodiment, in the case that the fault prediction result indicates that the level of the fault is the first fault level, the operating parameter of the air conditioner can be adjusted to the shutdown processing parameter, and the safety hazard caused by the fault corresponding to the first fault level can be avoided.

[0067] As an embodiment of the embodiment, in the case that the fault prediction result indicates that the level of the fault is the second fault level, the step of determining the fault processing parameter based on the fault prediction result and the corresponding relationship between the prediction result and the processing parameter preset in advance comprises:

[0068] determining the function suspension parameter based on the fault prediction result and the corresponding relationship between the prediction result and the processing parameter preset in advance, and taking the function suspension parameter as the fault processing parameter.

[0069] In the case that the fault prediction result indicates that the level of the fault is the second fault level, it indicates that the severity of the fault of the air conditioner is low, and the air conditioner can operate, but the function corresponding to the fault prediction result cannot operate. In this case, the fault processing parameter is the function suspension parameter, and the function suspension parameter is a parameter for controlling the suspension of the function corresponding to the fault prediction result.

[0070] The step of adjusting the operating parameter of the air conditioner to the fault processing parameter can comprise:

[0071] adjusting the operating parameter of the air conditioner to the function suspension parameter. In this way, the air conditioner can lock the function corresponding to the fault prediction result, that is, suspend the function corresponding to the fault prediction result. Thus, even if the user subsequently invokes the function corresponding to the fault prediction result, the air conditioner will not respond, and the safety hazard caused by the fault corresponding to the second fault level can be avoided.

[0072] For example, the fault prediction result is a human body sensing sensor anomaly, the level of the human body sensing sensor anomaly is the second fault level, and according to the corresponding relationship between the human body sensing sensor anomaly and the processing parameter preset in advance, the human body sensing function suspension parameter can be determined, and the operating parameter of the air conditioner can be adjusted to the human body sensing function suspension parameter.

[0073] It can be seen that in the embodiment, in the case that the fault prediction result indicates that the level of the fault is the second fault level, the operating parameter of the air conditioner can be adjusted to the function suspension parameter, and the safety hazard caused by the fault corresponding to the second fault level can be avoided.

[0074] As an implementation of the embodiment of the present application, in the case that the fault prediction result indicates that the level of the fault is the third fault level, it is explained that the severity of the fault of the air conditioner is the lowest, that is, the fault does not affect the operation of the air conditioner, and in this case, the parameter corresponding to the fault prediction result is the parameter that the air conditioner is currently operating, and therefore, the step of adjusting the operating parameter of the air conditioner to the fault handling parameter can not be performed, that is, the operating parameter of the air conditioner is not changed.

[0075] As an implementation of the embodiment of the present application, the fault prediction model can include multiple, and the fault predicted by each fault prediction model is not the same.

[0076] The step of inputting the operating data into the pre-trained fault prediction model to obtain the fault prediction result can include:

[0077] The operating data is input into each fault prediction model to obtain the corresponding fault prediction result.

[0078] In an implementation, the number of fault prediction results can be consistent with the number of fault prediction models, and in this case, the fault prediction result can be a result representing that the air conditioner has a fault, or a result representing that the air conditioner does not have a fault.

[0079] In the case that the fault prediction result is a result representing that the air conditioner does not have a fault, the step of determining the fault handling parameter based on the fault prediction result and the pre-set correspondence between the prediction result and the handling parameter can not be performed, and in the pre-set correspondence between the prediction result and the handling parameter, there is no parameter corresponding to the fault prediction result representing that the air conditioner does not have a fault.

[0080] In the case that the fault prediction result is a result representing that the air conditioner has a fault, the step of determining the fault handling parameter based on the fault prediction result and the pre-set correspondence between the prediction result and the handling parameter can be performed, and the number of fault handling parameters is less than the number of fault prediction models.

[0081] In another implementation, the fault prediction result is only a result representing that the air conditioner has a fault. In the case that the fault prediction result is a result representing that the air conditioner has a fault, the step of determining the fault handling parameter based on the fault prediction result and the pre-set correspondence between the prediction result and the handling parameter can be performed, and the number of fault handling parameters is consistent with the number of fault prediction results.

[0082] For example, in the case that the fault prediction result is a result representing that the fan is damaged, the shutdown handling parameter can be determined as the fault handling parameter based on the fan damage and the pre-set correspondence between the prediction result and the handling parameter.

[0083] In a case where the fault prediction result is the human body induction sensor abnormality, the human body induction function suspension parameter can be determined as the fault handling parameter based on the human body induction sensor abnormality and a preset corresponding relationship between the prediction result and the handling parameter.

[0084] In a case where the fault prediction result is the four-way valve abnormality, the heating function suspension parameter can be determined as the fault handling parameter based on the four-way valve abnormality and a preset corresponding relationship between the prediction result and the handling parameter.

[0085] In a case where the fault handling parameter includes multiple parameters, the step of adjusting the operation parameter of the air conditioner to the fault handling parameter can include:

[0086] According to the preset parameter priority, the fault handling parameter with the highest priority is determined.

[0087] The operation parameter of the air conditioner is adjusted to the fault handling parameter with the highest priority.

[0088] The preset parameter priority corresponds to the level of the fault, and the higher the severity of the fault, the higher the priority of the corresponding fault handling parameter. The fault handling parameter corresponding to the first fault level is the shutdown handling parameter, and the handling parameter corresponding to the second fault level is the function suspension parameter.

[0089] The severity of the fault corresponding to the first fault level is higher than the severity of the fault corresponding to the second fault level, and the priority of the shutdown handling parameter is higher than the priority of the function suspension parameter.

[0090] In a case where the fault handling parameter includes multiple different function suspension parameters, the functions corresponding to the function suspension parameters can be suspended, that is, the operation parameter of the air conditioner is adjusted to each function suspension parameter in turn.

[0091] In a case where the fault handling parameter includes the shutdown handling parameter and at least one function suspension parameter, the shutdown handling parameter can be determined as the fault handling parameter with the highest priority, and then the operation parameter of the air conditioner can be adjusted to the shutdown handling parameter.

[0092] As can be seen, in the embodiment, in a case where the fault handling parameter includes multiple parameters, the operation parameter of the air conditioner can be adjusted to the fault handling parameter with the highest priority according to the preset parameter priority, thereby further reducing the occurrence rate of safety hazards and improving the user experience.

[0093] As an embodiment of the present application, before the step of adjusting the operation parameter of the air conditioner to the fault handling parameter, the method can further include:

[0094] Based on the fault prediction result, generate fault reminding information, and send the fault reminding information to an application terminal, so that the application terminal plays and / or displays the fault reminding information.

[0095] After obtaining the fault prediction result, the fault reminding information can be generated according to the fault prediction result. After generating the fault reminding information, the fault reminding information can be sent to the application terminal, and then the application terminal can play and / or display the fault reminding information.

[0096] In an embodiment, the application terminal can be a mobile terminal such as a mobile phone, a computer, a tablet computer, etc. The application terminal can also be a smart home appliance terminal commonly used by the user. This is reasonable.

[0097] As an embodiment, the specific information of the fault and the contact information of the corresponding maintenance personnel can be taken as the fault reminding information according to the fault prediction result and the location information of the air conditioner, and then the fault reminding information can be sent to the application terminal of the user and the application terminal of the maintenance personnel. In this way, the user can contact the maintenance personnel to maintain the air conditioner according to the needs, thereby improving the efficiency of solving the fault.

[0098] In the case where the fault prediction result indicates that the level of the fault is the third fault level, the fault solving method can be determined according to the fault prediction result and the corresponding relationship between the prediction result and the solving method stored in advance. In this way, the user can solve the fault of the air conditioner according to the fault solving method.

[0099] For example, the fault prediction result indicates that dirty filter screen causes poor heat exchange, and the corresponding fault level of dirty filter screen causing poor heat exchange is the third fault level. The fault solving method can be determined according to dirty filter screen causing poor heat exchange and the corresponding relationship between the prediction result and the solving method stored in advance.

[0100] In the case where the fault prediction result indicates that the level of the fault is the first fault level, the second fault level or the third fault level, the above-mentioned step of generating the fault reminding information according to the fault prediction result can be performed. In this way, the user can quickly know the problem of the air conditioner, and the use experience of the user can be improved.

[0101] As an embodiment of the present application, in the case where the fault prediction result indicates that the level of the fault is the second fault level, the fault reminding information includes the signal of the unavailable function.

[0102] After the step of adjusting the operating parameter of the air conditioner to the fault handling parameter, the method can further include:

[0103] In the case where the adjustment instruction of the unavailable function is received, a pre-set unavailable prompt sound corresponding to the unavailable function is played.

[0104] In order to avoid the security risks caused by the fault corresponding to the second fault level, after adjusting the operating parameters of the air conditioner to the fault handling parameters, that is, adjusting the operating parameters of the air conditioner to the function suspension parameters, in the case of receiving the adjustment instruction of the unavailable function, a pre-set unavailable prompt sound corresponding to the unavailable function can be played, for example, the unavailable prompt sound can be voice information corresponding to "human body sensing function unavailable".

[0105] In this way, the user can be reminded that the function (unavailable function) corresponding to the fault prediction result cannot be used at present, and the user's use experience can be further improved.

[0106] As an embodiment of the present application, after the above step of inputting the operating data into the pre-trained fault prediction model to obtain the fault prediction result, the method can further include:

[0107] The fault prediction result is sent to a server to enable the server to determine fault resolution information based on the fault prediction result. The fault resolution information sent by the server is received, and the fault resolution information is sent to an application terminal.

[0108] After obtaining the fault prediction result, the fault prediction result can be sent to the server, and the server can determine the fault resolution information according to the fault prediction result. In an embodiment, the fault resolution information can be determined according to the fault prediction result and a pre-stored corresponding relationship between the prediction result and the resolution information. The pre-stored corresponding relationship between the prediction result and the resolution information in the server can be updated in real time, so that more accurate fault resolution information can be determined.

[0109] In another embodiment, after obtaining the fault prediction result, the server can send the fault prediction result to a designated staff to enable the staff to upload the fault resolution information corresponding to the fault prediction result to the server.

[0110] After obtaining the fault resolution information, the server can send the fault resolution information to the air conditioner, and then the air conditioner can send the fault resolution information to the application terminal, so that the user can obtain the corresponding fault resolution information.

[0111] After obtaining the fault resolution information, the server can also send the fault resolution information to the application terminal according to a pre-stored corresponding relationship between the air conditioner and the application terminal, so that the user can obtain the corresponding fault resolution information.

[0112] It can be seen that in the embodiment, more accurate fault resolution information can be obtained and sent to the application terminal, so that the user can obtain corresponding fault resolution information, thereby improving the user experience.

[0113] As an embodiment of the present application, the training method of the above fault prediction model can include:

[0114] Obtain the initial model, the sample running data and the sample fault result;

[0115] Input the sample running data into the initial model to obtain a prediction result;

[0116] Adjust the parameters of the initial model based on the difference between the prediction result and the sample fault result until the initial model converges to obtain the fault prediction model.

[0117] In an embodiment, the detection position corresponding to the sample fault result can be determined according to different sample fault results, and then the fault information can be manually input. When the air conditioner with the fault is started, the sample running data corresponding to the detection position can be obtained.

[0118] For example, the sample fault result is damage of the air conditioner outdoor unit fan blade. After starting the air conditioner with the damaged air conditioner outdoor unit fan blade, the sample running data such as motor speed, fan current, radiator temperature, compressor exhaust suction temperature, etc. can be obtained.

[0119] As an embodiment, in order to further improve the accuracy of subsequent fault prediction results, the prediction normal range value and the prediction abnormal range value of each running data can be determined during the training of the initial model.

[0120] After the training of the fault prediction model is completed, that is, after the prediction normal range value and the prediction abnormal range value of the data are determined, the running data of the air conditioner is input into the fault prediction model. In the case where the fault prediction result indicates that the running data belongs to the prediction normal range value, it means that the fault corresponding to the fault prediction model has not occurred. In the case where the fault prediction result indicates that the running data belongs to the prediction abnormal range value, it means that the fault corresponding to the fault prediction model has occurred.

[0121] As an embodiment, after obtaining the sample running data and the sample fault result, the sample running data and the sample fault result can be divided into three levels, wherein the sample running data and the sample fault result have a corresponding relationship.

[0122] The sample running data and the sample fault result are divided into a first fault level, a second fault level and a third fault level, one sample fault result corresponds to multiple sample running data, and for each sample fault result, a fault prediction model corresponding to the sample fault result can be trained. After obtaining multiple fault prediction models, the fault prediction models can be divided into models corresponding to the first fault level, the second fault level and the third fault level, so that after obtaining a fault prediction result subsequently, the level of the fault indicated by the fault prediction result can be determined according to the level of the fault prediction model corresponding to the fault prediction result.

[0123] For the fault prediction model corresponding to the second fault level, an air conditioner function component library can be set in advance, so as to subsequently determine the corresponding unavailable function and then suspend the unavailable function. In order to more conveniently understand the fault judgment method provided by the embodiment of the application, the fault judgment method provided by the embodiment of the application will be introduced below by taking Figure 2 as an example.

[0124] For example, as shown in Figure 2 , the fault judgment method provided by the embodiment of the application can include the following steps.

[0125] S201, obtaining an initial model, sample running data and a sample fault result.

[0126] The sample fault result includes sample fault results corresponding to the first fault level, the second fault level and the third fault level, the sample fault result corresponding to the first fault level includes multiple samples, the sample fault result corresponding to the second fault level includes multiple samples, and the sample fault result corresponding to the third fault level includes multiple samples. Each sample fault result corresponds to multiple sample running data.

[0127] S202, inputting the sample running data into the initial model to obtain a prediction result, adjusting the parameters of the initial model based on the difference between the prediction result and the sample fault result until the initial model converges to obtain a fault prediction model.

[0128] S203, completing program programming of the fault prediction model through embedded software development and compiling the air conditioner function component library.

[0129] S204, obtaining running data of the air conditioner.

[0130] S205, inputting the running data into the fault prediction model trained in advance to obtain a fault prediction result, determining a fault handling parameter based on the corresponding relationship between the fault prediction result and the prediction result and the handling parameter set in advance, and adjusting the running parameter of the air conditioner to the fault handling parameter.

[0131] S206, generating fault reminding information based on the fault prediction result.

[0132] S207, send the predicted fault reminding information to the application terminal, so that the application terminal plays and / or displays the fault reminding information.

[0133] In a case where the fault prediction result indicates that the level of the fault is the first fault level, the air conditioner stops and issues an alarm. In a case where the fault prediction result indicates that the level of the fault is the second fault level, the air conditioner suspends the unavailable function and sends the fault reminding information to the application terminal. In a case where the fault prediction result indicates that the level of the fault is the third fault level, the air conditioner continues to run and sends the fault reminding information to the application terminal.

[0134] It can be seen that, in the embodiment, different levels of faults can be predicted by the fault prediction model, so that the air conditioner is processed in different ways, accurate judgment of the fault can be achieved, the analysis time of the after-sales engineer is reduced, the after-sales can process the fault according to the fault reminding information, the cycle of processing the fault is reduced, the occurrence rate of safety hazards is reduced, and the use experience of the user is improved.

[0135] The fault judgment device provided by the present application is described below, and the fault judgment device described below can be referred to in correspondence with the fault judgment method described above.

[0136] As shown in Figure 3 The embodiment of the present application provides a fault judgment device, the device is arranged in an air conditioner, and the device comprises:

[0137] The acquisition module 310 is configured to acquire operation data of the air conditioner.

[0138] The input module 320 is configured to input the operation data into a pre-trained fault prediction model to obtain a fault prediction result.

[0139] The fault prediction model is a model trained based on sample operation data and sample fault results.

[0140] The determination module 330 is configured to determine a fault processing parameter based on the fault prediction result and a pre-set corresponding relationship between the fault prediction result and the processing parameter.

[0141] The adjustment module 340 is configured to adjust the operation parameter of the air conditioner to the fault processing parameter.

[0142] As an embodiment of the present application, the determination module 330 comprises:

[0143] The first determining unit is configured to, in a case where the fault prediction result indicates that the level of the fault is a first fault level, determine a shutdown processing parameter based on the fault prediction result and a preset corresponding relationship between a prediction result and a processing parameter, and take the shutdown processing parameter as the fault processing parameter, wherein the shutdown processing parameter is a parameter for controlling the air conditioner to shut down and issuing an alarm.

[0144] The adjusting module 340 includes:

[0145] The first adjusting unit is configured to adjust the operation parameter of the air conditioner to the shutdown processing parameter.

[0146] As an embodiment of the present application, the determining module 330 includes:

[0147] The first determining unit is configured to, in a case where the fault prediction result indicates that the level of the fault is a second fault level, determine a function suspension parameter based on the fault prediction result and a preset corresponding relationship between a prediction result and a processing parameter, and take the function suspension parameter as the fault processing parameter.

[0148] The adjusting module 340 includes:

[0149] The second adjusting unit is configured to adjust the operation parameter of the air conditioner to the function suspension parameter.

[0150] As an embodiment of the present application, the apparatus further includes:

[0151] The generating module is configured to, before adjusting the operation parameter of the air conditioner to the fault processing parameter, generate fault reminding information based on the fault prediction result.

[0152] The first sending module is configured to send the fault reminding information to an application terminal, so that the application terminal plays and / or displays the fault reminding information.

[0153] As an embodiment of the present application, in a case where the fault prediction result indicates that the level of the fault is a second fault level, the fault reminding information includes information of an unavailable function.

[0154] The apparatus further includes:

[0155] The playing module is configured to, after adjusting the operation parameter of the air conditioner to the fault processing parameter, in a case where an adjusting instruction of the unavailable function is received, play a preset unavailable prompt sound corresponding to the unavailable function.

[0156] As an embodiment of the present application, the fault prediction model includes a plurality of, and the input module 320 can include:

[0157] The input unit is configured to input the operation data into each of the fault prediction models to obtain corresponding fault prediction results.

[0158] The fault handling parameters include a plurality of parameters, and the adjusting module 340 can include:

[0159] A third adjusting unit is configured to determine a fault handling parameter with the highest priority according to a pre-set parameter priority, and adjust the operation parameter of the air conditioner to the fault handling parameter with the highest priority.

[0160] As an embodiment of the present application, the device further includes:

[0161] The second sending module is configured to send the fault prediction result to a server after obtaining the fault prediction result by inputting the operation data into the pre-trained fault prediction model, so that the server determines fault resolution information based on the fault prediction result.

[0162] The receiving module is configured to receive the fault resolution information sent by the server and send the fault resolution information to an application terminal.

[0163] As an embodiment of the present application, the device can further include a training module, and the fault prediction model is obtained by the training module.

[0164] The training module is configured to obtain an initial model, the sample operation data and the sample fault result, input the sample operation data into the initial model to obtain a prediction result, adjust parameters of the initial model based on a difference between the prediction result and the sample fault result until the initial model converges to obtain the fault prediction model.

[0165] Figure 4 An example of a schematic diagram of an entity structure of an air conditioner is shown in FIG. 1. Figure 4As shown, the air conditioner can include a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other through the communications bus 440. The processor 410 can invoke the logical instructions in the memory 430 to execute the fault judgment method, the method being applied to an air conditioner and comprising: obtaining running data of the air conditioner, inputting the running data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample running data and sample fault results, determining a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters, and adjusting the running parameters of the air conditioner to the fault handling parameter.

[0166] In addition, the logical instructions in the memory 430 described above can be implemented in the form of a software functional unit and sold or used as a standalone product, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application or parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0167] On the other hand, the present application also provides a computer program product, which comprises a computer program that can be stored on a non-transitory computer-readable storage medium, and the computer program can be executed by a processor to enable a computer to execute the fault judgment method provided by the above-mentioned methods, the method being applied to an air conditioner and comprising: obtaining running data of the air conditioner, inputting the running data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample running data and sample fault results, determining a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters, and adjusting the running parameters of the air conditioner to the fault handling parameter.

[0168] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the fault determination method provided by each of the above methods, the method being applied to an air conditioner and comprising: obtaining operation data of the air conditioner, inputting the operation data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample operation data and sample fault results, determining a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters, and adjusting an operation parameter of the air conditioner to the fault handling parameter.

[0169] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0170] From the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0171] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A failure determination method characterized by comprising: The method is applied to an air conditioner, and the method comprises: obtaining operation data of the air conditioner; inputting the operation data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample operation data and sample fault results; determining a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters; adjusting an operation parameter of the air conditioner to the fault handling parameter; the fault prediction model comprises a plurality of, and the step of inputting the operation data into a pre-trained fault prediction model to obtain a fault prediction result comprises: inputting the operation data into each of the fault prediction models to obtain a corresponding fault prediction result; the fault handling parameter comprises a plurality of, and the step of adjusting the operation parameter of the air conditioner to the fault handling parameter comprises: determining a fault handling parameter with the highest priority according to a pre-set parameter priority; adjusting the operation parameter of the air conditioner to the fault handling parameter with the highest priority; the training method of the fault prediction model comprises: obtaining an initial model, the sample operation data and the sample fault result; inputting the sample operation data into the initial model to obtain a prediction result; adjusting parameters of the initial model based on the difference between the prediction result and the sample fault result until the initial model converges to obtain the fault prediction model.

2. The failure determination method according to claim 1, characterized by, in the case where the fault prediction result indicates that the level of the fault is a first fault level, the step of determining a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters comprises: determining a shutdown handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters, and taking the shutdown handling parameter as the fault handling parameter, wherein the shutdown handling parameter is a parameter for controlling the air conditioner to shut down and issuing an alarm; the step of adjusting the operation parameter of the air conditioner to the fault handling parameter comprises: adjusting the operation parameter of the air conditioner to the shutdown handling parameter.

3. The failure determination method according to claim 1, characterized by, in the case where the fault prediction result indicates that the level of the fault is a second fault level, the step of determining a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters comprises: determining a function suspension parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters, and taking the function suspension parameter as the fault handling parameter; the step of adjusting the operation parameter of the air conditioner to the fault handling parameter comprises: adjusting the operation parameter of the air conditioner to the function suspension parameter.

4. The failure determination method according to claim 1 or 3, characterized by, before the step of adjusting the operation parameter of the air conditioner to the fault handling parameter, the method further comprises: generating fault reminder information based on the fault prediction result; sending the fault reminder information to an application terminal to enable the application terminal to play and / or display the fault reminder information.

5. The failure determination method according to any one of claims 1 to 3, characterized by, After the step of inputting the operation data into the pre-trained fault prediction model to obtain a fault prediction result, the method further comprises: sending the fault prediction result to a server, so that the server determines fault resolution information based on the fault prediction result; receiving the fault resolution information sent by the server and sending the fault resolution information to an application terminal.

6. A failure determination device characterized by comprising: The device is used to implement the fault determination method according to any one of claims 1-5, and the device is arranged in an air conditioner and comprises: an acquisition module configured to acquire operation data of the air conditioner; an input module configured to input the operation data into a pre-trained fault prediction model to obtain a fault prediction result, wherein the fault prediction model is a model trained based on sample operation data and sample fault results; a determination module configured to determine a fault handling parameter based on the fault prediction result and a pre-set correspondence between prediction results and handling parameters; an adjustment module configured to adjust an operation parameter of the air conditioner to the fault handling parameter.

7. An air conditioner comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the fault determination method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the fault determination method according to any one of claims 1-5.

Images