Compressor fault handling method and device, electronic equipment and storage medium
By performing wavelet analysis on the temperature and sound signals of the air conditioner compressor, the system can automatically diagnose and handle faults, solving the problems of low efficiency and insufficient accuracy in handling air conditioner compressor faults, and achieving efficient and accurate fault handling.
Patent Information
- Application Number
- CN202210779636.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-04
- Publication Date
- 2025-11-25
- Estimated Expiration
- 2042-07-04
AI Technical Summary
The diagnosis and repair of air conditioner compressor faults are time-consuming and rely on human experience, resulting in low efficiency and insufficient accuracy.
By acquiring the temperature and sound signals of the compressor, and using wavelet analysis models to decompose and analyze the signals, the fault type can be predicted and the handling method determined, thereby achieving automated fault diagnosis and handling.
It improves the efficiency and accuracy of compressor fault diagnosis, reduces manual intervention, and enhances the efficiency and precision of fault handling.
Smart Images
Figure CN115238474B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of equipment fault processing, and in particular to a compressor fault processing method and device, an electronic device and a storage medium. BACKGROUND
[0002] With the development of science and technology, people pursue a more comfortable life, and the demand for air conditioners is also gradually increasing.
[0003] The compressor of the air conditioner is the key to air conditioning refrigeration in the air conditioner refrigerant circuit, which drives the refrigerant to compress. If the air conditioner cannot cool or the temperature is unbalanced, the staff needs to check on site whether it is a compressor fault. If so, check the cause of the fault to repair the compressor fault, which consumes a lot of time and requires staff to have enough experience.
[0004] Therefore, there is an urgent need for a method for processing compressor faults to improve the efficiency and accuracy of fault processing. SUMMARY
[0005] Therefore, the embodiments of the present application provide a compressor fault processing method and device, an electronic device and a storage medium to realize the diagnosis and processing of compressor faults and improve the accuracy and efficiency of processing.
[0006] In a first aspect, the embodiments of the present application provide a compressor fault processing method, which comprises:
[0007] Obtaining a target compressor signal to be processed, and performing signal decomposition on the signal to be processed to obtain a target signal;
[0008] The signal to be processed includes at least one of a temperature sub-signal and a sound sub-signal.
[0009] Inputting the target signal into a fault analysis model to obtain a fault analysis result;
[0010] Based on the fault analysis result, it is determined whether the target compressor is faulty;
[0011] If so, a fault processing method is determined based on the fault type, and the compressor is processed based on the fault processing method.
[0012] Optimally, the fault type includes at least one of compressor frosting, compressor abnormal sound and compressor abnormal gas valve; and the fault analysis result includes at least one of a power signal and an energy signal.
[0013] Before the fault processing method is determined based on the fault type, it further comprises:
[0014] determine a fault type based on the fault analysis result;
[0015] The determination of the fault type based on the fault analysis result comprises:
[0016] If the power signal fluctuates within a first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound.
[0017] If the power signal fluctuates within a second fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor valve abnormality.
[0018] The determination of the fault type corresponding to the fault analysis result based on the power signal fluctuating within the first fault signal range comprises:
[0019] If the power signal fluctuates within the first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound based on the energy signal.
[0020] The determination of the fault type corresponding to the fault analysis result based on the energy signal comprises:
[0021] If the energy signal meets a first preset condition, the fault type corresponding to the fault analysis result is compressor frosting.
[0022] If the energy signal meets a second preset condition, the fault type corresponding to the fault analysis result is compressor abnormal sound.
[0023] The first fault signal range comprises at least one first fault signal sub-range, each fault signal sub-range corresponds to a first frosting level / first abnormal sound level, and the first preset condition comprises at least one first preset sub-condition, each first preset sub-condition corresponds to a second frosting level.
[0024] After determining the fault type corresponding to the fault analysis result based on the energy signal, the method further comprises:
[0025] Determining a first frosting level based on the first fault signal sub-range in which the power signal is located.
[0026] Determining a first frosting level based on the first preset sub-condition met by the energy signal.
[0027] Determining a target frosting level of the compressor based on the first frosting level and the second frosting level.
[0028] The determination of the fault processing mode based on the fault type comprises:
[0029] determine a fault handling mode based on the fault type and the fault level;
[0030] The determining of the fault handling mode based on the fault type and the fault level comprises:
[0031] If the fault type is compressor frosting, then a compressor running rate corresponding to the frosting level is determined according to the frosting level;
[0032] If the fault type is compressor abnormality, then a compressor running rate corresponding to the abnormality level is determined according to the abnormality level;
[0033] If the fault level is compressor abnormality, then a compressor running rate corresponding to the abnormality level is determined according to the abnormality level.
[0034] The method further comprises, before the obtaining of the to-be-processed signal of the target compressor, the following optimization:
[0035] The method further comprises, before the obtaining of the to-be-processed signal of the target compressor, the following optimization:
[0036] The pre-establishing of the fault analysis model comprises:
[0037] The method further comprises the following steps of:
[0038] The method further comprises the following steps of:
[0039] The method further comprises the following steps of:
[0040] In a second aspect, an embodiment of the present application further provides a compressor fault handling device, which comprises:
[0041] A to-be-processed signal acquisition module is configured to acquire a to-be-processed signal of a target compressor and perform signal decomposition on the to-be-processed signal to obtain a target signal; wherein the to-be-processed signal comprises at least one of a temperature sub-signal and an audio sub-signal;
[0042] An analysis result acquisition module is configured to input the target signal into a fault analysis model to obtain a fault analysis result;
[0043] A fault prediction module is configured to predict whether the target compressor is faulty based on the fault analysis result;
[0044] The fault processing mode determination module is configured to determine a fault processing mode based on the fault type if the target compressor is faulty, so as to perform fault processing on the compressor based on the processing mode.
[0045] In a third aspect, an electronic device is provided, and the electronic device includes:
[0046] one or more processors;
[0047] a memory device storing one or more programs,
[0048] When the one or more programs are executed by the one or more processors, the one or more processors implement the compressor fault processing method according to any of the embodiments of the present application.
[0049] In a fourth aspect, a storage medium containing computer executable instructions is provided, and the computer executable instructions are used to perform the compressor fault processing method according to any of the embodiments of the present application when executed by a computer processor.
[0050] The technical solution of the embodiments of the present application obtains a to-be-processed signal of a target compressor, performs signal decomposition on the to-be-processed signal to obtain a target signal, inputs the target signal into a fault analysis model to obtain a fault analysis result, predicts whether the target compressor is faulty based on the fault analysis result, determines a fault processing method based on the fault type if the target compressor is faulty, and performs fault processing on the compressor based on the fault processing method. The technical solution of the embodiments of the present application realizes the prediction of the compressor fault and the determination of the corresponding fault processing method based on the fault type, and then avoids the fault of the compressor, thereby improving the efficiency and accuracy of fault processing. BRIEF DESCRIPTION OF DRAWINGS
[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.
[0052] wherein:
[0053] Figure 1 FIG. 1 is a flowchart of a compressor fault processing method according to an embodiment of the present application;
[0054] Figure 2 FIG. 2 is a power spectrum diagram according to an embodiment of the present application;
[0055] Figure 3A flowchart of a compressor fault processing method in the embodiment one of the present application;
[0056] Figure 4 A flowchart of a compressor fault processing method in the embodiment two of the present application;
[0057] Figure 5 A structural diagram of a compressor fault processing device in the embodiment three of the present application;
[0058] Figure 6 A structural diagram of an electronic device in the embodiment four of the present application. DETAILED DESCRIPTION
[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.
[0060] Before the technical solutions in the embodiments of the present application are described, the application scenarios of the embodiments of the present application are exemplarily described:
[0061] The embodiments of the present application mainly process the fault of a compressor of a photovoltaic refrigeration system. A solar panel converts light radiation into electric energy and provides power supply for the compressor in the refrigeration system. When the light condition allows, the photovoltaic power generation system directly supplies power for the compressor through a conversion circuit. When the light condition is poor, the photovoltaic power generation system supplies power for the compressor through a storage battery. Since the refrigeration system causes large energy consumption, and the refrigeration unit is a main energy consumption equipment, when a fault occurs, the energy consumption of the refrigeration system will be increased, and the service life of the equipment will be reduced. Therefore, the fault prediction and processing of the refrigeration system are very important. The embodiments of the present application obtain a target signal through the decomposition of a to-be-processed signal of a target compressor, process the target signal based on a fault analysis model, further predict whether the compressor has a fault, determine the fault type, process the compressor based on the fault processing mode corresponding to the fault type, and avoid the fault in a targeted manner, thereby prolonging the service life of the equipment.
[0062] Embodiment one
[0063] Figure 1 A flowchart of a compressor fault processing method provided by the embodiments of the present application. The embodiments of the present application can be applicable to the case of processing the fault of a photovoltaic refrigeration compressor. The method of the embodiments of the present application can be executed by a compressor fault processing device. The device can be realized in the form of software and / or hardware.
[0064] AsFigure 1 The compressor fault processing method of the embodiment of the present application specifically comprises the following steps:
[0065] S110, obtaining a to-be-processed signal of a target compressor, and performing signal decomposition on the to-be-processed signal to obtain a target signal.
[0066] The compressor refers to a compressor with refrigeration and heating effect in an air conditioner. The power supply mode of the air conditioner can be photovoltaic power generation or mains power supply. The to-be-processed signal includes at least one of a temperature sub-signal and a sound sub-signal. The method for obtaining the to-be-processed signal includes but is not limited to obtaining the temperature sub-signal through a temperature sensor and obtaining the sound sub-signal through a sound sensor. The temperature sensor can be a T-type thermocouple, a K-type thermocouple, etc. The sound sub-signal includes a frequency sub-signal and an amplitude sub-signal. Optionally, the frequency sub-signal and the amplitude sub-signal of the sound are recorded through a phyphox sound parameter measuring device. The sampling frequency for obtaining the to-be-processed signal can be 1 minute, 2 minutes, or other sampling frequencies. The target signal refers to a signal that can be analyzed for faults, and the target signal can be used to determine whether the target compressor has failed. The signal decomposition method includes but is not limited to wavelet multi-level decomposition and variational mode decomposition.
[0067] Specifically, the to-be-processed signal of the target compressor is obtained, and the to-be-processed signal is decomposed to obtain the target signal, so as to prepare for subsequent processing of the target signal based on the fault analysis model.
[0068] It should be noted that after the to-be-processed signal is obtained, the to-be-processed signal is preprocessed to obtain a to-be-decomposed signal, and then the to-be-decomposed signal is decomposed to obtain the target signal. The preprocessing process includes converting the format of the to-be-processed signal, so that the format of the to-be-processed signal can be decomposed. For example, the signal format requires mat during signal decomposition, and the to-be-processed signal is in xlsx format. At this time, it needs to be converted to mat format, and the mat format to-be-processed signal is set to a column vector to obtain the to-be-decomposed signal. The to-be-decomposed signal is decomposed by wavelet multi-level decomposition, and the decomposed signal is denoised to obtain the target signal. Optionally, wavelet multi-level decomposition can be realized on MATLAB, and the subsequent fault analysis model can also be built on MATLAB. Of course, it can also be built on other software. Therefore, the format of the to-be-processed signal is changed according to the software used for preprocessing.
[0069] S120, inputting the target signal into a fault analysis model to obtain a fault analysis result.
[0070] The fault analysis model refers to a model for obtaining a fault analysis result by processing the target signal, and determining whether the target compressor is faulty according to the fault analysis result. The fault analysis model can be based on a wavelet analysis model or other models with signal analysis functions. The fault analysis result refers to a result obtained by processing the target signal by the fault analysis model, and whether the compressor is faulty can be predicted based on the fault analysis result.
[0071] Specifically, the target signal is processed by the fault analysis model to obtain a fault analysis result, and whether the target compressor is faulty is predicted based on the fault analysis result. For example, the fault analysis result is a power spectrum diagram corresponding to the sound sub-signal and / or an energy histogram corresponding to the temperature sub-signal. Whether the compressor is faulty is predicted based on the power signal in the power spectrum diagram and / or the energy signal in the energy histogram.
[0072] Further, in the embodiment of the present application, before obtaining the to-be-processed signal of the target compressor, the fault analysis model is also pre-built. The pre-built fault analysis model includes: collecting a first signal group of a first compressor group that is faulty and a second signal group of a second compressor group that is not faulty; the first signal group includes sound sub-signals and temperature sub-signals corresponding to each fault type of the faulty compressor, and the second signal group includes sound sub-signals and temperature sub-signals corresponding to the non-faulty compressor; determining a target training group based on the first signal group and the second signal group; training a wavelet analysis model based on the target training group to obtain the fault analysis model.
[0073] The first compressor group includes at least three faulty compressors, and the fault types of the compressors can be abnormal gas valve, compressor frosting, compressor abnormal sound, etc. Optionally, the number of compressors included in the first compressor group can be determined according to the fault type of the compressor. For example, one fault type corresponds to two compressors, so that the first compressor group includes at least six faulty compressors. Optionally, each faulty compressor is numbered, and the first signal group of the first compressor group can be sorted according to the number of the faulty compressor, so that the first signal group corresponds to the faulty compressor of the first compressor group one by one. Similarly, the second compressor group and the second signal group are set in the same way.
[0074] Specifically, the target training group is determined based on the first signal group and the second signal group, and the wavelet analysis model is trained based on the target training group to obtain the fault analysis model. Before obtaining the to-be-processed signal of the target compressor, the fault analysis model is built, so that the target signal can be processed when the target signal is obtained, and the efficiency of fault analysis is improved.
[0075] Further, in the embodiment of the present application, the algorithm is edited by MATLAB to train the wavelet analysis model to build the fault analysis model. Firstly, the signal frequency domain is analyzed, the signals of the target training group are filtered in sequence to obtain the signal spectrum diagram. Then, the signal frequency domain is strengthened, the signals corresponding to the signal spectrum diagram are loaded, the signals are decomposed by one level wavelet, the approximate reconstruction coefficients are determined, the approximation and the characteristics are determined, the signals are reconstructed by wavelet inverse transform, the signals are decomposed by multi-level wavelet, the approximate coefficients and the characteristics are extracted, the three-level approximation is reconstructed, the one-level, two-level and three-level characteristics are reconstructed, the results of multi-level decomposition are determined, the initial signals in three-level decomposition are reconstructed, and the power spectrum diagram is determined. The signals corresponding to the power spectrum diagram are loaded, the signals are decomposed by one level wavelet, the approximate reconstruction coefficients are determined, the approximation and the characteristics are determined, the signals are reconstructed by wavelet inverse transform, the signals are decomposed by multi-level wavelet, the approximate coefficients and the characteristics are extracted, the three-level approximation is reconstructed, the one-level, two-level and three-level characteristics are reconstructed, the results of multi-level decomposition are displayed, the initial signals in three-level decomposition are reconstructed, the signals are compressed, and the energy histogram is determined. Through the wavelet analysis algorithm, the first signal group of the compressor without fault and the second signal group of the compressor with fault are trained to obtain the energy histogram and the power spectrum diagram corresponding to the fault compressor, determine the energy signal range and the power signal range, and complete the training of the fault analysis model. Optionally, after obtaining the power spectrum diagram, the power signal is normalized to obtain the normalized frequency diagram, as shown in Figure 2 for the staff to view.
[0076] S130, based on the fault analysis result, judging whether the target compressor is faulty.
[0077] Specifically, when the fault analysis result is a value, it is judged that the target compressor is faulty. For example, when the power signal displayed by the power spectrum diagram fluctuates within the preset power range, it is judged that the target compressor is faulty and / or when the energy signal displayed by the energy histogram fluctuates within the preset energy range, it is determined that the target compressor is faulty.
[0078] It should be noted that for different fault types, the corresponding preset power range and the preset energy range are different. For example, for the abnormal sound of the compressor, the frequency of the fault sound is within a first preset range, for the frosting of the compressor, the frequency of the fault sound is within a second preset range, and for the abnormality of the gas valve of the compressor, the frequency of the fault sound is within a third preset range. Optionally, for the frosting of the compressor, the energy signal corresponding to the fault temperature is within a fourth preset range. It should be understood that the first preset range, the second preset range, the third preset range and the fourth preset range here are only to distinguish the preset ranges and do not have the order.
[0079] In the embodiment of the present application, when it is predicted that the compressor is about to fail, step S140 is performed, otherwise, the signal to be processed is continuously acquired, and the signal to be processed is subjected to signal decomposition processing and subsequent steps. When it is predicted that the compressor is about to fail, a warning information can be sent out and the fault is processed. The warning information can be sent out by the photovoltaic refrigeration system, and the warning information includes but is not limited to the compressor number, position, and failure time. Referring to Figure 3 Since the sound sub-signal and / or the temperature sub-signal may change before the compressor fails, when the compressor fails, the sound sub-signal and / or the temperature sub-signal change accordingly. Therefore, according to the fault analysis result, whether the compressor is about to fail can be predicted in the embodiment of the present application.
[0080] S140, determining a fault processing mode based on the fault type, and processing the fault of the compressor based on the fault processing mode.
[0081] The fault type refers to the type of the fault of the compressor, such as compressor frosting, compressor abnormal sound, compressor valve abnormality, etc. The fault processing mode refers to the mode of repairing the fault of the compressor or avoiding the fault.
[0082] Specifically, the fault processing mode can be determined based on a mapping relationship between the fault type and the fault processing mode, and the current fault type, can be determined based on a preset algorithm to process the fault type to obtain the fault processing method corresponding to the fault type, or can be determined based on a preset rule to process the fault type to obtain the fault processing method corresponding to the fault type. The fault of the compressor is processed based on the fault processing mode, which improves the accuracy and efficiency of fault processing.
[0083] The technical scheme of the embodiment of the present application acquires the signal to be processed of the target compressor, and obtains the target signal by signal decomposition processing of the signal to be processed. The target signal is input into the fault analysis model to obtain the fault analysis result. If so, the fault processing mode is determined based on the fault type, and the fault of the compressor is processed based on the fault processing mode. The technical scheme of the embodiment of the present application realizes the fault prediction and fault processing of the target compressor, and improves the processing effect and accuracy of the target compressor.
[0084] Embodiment two
[0085] Figure 4 is a flowchart of a compressor fault processing method provided by the embodiment of the present application. The embodiment of the present application adds a step of determining the fault type before step S140 based on the optional scheme of the above-mentioned embodiment. The specific added content will be described in detail in the embodiment of the present application, and the technical terms same as or similar to the above-mentioned embodiment will not be described again.
[0086] As Figure 4 shown, the compressor fault processing method provided by the embodiment of the application specifically comprises the following steps:
[0087] S210, obtaining a to-be-processed signal of a target compressor, and performing signal decomposition on the to-be-processed signal to obtain a target signal.
[0088] S220, inputting the target signal into a fault analysis model to obtain a fault analysis result.
[0089] S230, pre-judging whether the target compressor is faulty based on the fault analysis result.
[0090] S240, determining a fault type based on the fault analysis result.
[0091] The fault type comprises at least one of compressor frosting, compressor abnormal sound, and compressor abnormal gas valve; the fault analysis result comprises at least one of a power signal and an energy signal; the power signal can be in the form of a power spectrum diagram, and the energy signal can be in the form of an energy histogram.
[0092] Specifically, the fault type is determined according to the fault analysis result, so that the target compressor is processed based on a fault processing mode corresponding to the fault type. Optionally, a mapping table between the fault analysis result and the fault type is set in advance, and the fault type is determined based on the fault analysis result and the mapping table. Alternatively, a fault type determination rule is set in advance, and the fault type is obtained by processing the fault analysis result based on the fault type determination rule. For example, when the power signal meets a first preset rule, the fault type is determined to be compressor frosting, when the power signal meets a second preset rule, the fault type is determined to be compressor abnormal sound, and when the power signal meets a third preset rule, the fault type is determined to be compressor abnormal gas valve.
[0093] Further, in the embodiment of the application, determining the fault type based on the fault analysis result comprises: if the power signal fluctuates within a first fault signal range, determining that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound; and if the power signal fluctuates within a second fault signal range, determining that the fault type corresponding to the fault analysis result is compressor abnormal gas valve.
[0094] The first fault signal range refers to a fluctuation range of the power signal corresponding to compressor frosting / abnormal sound. The second fault signal range refers to a fluctuation range of the power signal corresponding to compressor abnormal gas valve. It should be noted that, since the fluctuation range of the sound sub-signal when the compressor is frosting / abnormal sound has an overlapping part, and correspondingly, the power signal obtained from the sound sub-signal through the fault analysis model also has an overlapping part, the first fault signal range refers to the fluctuation range of the power signal corresponding to compressor frosting / abnormal sound.
[0095] Specifically, when the power signal fluctuates in the first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound. When the power signal fluctuates in the second fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor valve abnormality. Since the fluctuation ranges of the power signals corresponding to the two fault types of compressor frosting and compressor abnormal sound overlap, the distinguishing method for the two will be described in detail in the following steps, which will not be specifically illustrated here. By the difference in the fluctuation range of the power signal, the corresponding fault type is determined, and the accuracy of the fault type determination is improved.
[0096] Further, in the embodiment of the present application, if the power signal fluctuates in the first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound, comprising: if the power signal fluctuates in the first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound based on the energy signal.
[0097] The energy signal is a result obtained by processing the temperature sub-signal by the fault analysis model.
[0098] Specifically, when the power signal fluctuates in the first fault signal range, the fault type corresponding to the fault analysis result is determined based on the energy signal. For example, when the energy signal fluctuates in the fourth preset range, it is determined that the fault type is compressor frosting. If not, it is determined that the fault type is compressor abnormal sound.
[0099] Further, in the embodiment of the present application, the fault type corresponding to the fault analysis result is determined based on the energy signal. Comprising: if the energy signal meets the first preset condition, the fault type corresponding to the fault analysis result is compressor frosting; if the energy signal meets the second preset condition, the fault type corresponding to the fault analysis result is compressor abnormal sound.
[0100] The first preset condition includes but is not limited to that the energy signal decreases by more than a preset threshold in a first preset time period, for example, the preset threshold is 30db and the first preset time period is 24 hours. The second preset condition includes but is not limited to that the energy signal decreases within a preset range in a second preset time period, the energy signal decreases in a gradient form in the second preset time period, etc. It should be understood that the first preset time period, the second preset time period, the preset threshold and the preset range herein can be set according to actual conditions, which will not be specifically limited here.
[0101] Specifically, when the drop amplitude of the energy signal meets the first preset condition, it is determined that the fault type corresponding to the fault analysis result is compressor frosting. When the drop amplitude of the energy signal meets the second preset condition, it is determined that the fault analysis result is compressor abnormal sound. By setting the preset conditions corresponding to the two fault types, and then determining the fault type corresponding to the fault analysis result according to the preset conditions, the accuracy of fault determination is improved.
[0102] Further, in the embodiment of the present application, the first fault signal range includes at least one first fault signal sub-range, each fault signal sub-range corresponds to a first frosting level / first abnormal sound level, the first preset condition includes at least one first preset sub-condition, each first preset sub-condition corresponds to a second frosting level one by one; after determining that the fault type corresponding to the fault analysis result based on the energy signal is compressor frosting, it further includes: determining the first frosting level based on the first fault signal sub-range where the power signal is located; determining the first frosting level based on the first preset sub-condition met by the drop amplitude of the energy signal; determining the target frosting level of the compressor based on the first frosting level and the second frosting level.
[0103] Among them, the first frosting level includes frosting level 1, frosting level 2, frosting level 3, etc., and the second frosting level includes frosting level 1, frosting level 2, frosting level 3, etc. The first frosting level and the second frosting level are only to distinguish between the two and have a sequence. For example, the first fault signal sub-range can be (-15db, -20db], (-20db, -25db], (-25db, -30db], etc. Correspondingly, the first frosting level corresponding to the first fault signal sub-range is frosting level 1, frosting level 2, frosting level 3 in turn. For example, the first preset sub-condition can be that the drop amplitude of the energy signal within 24 hours is greater than 20db, the drop amplitude of the energy signal within 24 hours is greater than 25db, and the drop amplitude of the energy signal within 24 hours is greater than 30db. Correspondingly, the second frosting level corresponding to the first preset sub-condition is frosting level 1, frosting level 2, frosting level 3 in turn.
[0104] Specifically, the first frosting level is determined based on the first fault signal sub-range where the power signal is located, the second frosting level is determined based on the energy signal, and the target frosting level is determined based on the first frosting level and the second frosting level. Optionally, in the embodiment of the present application, the proportion of the first frosting level and the second frosting level is set in advance, and the target frosting level is determined based on the first frosting level and the second frosting level and the respective proportions. For example, the first frosting level is frosting level 1, the second frosting level is frosting level 2, the first frosting level accounts for 20%, and the second frosting level accounts for 80%, so the target frosting level is calculated to be frosting level 2.
[0105] S250, determine a fault handling mode based on the fault type, and handle the fault of the compressor based on the fault handling mode.
[0106] Further, in the embodiment of the present application, the determination of the fault handling mode based on the fault type comprises: determining the fault handling mode based on the fault type and the fault level; determining the fault handling mode based on the fault type and the fault level comprises: if the fault type is compressor frosting, determining the compressor running rate corresponding to the frosting level according to the frosting level; if the fault type is compressor abnormal valve, determining the compressor running rate corresponding to the abnormal level according to the abnormal level; if the fault level is compressor abnormal sound, determining the compressor running rate corresponding to the abnormal sound level according to the abnormal sound level.
[0107] Wherein, the compressor running rate corresponding to the frosting level, the compressor running rate corresponding to the abnormal level and the compressor running rate determined according to the abnormal level can be set according to actual conditions. For example, the compressor running rate corresponding to the frosting level 1 is XX, and the compressor running rate corresponding to the frosting level 2 is YY. Correspondingly, the compressor running rate corresponding to each abnormal level and each abnormal sound level is set.
[0108] Specifically, according to the fault type and the fault level corresponding to the fault type, the corresponding fault handling mode is determined, and then the fault repair and fault avoidance of the compressor are performed according to the fault handling mode. For example, when the fault type is compressor frosting, the compressor running rate corresponding to the frosting level is determined according to the frosting level, and the current running rate of the compressor is adjusted according to the compressor running rate. Thus, the effect of avoiding the fault of the compressor is achieved. Similarly, the fault handling of the compressor abnormal sound and the compressor abnormal valve is the same as the above-mentioned fault handling principle when the compressor is frosting, which will not be repeated here.
[0109] Embodiment three
[0110] Figure 5 The structure diagram of the compressor fault handling device provided in the embodiment of the present application, the compressor fault handling device provided in the embodiment of the present application can execute the compressor fault handling method provided in any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.
[0111] The compressor fault handling device provided in the embodiment of the present application comprises: a to-be-processed signal acquisition module 310, an analysis result acquisition module 320, a fault prediction module 330 and a fault handling mode determination module 340; wherein:
[0112] The signal to be processed acquisition module 310 is configured to acquire a target compressor signal to be processed, and perform signal decomposition on the signal to be processed to obtain a target signal; wherein the signal to be processed includes at least one of a temperature sub-signal and an audio sub-signal; the analysis result acquisition module 320 is configured to input the target signal into a fault analysis model to obtain a fault analysis result; the fault prediction module 330 is configured to predict whether the target compressor is faulty based on the fault analysis result; and the fault processing mode determination module 340 is configured to, if the target compressor is faulty, determine a fault processing mode based on a fault type, so as to perform fault processing on the compressor based on the processing mode.
[0113] Further, the fault type includes at least one of compressor frosting, compressor abnormal sound, and compressor abnormal gas valve; the fault analysis result includes at least one of a power signal and an energy signal; and the device of the embodiment of the application further includes:
[0114] The fault type determination module is configured to determine a fault type based on the fault analysis result, and is further configured to: if the power signal fluctuates within a first fault signal range, determine that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound; and if the power signal fluctuates within a second fault signal range, determine that the fault type corresponding to the fault analysis result is compressor abnormal gas valve.
[0115] Further, the fault type determination module is further configured to:
[0116] If the power signal fluctuates within the first fault signal range, determine that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound based on the energy signal.
[0117] Further, the fault type determination module is further configured to: if a drop amplitude of the energy signal meets a first preset condition, determine that the fault type corresponding to the fault analysis result is compressor frosting; and if the drop amplitude of the energy signal meets a second preset condition, determine that the fault type corresponding to the fault analysis result is compressor abnormal sound.
[0118] Further, the first fault signal range includes at least one first fault signal sub-range, each fault signal sub-range corresponds to a first frosting level / first abnormal sound level, the first preset condition includes at least one first preset sub-condition, and each first preset sub-condition corresponds to a second frosting level in one-to-one manner; and the device of the embodiment of the application further includes: a frosting fault level determination module configured to determine a first frosting level based on a first fault signal sub-range in which the power signal is located, determine the first frosting level based on a first preset sub-condition met by the drop amplitude of the energy signal, and determine a target frosting level of the compressor based on the first frosting level and the second frosting level.
[0119] Further, the fault processing mode determination module 340 further includes a mode determination submodule, configured to determine the fault processing mode based on the fault type and the fault level; the mode determination submodule is further configured to: if the fault type is compressor frosting, determine the compressor running rate corresponding to the frosting level according to the frosting level; if the fault type is compressor abnormality, determine the compressor running rate corresponding to the abnormality level according to the abnormality level; if the fault level is compressor abnormal sound, determine the compressor running rate corresponding to the abnormal sound level according to the abnormal sound level.
[0120] Further, the device of the embodiment of the present application further includes a model building module, configured to build a fault analysis model in advance; the model building module is further configured to: collect a first signal group of a first compressor unit that has occurred a fault, and a second signal group of a second compressor unit that has not occurred a fault; the first signal group includes sound sub-signals and temperature sub-signals corresponding to each fault type of the fault compressor, and the second signal group includes sound sub-signals and temperature sub-signals corresponding to the non-fault compressor; determine a target training group based on the first signal group and the second signal group; train a wavelet analysis model based on the target training group to obtain the fault analysis model.
[0121] The compressor fault processing device of the embodiment of the present application includes a to-be-processed signal acquisition module, configured to acquire a to-be-processed signal of a target compressor, and perform signal decomposition on the to-be-processed signal to obtain a target signal; an analysis result acquisition module, configured to input the target signal into a fault analysis model to obtain a fault analysis result; a fault prediction module, configured to predict whether the target compressor has occurred a fault based on the fault analysis result; and a fault processing mode determination module, configured to determine a fault processing mode based on a fault type, and perform fault processing on the compressor based on the processing mode. The technical scheme of the embodiment of the present application realizes the prediction of the compressor fault and the processing of the compressor that has occurred a fault, and improves the efficiency and accuracy of the fault processing.
[0122] It should be noted that each module and submodule included in the above device is only divided according to the function logic, and is not limited to the above division, as long as the corresponding function can be realized; in addition, the specific name of each functional module is only for convenient mutual distinction, and does not serve to limit the protection scope of the embodiment of the present application.
[0123] Embodiment four
[0124] Figure 6 A structural schematic diagram of an electronic device provided by the embodiment of the present application. Figure 6 A block diagram of an exemplary electronic device 50 suitable for use in implementing embodiments of the present application is shown. Figure 6 The electronic device 50 shown is merely an example, and should not bring any limitation to the function and use range of the embodiment of the present application.
[0125] As shown in Figure 6 FIG. 1, electronic device 50 is in the form of a general-purpose computer. Components of electronic device 50 can include, but are not limited to, one or more processors or processing units 501, a system memory 502, and a bus 503 that couples various system components including system memory 502 to processing unit 501.
[0126] Bus 503 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics bus (e.g., AGP or Accelerated Graphics Port bus), and a local bus using any of a variety of bus architectures. By way of example, these architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
[0127] Electronic device 50 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 50 and includes both volatile and non- volatile media, removable and non-removable media.
[0128] System memory 502 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 504 and / or cache memory 505. Electronic device 50 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 506 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 6 not shown, a magnetic hard disk drive for reading from and writing to non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 6 In this regard, storage system 506 can be connected to bus 503 by one or more data media interfaces. As will be appreciated by persons skilled in the art, a storage system 506 can include one or more program products configured to implement the functions of various embodiments described herein.
[0129] Program / utility 508, having a set of programs / modules 507, can be stored in, for example, memory 502 by way of example, such programs includes an operating system, one or more applications, other program modules, and program data, each of which or a combination thereof, can include implementation of a networking environment. Programs 507 generally carry out the functions and / or methodologies of embodiments of the application as described herein.
[0130] Electronic device 50 can also communicate with one or more external devices 509, such as a keyboard or pointing device, a display 510, etc.; one or more devices that enable a user to interact with electronic device 50; and / or any devices (e.g., network card, modem, etc.) that enable electronic device 50 to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface(s) 511. Still yet, electronic device 50 can communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), and / or a public network, such as the Internet, via network adapter 512. As depicted, network adapter 512 communicates with the other components of electronic device 50 via bus 503. It should be appreciated that although not shown, other hardware and / or software modules could be used in conjunction with electronic device 50. Examples, include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc. Figure 6 Other hardware and / or software modules can be used in conjunction with electronic device 50, as desired, including but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc., which are not shown in FIG. 5.
[0131] Processing unit 501 performs various function applications and data processing by running programs stored in system memory 502, such as implementing the compressor fault processing method provided by the embodiments of the present application.
[0132] Embodiment Five
[0133] The embodiments of the present application also provide a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to perform a compressor fault processing method, the method comprising:
[0134] Obtaining a to-be-processed signal of a target compressor, and performing signal decomposition on the to-be-processed signal to obtain a target signal; wherein the to-be-processed signal comprises at least one of a temperature sub-signal and a sound sub-signal; inputting the target signal into a fault analysis model to obtain a fault analysis result; judging whether the target compressor is faulty based on the fault analysis result; if yes, determining a fault processing mode based on a fault type, and performing fault processing on the compressor based on the fault processing mode.
[0135] The computer storage medium of the embodiments of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.
[0136] The computer readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave, in which computer readable program code is embodied. Such propagated data signals can take a wide variety of forms, including but not limited to electro-magnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a storage medium, that is capable of storing the program for use by or in connection with the instruction execution system, apparatus or device.
[0137] The program code embodied on the computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the above.
[0138] The computer program code for carrying out operations of the embodiments of the present application can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as "C" or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).
[0139] The above merely provides the preferred embodiment of the application, and cannot allude the protection scope of the application, therefore any equivalent changes made according to the claims of the application shall be within the scope of the application.
Claims
1. A method of compressor fault handling, characterized by, The method comprises the following steps: acquiring a to-be-processed signal of a target compressor, and performing signal decomposition on the to-be-processed signal to obtain a target signal; wherein the to-be-processed signal comprises at least one of a temperature sub-signal and a sound sub-signal; inputting the target signal into a fault analysis model to obtain a fault analysis result; predicting whether the target compressor is faulty based on the fault analysis result; if yes, determining a fault handling mode based on the fault type, and performing fault handling on the compressor based on the fault handling mode; the fault type comprises at least one of compressor frosting, compressor abnormal sound, and compressor abnormal gas valve; and the fault analysis result comprises at least one of a power signal and an energy signal; before the step of determining the fault handling mode based on the fault type, the method further comprises the following steps: determining the fault type based on the fault analysis result; the step of determining the fault type based on the fault analysis result comprises the following steps: if the power signal fluctuates within a first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound; if the power signal fluctuates within a second fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor abnormal gas valve; wherein if the power signal fluctuates within the first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound, which comprises the following steps: if the power signal fluctuates within the first fault signal range, it is determined that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound based on the energy signal; the step of determining that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound based on the energy signal comprises the following steps: if the energy signal meets a first preset condition, the fault type corresponding to the fault analysis result is compressor frosting; if the energy signal meets a second preset condition, the fault type corresponding to the fault analysis result is compressor abnormal sound.
2. The compressor fault handling method of claim 1, wherein, the first fault signal range comprises at least one first fault signal sub-range, each fault signal sub-range corresponds to a first frosting level / first abnormal sound level, and the first preset condition comprises at least one first preset sub-condition, each first preset sub-condition corresponds to a second frosting level one by one; after the step of determining that the fault type corresponding to the fault analysis result is compressor frosting based on the energy signal, the method further comprises the following steps: determining a first frosting level based on the first fault signal sub-range where the power signal is located; determining a second frosting level based on the first preset sub-condition met by the energy signal; determining a target frosting level of the compressor based on the first frosting level and the second frosting level.
3. The compressor fault handling method of claim 1, wherein, the step of determining the fault handling mode based on the fault type comprises the following steps: determining the fault handling mode based on the fault type and the fault level; the step of determining the fault handling mode based on the fault type and the fault level comprises the following steps: if the fault type is compressor frosting, determining a compressor running rate corresponding to the frosting level according to the frosting level; if the fault type is compressor abnormal gas valve, determining a compressor running rate corresponding to the abnormal level according to the abnormal level. If the fault level is compressor abnormal sound, according to the abnormal sound level, a compressor running rate corresponding to the abnormal sound level is determined.
4. The compressor fault handling method of claim 1, wherein, Before the obtaining of the to-be-processed signal of the target compressor, the method further includes: a fault analysis model is pre-built; the pre-built fault analysis model includes: a first signal group of a first compressor group in which a fault occurs and a second signal group of a second compressor group in which no fault occurs are collected; the first signal group includes sound sub-signals and temperature sub-signals corresponding to each fault type of the fault compressor, and the second signal group includes sound sub-signals and temperature sub-signals corresponding to the non-fault compressor; a target training group is determined based on the first signal group and the second signal group; a wavelet analysis model is trained based on the target training group, to obtain the fault analysis model.
5. A compressor fault handling apparatus characterized by, includes: a to-be-processed signal acquisition module, configured to acquire a to-be-processed signal of a target compressor, and perform signal decomposition on the to-be-processed signal to obtain a target signal; wherein the to-be-processed signal includes at least one of a temperature sub-signal and an audio sub-signal; an analysis result acquisition module, configured to input the target signal into a fault analysis model to obtain a fault analysis result; a fault prediction module, configured to predict whether the target compressor is faulty based on the fault analysis result; a fault processing mode determination module, configured to, if the target compressor is faulty, determine a fault processing mode based on a fault type, and perform fault processing on the compressor based on the processing mode; the fault type includes at least one of compressor frosting, compressor abnormal sound, and compressor gas valve abnormality; and the fault analysis result includes at least one of a power signal and an energy signal; before the determination of the fault processing mode based on the fault type, the method further includes: determining the fault type based on the fault analysis result; the determination of the fault type based on the fault analysis result includes: if the power signal fluctuates within a first fault signal range, determining that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound; if the power signal fluctuates within a second fault signal range, determining that the fault type corresponding to the fault analysis result is compressor gas valve abnormality; if the power signal fluctuates within a first fault signal range, determining that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound, includes: if the power signal fluctuates within a first fault signal range, determining that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound based on the energy signal; the determination that the fault type corresponding to the fault analysis result is compressor frosting / abnormal sound based on the energy signal includes: if a drop amplitude of the energy signal meets a first preset condition, the fault type corresponding to the fault analysis result is compressor frosting; if a drop amplitude of the energy signal meets a second preset condition, the fault type corresponding to the fault analysis result is compressor abnormal sound.
6. An electronic device, comprising: The electronic device includes: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the compressor fault processing method according to any one of claims 1-4.
7. A storage medium containing computer-executable instructions for performing the compressor fault handling method of any of claims 1-4 when executed by a computer processor.