Fault diagnosis method and device for compressor and water chilling unit

Abstract

The invention discloses a fault diagnosis method and device for a compressor and a water chilling unit, and belongs to the field of fault diagnosis. The fault diagnosis method for the compressor comprises the following steps: acquiring actual winding temperature information and a first target threshold value of a motor in the compressor; on the basis of the actual winding temperature information and the first target threshold value, under the condition that a motor cooling fault is determined, the fault type of the compressor is determined on the basis of at least one of the power information and the pressure difference information of the motor; and based on the fault type, the fault level of the compressor is determined. According to the fault diagnosis method of the compressor, the detection precision and accuracy are high, on the basis of motor cooling fault detection, the fault type is further diagnosed, the fault level is determined based on the fault type, effective guidance can be provided for operation maintenance after the fault occurs, and the reliability and safety of operation of the compressor motor are effectively improved.

Description

Technical Field

[0001] The present application belongs to the field of fault diagnosis, and in particular, relates to a compressor fault diagnosis method, device and chiller. Background Art

[0002] The compressor is the core component of the chiller and provides power for the refrigeration system. When the motor cooling fails, the temperature of the motor winding will continue to rise, causing the compressor to operate in a less efficient manner and even causing insulation failure, posing a safety hazard. In related technologies, the motor cooling fault is mainly diagnosed by real-time monitoring of the motor winding temperature, thereby achieving early warning of motor cooling faults. However, the accuracy of the diagnostic results of this method is not high, and it is impossible to further evaluate the cause and severity of the fault. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a compressor fault diagnosis method, device and chiller, which have high detection precision and accuracy, and can provide effective guidance for operation and maintenance after a fault, effectively improving the reliability and safety of the compressor motor operation.

[0004] In a first aspect, the present application provides a compressor fault diagnosis method, the method comprising:

[0005] Acquiring actual winding temperature information and a first target threshold value of a motor in a compressor;

[0006] In the case where a motor cooling fault is determined based on the actual winding temperature information and the first target threshold, determining a fault type of the compressor based on at least one of power information and pressure difference information of the motor;

[0007] Based on the fault type, a fault level of the compressor is determined.

[0008] According to the compressor fault diagnosis method of the present application, the motor cooling fault is detected by measuring the actual winding temperature information, fully considering the influence of the refrigerant flow rate and the ambient temperature, and the detection precision and accuracy are high; on the basis of the motor cooling fault detection, the fault type is further diagnosed and the fault level is determined based on the fault type, which can provide effective guidance for post-fault operation and maintenance, and effectively improve the reliability and safety of the compressor motor operation.

[0009] According to an embodiment of the present application, determining a motor cooling fault based on the actual winding temperature information and the first target threshold value includes:

[0010] Based on the actual winding temperature information and the first target threshold, determining a target abnormality detection algorithm; the target abnormality detection algorithm is a rule-based abnormality detection algorithm or a model-based abnormality detection algorithm;

[0011] Based on the target abnormality detection algorithm, the motor cooling fault is determined.

[0012] According to an embodiment of the present application, the actual winding temperature information includes an actual winding temperature, and the first target threshold includes a winding temperature alarm threshold; and determining a target abnormality detection algorithm based on the actual winding temperature information and the first target threshold includes:

[0013] In a case where the actual winding temperature is greater than the winding temperature alarm threshold, determining that the target abnormality detection algorithm is the rule-based abnormality detection algorithm;

[0014] When the actual winding temperature is not greater than the winding temperature alarm threshold, the target abnormality detection algorithm is determined to be the model-based abnormality detection algorithm.

[0015] According to one embodiment of the present application, determining the motor cooling fault based on the target abnormality detection algorithm includes:

[0016] In the case of performing a fault alarm based on the target abnormality detection algorithm, determining the fault alarm information based on the number of fault alarms;

[0017] When the fault alarm information is greater than the second target threshold, the motor cooling fault is determined.

[0018] According to an embodiment of the present application, the actual winding temperature information includes at least one of the actual winding temperature and the actual winding temperature rise value, and the first target threshold includes at least one of the winding temperature alarm threshold and the winding temperature rise alarm threshold; the fault alarm based on the target abnormality detection algorithm includes:

[0019] When the actual winding temperature is greater than the winding temperature alarm threshold, a fault alarm is issued;

[0020] In the case where the target abnormality detection algorithm is the model-based abnormality detection algorithm, obtaining an absolute value of a difference between the actual winding temperature rise value and the predicted winding temperature rise value; the predicted winding temperature rise value is obtained based on a winding temperature rise model;

[0021] When the absolute value of the difference is greater than the winding temperature rise alarm threshold, a fault alarm is issued.

[0022] According to an embodiment of the present application, when the target abnormality detection algorithm is the model-based abnormality detection algorithm, determining the motor cooling fault based on the target abnormality detection algorithm includes:

[0023] The motor cooling fault is determined based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold; the predicted winding temperature rise value is obtained based on a winding temperature rise model.

[0024] The determining the motor cooling fault based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold comprises:

[0025] According to one embodiment of the present application, when the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value is greater than the winding temperature rise alarm threshold, the motor cooling fault is determined.

[0026] According to one embodiment of the present application, the predicted winding temperature rise value is determined based on the following steps:

[0027] Inputting the actual operating parameters of the compressor into a winding temperature rise model to obtain the predicted winding temperature rise value output by the temperature rise model;

[0028] Among them, the winding temperature rise model includes a fitting polynomial model, a machine learning model or a physical model, and the actual working parameters include at least one of the actual compressor power, the actual refrigerant outlet pressure, the actual refrigerant inlet pressure, the actual refrigerant outlet temperature and the actual refrigerant inlet temperature.

[0029] According to an embodiment of the present application, before determining the motor cooling fault based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold, the method further includes:

[0030] When the winding temperature rise model is not calibrated, calibrating the winding temperature rise model based on actual operating parameters of the compressor;

[0031] When the winding temperature rise model has been calibrated and the training samples meet the target conditions, the winding temperature rise model is updated based on the training samples, and the training samples are obtained from the actual working parameters.

[0032] According to an embodiment of the present application, determining the fault type of the compressor based on at least one of the power information and the pressure difference information of the motor includes:

[0033] When the power information is greater than a first threshold, determining that the fault type is an internal short circuit;

[0034] When the pressure difference information is less than a second threshold, the fault type is determined to be a pressure difference abnormality.

[0035] According to an embodiment of the present application, determining the fault type of the compressor based on at least one of the power information and the pressure difference information of the motor includes: determining that the fault type is an internal short circuit when the power information is greater than a first threshold;

[0036] When the power information is not greater than the first threshold and the pressure difference information is less than a second threshold, determining that the fault type is a pressure difference abnormality;

[0037] When the power information is not greater than the first threshold and the pressure difference information is not less than the second threshold, it is determined that the fault type is abnormal cooling flow.

[0038] According to an embodiment of the present application, determining the fault level of the compressor based on the fault type includes:

[0039] When the fault type is an internal short circuit, the fault level is determined based on at least one of the actual winding temperature information and the power information.

[0040] According to an embodiment of the present application, determining the fault level based on at least one of the actual winding temperature information and the power information includes:

[0041] When the actual winding temperature information is greater than a severe internal short circuit temperature threshold, or the power information is greater than a severe internal short circuit power percentage threshold, determining that the fault level is a severe fault;

[0042] When the actual winding temperature information is greater than the moderate internal short-circuit temperature threshold and not greater than the severe internal short-circuit temperature threshold, or the power information is greater than the moderate internal short-circuit power percentage threshold and not greater than the severe internal short-circuit power percentage threshold, the fault level is determined to be a moderate fault;

[0043] When the actual winding temperature information is not greater than the moderate internal short-circuit temperature threshold, and the power information is not greater than the moderate internal short-circuit power percentage threshold, the fault level is determined to be a mild fault.

[0044] In a second aspect, the present application provides a compressor fault diagnosis device, the device comprising:

[0045] A first processing module, used for obtaining actual winding temperature information of a motor in the compressor and a first target threshold;

[0046] a second processing module, configured to determine a fault type of the compressor based on at least one of power information and pressure difference information of the motor, when a motor cooling fault is determined based on the actual winding temperature information and the first target threshold;

[0047] The third processing module is used to determine the fault level of the compressor based on the fault type.

[0048] According to the compressor fault diagnosis device of the present application, the motor cooling fault is detected by measuring the actual winding temperature information, and the influence of the refrigerant flow rate and the ambient temperature is fully considered, and the detection precision and accuracy are high; on the basis of the motor cooling fault detection, the fault type is further diagnosed and the fault level is determined based on the fault type, which can provide effective guidance for post-fault operation and maintenance, and effectively improve the reliability and safety of the compressor motor operation.

[0049] In a third aspect, the present application provides a chiller, comprising:

[0050] compressor;

[0051] a motor connected to the compressor;

[0052] As described in the second aspect, the compressor fault diagnosis device is electrically connected to the compressor and the motor respectively.

[0053] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the compressor fault diagnosis method as described in the first aspect above.

[0054] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the compressor fault diagnosis method as described in the first aspect above.

[0055] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects:

[0056] The motor cooling fault is detected by measuring the actual winding temperature information, fully considering the influence of the refrigerant flow rate and the ambient temperature, and the detection precision and accuracy are high. On the basis of the motor cooling fault detection, the fault type is further diagnosed and the fault level is determined based on the fault type, which can provide effective guidance for post-fault operation and maintenance, and effectively improve the reliability and safety of the compressor motor operation.

[0057] Furthermore, by combining the rule-based anomaly detection algorithm and the model-based anomaly detection algorithm, when the rule-based anomaly detection algorithm diagnoses that the winding temperature is normal, the model-based anomaly detection algorithm is further used to diagnose whether the winding temperature rise is normal, so as to determine whether the motor cooling is faulty. It can further detect gradual faults on the basis of detecting instantaneous faults or more serious faults, thereby achieving early warning of faults. It is suitable for any fault detection scenario, has high flexibility and universality, and can effectively improve the reliability and safety of compressor motor operation.

[0058] Furthermore, by setting the winding temperature rise model to a fitting polynomial model, a machine learning model or a physical model, the accuracy of different application scenarios can be met; the parameters of the winding temperature rise model are set to the power (or current) of the unit operation, the pressure and temperature of the refrigerant entering and leaving the motor, which are easy to obtain and do not require the installation of complex and expensive detection equipment, and the cost is low.

[0059] Furthermore, through the online automatic calibration of the operating parameters of the unit and the online automatic updating of the winding temperature rise model, no manual settings are required and it has good versatility.

[0060] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0062] Figure 1 This is one of the flow charts of the compressor fault diagnosis method provided in the embodiment of the present application;

[0063] Figure 2 This is the second flow chart of the compressor fault diagnosis method provided in the embodiment of the present application;

[0064] Figure 3 is a structural schematic diagram of a compressor fault diagnosis device provided in an embodiment of the present application;

[0065] Figure 4 It is a schematic diagram of the structure of the chiller provided in the embodiment of the present application. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0067] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0068] In combination with the accompanying drawings, the compressor fault diagnosis method, the compressor fault diagnosis device, the chiller and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0069] The compressor fault diagnosis method may be applied to a terminal, and may be specifically executed by hardware or software in the terminal.

[0070] It should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse and joystick.

[0071] The compressor fault diagnosis method provided in the embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the compressor fault diagnosis method. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The compressor fault diagnosis method provided in the embodiment of the present application is described below using an electronic device as an example of the execution subject.

[0072] like Figure 1 As shown, the compressor fault diagnosis method includes: step 110, step 120 and step 130.

[0073] Step 110, obtaining a first target threshold and actual winding temperature information of a motor in a compressor;

[0074] In this step, the actual winding temperature information may include an actual winding temperature rise value and an actual winding temperature.

[0075] Among them, the actual winding temperature can be collected based on the temperature sensor, such as collecting temperature at each certain time interval (such as 30s or 1min, etc., not limited in this application), so that the collected temperature is used as the actual winding temperature corresponding to the current collection moment.

[0076] During the actual execution process, the collected actual winding temperature information can be stored in a local or cloud database and retrieved when needed.

[0077] The category of the first target threshold corresponds to actual winding temperature information.

[0078] The first target threshold may be user-defined or automatically determined by the system, which is not limited in this application.

[0079] In some embodiments, the first target threshold may be an adaptive threshold. For example, the first target threshold may be learned through unit operation data.

[0080] In some embodiments, the first target threshold may include: a winding temperature rise alarm threshold and a winding temperature alarm threshold.

[0081] like Figure 2 As shown, in some embodiments, step 110 may further include: performing data cleaning on the acquired working parameters, and acquiring actual winding temperature information based on the cleaned data.

[0082] In this embodiment, by performing data cleaning on the working parameters to remove data without physical meaning, the accuracy and calculation rate of subsequent calculation results can be improved.

[0083] The acquired actual winding temperature information and the first target threshold are used to determine whether the motor cooling fails.

[0084] Step 120: When a motor cooling fault is determined based on the actual winding temperature information and the first target threshold, determine a fault type of the compressor based on at least one of the power information and the pressure difference information of the motor;

[0085] In this step, the fault type may include but is not limited to: internal short circuit, abnormal cooling flow rate, and abnormal pressure difference.

[0086] It can be understood that whether the motor cooling fails can be determined based on the actual winding temperature information and the first target threshold.

[0087] During the research and development process, the inventors discovered that in the related technology, there is a method of estimating the temperature of the DC motor winding by the rate of change of magnetic flux and / or resistance, but this method ignores the influence of the refrigerant flow rate and ambient temperature, thereby affecting the detection accuracy of the motor winding temperature.

[0088] In the present application, fault diagnosis is performed by using the actual winding temperature information obtained through actual measurement, effectively considering the influence of the refrigerant flow rate and the ambient temperature, thereby improving the detection accuracy.

[0089] In some embodiments, determining a motor cooling fault based on actual winding temperature information and a first target threshold may include:

[0090] Determining a target abnormality detection algorithm based on actual winding temperature information and a first target threshold;

[0091] Based on the targeted anomaly detection algorithm, motor cooling faults are identified.

[0092] In this embodiment, the target anomaly detection algorithm may be a rule-based anomaly detection algorithm or a model-based anomaly detection algorithm.

[0093] The rule-based anomaly detection algorithm may be a conventional detection algorithm, which is used to detect transient faults or more serious faults.

[0094] Model-based anomaly detection algorithms are suitable for gradual fault detection and can achieve early prediction of faults.

[0095] It can be understood that, based on the relationship between the actual winding temperature information and the first target threshold, different abnormality detection algorithms can be selected to further improve the accuracy of the detection result.

[0096] In some embodiments, the actual winding temperature information may include at least one of an actual winding temperature rise value and an actual winding temperature.

[0097] The first target threshold may include at least one of a winding temperature rise alarm threshold and a winding temperature alarm threshold.

[0098] Continue to refer Figure 2 In some embodiments, determining a target abnormality detection algorithm based on actual winding temperature information and a first target threshold value may include:

[0099] When the actual winding temperature is greater than the winding temperature alarm threshold, determining the target anomaly detection algorithm to be a rule-based anomaly detection algorithm;

[0100] When the actual winding temperature is not greater than the winding temperature alarm threshold, the target abnormality detection algorithm is determined to be a model-based abnormality detection algorithm.

[0101] In this embodiment, when the actual winding temperature is greater than the winding temperature alarm threshold, it can be considered that the winding temperature is abnormal, and the rule-based abnormality detection algorithm is entered.

[0102] Among them, the rule-based anomaly detection algorithm determines whether the motor cooling is faulty by comparing the actual winding temperature with the winding temperature alarm threshold.

[0103] In some embodiments, a motor cooling fault may be determined when entering a rule-based anomaly detection algorithm.

[0104] In other embodiments, when entering the rule-based anomaly detection algorithm, it is also possible to determine whether the motor cooling is faulty by comprehensively comparing the relationship between the actual winding temperature and the winding temperature alarm threshold over a period of time.

[0105] When the actual winding temperature is not greater than the winding temperature alarm threshold, it can be approximately considered that the current winding temperature is normal. It is necessary to further predict the change trend of the winding temperature and determine whether the change trend is normal, then enter the model-based anomaly detection algorithm.

[0106] The specific algorithms of the rule-based anomaly detection algorithm and the model-based anomaly detection algorithm will be described in the following embodiments and will not be described in detail here.

[0107] In some embodiments, determining a motor cooling fault based on a target abnormality detection algorithm may further include:

[0108] In the case of fault alarm based on the target anomaly detection algorithm, the fault alarm information is determined based on the number of fault alarms;

[0109] When the fault alarm information is greater than the second target threshold, a motor cooling fault is determined.

[0110] In this embodiment, the fault alarm information is used to represent the actual frequency or actual number of times the fault alarm occurs within the first target duration.

[0111] In some embodiments, the fault alarm information may be the total number of fault alarms within the first target duration, or the fault alarm information may be the proportion of fault alarms within the first target duration.

[0112] Among them, the first target duration can be based on user customization, such as setting it to 1 day or 2 days, etc., which is not limited in this application.

[0113] The second target threshold is the maximum allowable frequency or the maximum allowable number of fault alarms within the preset first target duration.

[0114] The second target threshold may be user-defined, or may be automatically determined by the system (such as obtained through learning from unit operation data), and this application does not limit this.

[0115] In the actual execution process, when the actual winding temperature information exceeds the first target threshold, it is considered that the winding temperature is too high, and a fault alarm is issued at this time, and the number of fault alarms is recorded to obtain fault alarm information.

[0116] It can be understood that when the fault alarm information exceeds the second target threshold, it is considered that the frequency or number of fault alarms exceeds the maximum allowable frequency or number, and a motor cooling fault is determined.

[0117] When the fault alarm information does not exceed the second target threshold, it is considered that the frequency or number of fault alarms is within the maximum allowable frequency or number, and the motor cooling is approximately considered normal.

[0118] According to the compressor fault diagnosis method provided by the embodiment of the present application, by comparing the first target threshold with the actual winding temperature information, and further comparing the number or proportion of fault alarms with the size of the second target threshold, it is possible to effectively eliminate the misjudgment of faults caused by accidental circumstances and improve the accuracy and precision of the motor cooling fault information finally obtained. It should be noted that for different target anomaly detection algorithms, the execution logic of the corresponding fault alarms is also different.

[0119] The following describes the specific methods for determining motor cooling failure from two perspectives.

[0120] 1. Determination of rule-based anomaly detection algorithm

[0121] In some embodiments, performing a fault alarm based on a target anomaly detection algorithm may include: performing a fault alarm when an actual winding temperature is greater than a winding temperature alarm threshold.

[0122] In this embodiment, the actual winding temperature information includes the actual winding temperature, and the first target threshold includes a winding temperature alarm threshold.

[0123] Whether the motor cooling is faulty can be determined based on the actual winding temperature and the winding temperature alarm threshold.

[0124] Taking the actual winding temperature information as the actual winding temperature and the first target threshold as the winding temperature alarm threshold as an example, the fault detection algorithm determines the condition 1 of the motor cooling fault at the current moment (such as every minute):

[0125] T MWT，a >T thr

[0126] Among them, T MWT，a is the actual winding temperature of the motor (unit: K), T thr is the winding temperature alarm threshold, which can be learned through the unit operation data.

[0127] During the actual execution process, in the case of a rule-based abnormality detection algorithm, the actual winding temperature and the winding temperature alarm threshold can be compared at regular time intervals within the first target time length, and a fault alarm is issued each time it is determined that the actual winding temperature is greater than the winding temperature alarm threshold. The number of fault alarms within the first target time length is accumulated to obtain fault alarm information, so as to further determine whether the motor cooling is faulty based on the fault alarm information and the second target threshold.

[0128] According to the compressor fault diagnosis method provided in the embodiment of the present application, fault diagnosis is performed through the actual winding temperature and the winding temperature alarm threshold, which can effectively detect instantaneous faults or more serious faults.

[0129] 2. Determination of model-based anomaly detection algorithm

[0130] In some embodiments, performing a fault alarm based on a target anomaly detection algorithm may include:

[0131] Obtaining the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value; the predicted winding temperature rise value is obtained based on the winding temperature rise model;

[0132] When the absolute value of the difference is greater than the winding temperature rise alarm threshold, a fault alarm is issued.

[0133] In this embodiment, the motor cooling fault may be determined based on the actual winding temperature rise value and the winding temperature alarm threshold.

[0134] Among them, the predicted winding temperature rise value is obtained based on the winding temperature rise model.

[0135] The specific method for determining the predicted winding temperature rise value will be described in the following embodiments and will not be elaborated here.

[0136] Taking the actual winding temperature information as the actual winding temperature rise value and the first target threshold as the winding temperature rise alarm threshold as an example, the fault detection algorithm determines the condition 2 of the motor cooling fault at the current moment (such as every minute):

[0137] |ΔT MWT，a -ΔT MWT，m |>ΔT thr

[0138] Where, ΔT MwT，a is the actual winding temperature rise of the motor (unit: K / minute), ΔT MWT，m To predict the winding temperature rise (unit: K / minute), ΔT thr (Unit: K / minute) is the winding temperature rise alarm threshold. The threshold value is different for different units and will be learned through the unit operation data.

[0139] When the actual winding temperature information exceeds the first target threshold, a fault alarm is issued. The number of fault alarms FC and the proportion of fault alarms FCR in a day are defined. When condition 3 is met:

[0140] FC>FC thr

[0141] Among them, FC thr is the second target threshold;

[0142] Or, when condition 4 is met:

[0143] FCR>FCR thr

[0144] Among them, FC thr is the second target threshold; FCR is defined as the number of fault alarms in a day / the number of minutes of actual operation in a day (number of valid samples).

[0145] It is judged that the motor cooling failure occurred on that day.

[0146] The second target threshold can be based on user customization, for example, for the fault caused by condition 1, FC thr Can be set to 20, FCR thr Can be set to 0.1; for the fault caused by condition 2, FC thr Can be set to 5, FCR thr It can be set to 0.05. The specific value can be determined based on actual conditions and is not limited in this application.

[0147] In other embodiments, when the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value is greater than the winding temperature rise alarm threshold, a motor cooling fault is determined.

[0148] In this embodiment, when it is determined that the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value is greater than the winding temperature rise alarm threshold, a motor cooling fault can be directly determined.

[0149] According to the compressor fault diagnosis method provided in the embodiment of the present application, fault detection is performed through the actual winding temperature rise value and the predicted winding temperature rise value obtained based on model prediction. It is suitable for gradual fault detection, can achieve early prediction of faults, and the prediction result has high accuracy.

[0150] In the present application, by providing a variety of motor cooling fault determination methods, the best determination method can be selected based on actual conditions, which is applicable to any fault detection scenario and has high flexibility and universality.

[0151] It should be noted that, in the actual implementation process, any one of the above two methods for determining the motor cooling fault information can be selected for fault detection based on actual needs.

[0152] In other embodiments, the above two methods (rule-based anomaly detection algorithm and model-based anomaly detection algorithm) may be combined to perform fault detection.

[0153] like Figure 2As shown, in some embodiments, when the target abnormality detection algorithm is a model-based abnormality detection algorithm, determining a motor cooling fault based on the target abnormality detection algorithm may include:

[0154] Based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold, the motor cooling fault is determined; the predicted winding temperature rise value is obtained based on the winding temperature rise model.

[0155] In this embodiment, the actual winding temperature information may include: an actual winding temperature rise value and an actual winding temperature.

[0156] The first target threshold may include: a winding temperature rise alarm threshold and a winding temperature alarm threshold.

[0157] Continue to refer Figure 2 ,In the actual execution process, the threshold-based anomaly detection module is ,executed first, that is, the actual winding temperature is compared with the ,winding temperature alarm threshold to determine whether the winding temperature is abnormal.

[0158] When the winding temperature alarm threshold is lower than the actual winding temperature, the winding temperature is considered abnormal and a fault alarm is directly issued; and the motor cooling fault information is determined based on the fault alarm information.

[0159] When the winding temperature alarm threshold is not less than the actual winding temperature, it is impossible to directly determine whether the winding temperature is abnormal. In this case, the cooling fault information can be further determined based on the abnormality detection algorithm of the model, that is, based on the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value and the size relationship of the winding temperature rise alarm threshold, determine whether the motor cooling is faulty. The specific determination method has been explained in the above embodiment and will not be repeated here.

[0160] According to the compressor fault diagnosis method provided in the embodiment of the present application, by combining the rule-based abnormality detection algorithm and the model-based abnormality detection algorithm, when the rule-based abnormality detection algorithm diagnoses that the winding temperature is normal, the model-based abnormality detection algorithm is further used to diagnose whether the winding temperature rise is normal, so as to determine whether the motor cooling is faulty. On the basis of detecting instantaneous faults or more serious faults, it is possible to further detect gradual faults, thereby achieving early warning of faults. The method is suitable for any fault detection scenario, has high flexibility and universality, and can effectively improve the reliability and safety of the compressor motor operation.

[0161] In the case where a motor cooling fault is determined, the fault type of the compressor is further determined based on at least one of the power information and the pressure difference information of the motor.

[0162] Continue to refer Figure 2 In some embodiments, step 120 may include:

[0163] When the power information is greater than the first threshold, determining the fault type is an internal short circuit;

[0164] When the pressure difference information is less than the second threshold, the fault type is determined to be a pressure difference abnormality.

[0165] In this embodiment, the first threshold and the second threshold may be user-defined, or may be learned through unit operation data, which is not limited in this application.

[0166] The first threshold is the upper limit of the power percentage operating range. The thresholds are different for different units and can be learned through the unit operating data.

[0167] The second threshold is the upper limit of the pressure difference operating range. The thresholds are different for different units and can be obtained through training with unit operating data.

[0168] Continue to refer Figure 2 In some embodiments, determining the fault type of the compressor based on at least one of the power information and the pressure difference information of the motor may include:

[0169] When the power information is greater than the first threshold, determining the fault type is an internal short circuit;

[0170] When the power information is not greater than the first threshold and the pressure difference information is less than the second threshold, determining that the fault type is a pressure difference abnormality;

[0171] When the power information is not greater than the first threshold and the pressure difference information is not less than the second threshold, it is determined that the fault type is abnormal cooling flow.

[0172] For example, when condition 1 is met, condition 5 is also met:

[0173] P>P thr

[0174] Among them, P is the power information, P thr is the first threshold;

[0175] The fault type is judged to be internal short circuit.

[0176] For example, when condition 1 is met, condition 6 is also met:

[0177]

[0178] in, is the pressure difference information, p r,thr is the second threshold;

[0179] The fault type is judged to be too small pressure difference.

[0180] For another example, when condition 1 is met and conditions 5 and 6 are not met, the fault type is determined to be insufficient cooling flow.

[0181] In some embodiments, when condition 2 is met, the most likely type of fault can be further determined by analyzing the degree to which the current power percentage deviates from the normal range of power percentage and the degree to which the current pressure difference deviates from the normal range of pressure difference. The specific determination method is similar to that in the above embodiment and will not be elaborated in this application.

[0182] Step 130: Determine the fault level of the compressor based on the fault type.

[0183] In this step, after the fault type is obtained, corresponding parameters are selected based on the specific fault type to further determine the fault level.

[0184] In some embodiments, the fault levels may include: severe fault, moderate fault, and minor fault.

[0185] Of course, in other embodiments, the fault level may also be divided into other levels, such as level one and level two, etc. The specific division may be based on actual conditions and is not limited in this application.

[0186] In some embodiments, step 130 may include: when the fault type is an internal short circuit, determining the fault level based on at least one of actual winding temperature information and power information.

[0187] In this embodiment, when the fault type is an internal short circuit, the fault level can be further determined.

[0188] In the actual implementation process, a judgment threshold can be set to classify the fault levels.

[0189] In some embodiments, determining the fault level based on at least one of the power information and the actual winding temperature information may include:

[0190] When the actual winding temperature information is greater than the severe internal short circuit temperature threshold, or the power information is greater than the severe internal short circuit power percentage threshold, the fault level is determined to be a severe fault;

[0191] When the actual winding temperature information is greater than the moderate internal short circuit temperature threshold and not greater than the severe internal short circuit temperature threshold, or the power information is greater than the moderate internal short circuit power percentage threshold and not greater than the severe internal short circuit power percentage threshold, the fault level is determined to be a moderate fault;

[0192] When the actual winding temperature information is not greater than the moderate internal short circuit temperature threshold, and the power information is not greater than the moderate internal short circuit power percentage threshold, the fault level is determined to be a mild fault.

[0193] In this embodiment, when:

[0194] T MWT，a >T thr，H

[0195] or,

[0196] P MwT，a >P thr，H

[0197] The internal short circuit is judged to be a serious fault, where Tt hr，H is the severe internal short circuit temperature threshold, P thr，H It is the severe internal short circuit power percentage threshold.

[0198] When satisfied:

[0199] T MWT，a >T thr，M

[0200] or,

[0201] P MwT，a >P thr，M

[0202] The internal short circuit is judged to be a moderate fault, where T thr，M is the medium internal short circuit temperature threshold, P thr，M It is the moderate internal short circuit power percentage threshold.

[0203] Otherwise, the internal short circuit is judged to be a minor fault.

[0204] According to the compressor fault diagnosis method provided in the embodiment of the present application, the motor cooling fault is detected by measuring the actual winding temperature information, and the influence of the refrigerant flow rate and the ambient temperature is fully considered, and the detection precision and accuracy are high; on the basis of the motor cooling fault detection, the fault type is further diagnosed and the fault level is determined based on the fault type, which can provide effective guidance for post-fault operation and maintenance, and effectively improve the reliability and safety of the compressor motor operation.

[0205] The specific method for determining the predicted winding temperature rise value is described below.

[0206] In some embodiments, the predicted winding temperature rise value may be determined based on the following steps: inputting actual operating parameters of the compressor into a winding temperature rise model, and obtaining the predicted winding temperature rise value output by the temperature rise model.

[0207] In this embodiment, the actual operating parameters of the compressor may include, but are not limited to: actual compressor power, actual refrigerant outlet pressure, actual refrigerant inlet pressure, actual refrigerant outlet temperature, actual refrigerant inlet temperature, and the like.

[0208] The winding temperature rise model may be a pre-trained machine learning model, or may be other types of models, such as a physical model or a fitted polynomial model, etc., which is not limited in this application.

[0209] In some embodiments, when the winding temperature rise model is a machine learning model, the machine learning model is trained with training samples, wherein the training samples include sample winding temperature rise values, and sample compressor power, sample refrigerant outlet pressure, sample refrigerant inlet pressure, sample refrigerant inlet temperature, sample refrigerant outlet temperature, etc. corresponding to the sample winding temperature rise values.

[0210] In some embodiments, the winding temperature rise model can be expressed as: ΔT = f(P, p2, p1, T2, T1);

[0211] Among them, P is the compressor power, p2 is the refrigerant outlet pressure, p1 is the refrigerant inlet pressure, T2 is the refrigerant outlet temperature, and T1 is the refrigerant inlet temperature.

[0212] In some embodiments, the physical model may be represented as:

[0213] Among them, h2 is the refrigerant outlet enthalpy, which can be calculated by interpolation in the physical property table according to p2 and T2; h1 is the refrigerant inlet pressure enthalpy, which can be calculated by interpolation in the physical property table according to p1 and T1; Δt is the time interval of temperature rise ΔT; Q is the motor heat Q = P(1-η)k1; η is the compressor efficiency, and k1 can be fitted through operating data; is the cooling flow rate, ρ is the refrigerant density, r is the hydraulic radius of the orifice, and k2 can be fitted through operating data.

[0214] According to the compressor fault diagnosis method provided in the embodiment of the present application, by setting the winding temperature rise model to a fitting polynomial, a machine learning model or a physical model, the accuracy of different application scenarios can be met; the parameters of the winding temperature rise model are set to the power (or current) of the unit operation, the pressure and temperature of the refrigerant entering and leaving the motor, which are easy to obtain and do not require the installation of complex and expensive detection equipment, and the cost is low.

[0215] Continue to refer Figure 2 In some embodiments, inputting the actual operating parameters of the compressor into the winding temperature rise model to obtain the predicted winding temperature rise value output by the temperature rise model may include:

[0216] When the actual working parameters exceed the set values ​​and cover the minimum operating range of the unit, or the actual working parameters do not exceed the set values, do not cover the minimum operating range of the unit, do not exceed the range of the winding temperature rise model and the actual working parameters are within the valid grid, the actual working parameters are input into the winding temperature rise model to obtain the predicted winding temperature rise value.

[0217] Continue to refer Figure 2 In some embodiments, before determining the motor cooling fault based on the actual winding temperature rise value, the winding temperature rise alarm threshold and the predicted winding temperature rise value, the method may further include:

[0218] When the winding temperature rise model is not calibrated, the winding temperature rise model is calibrated based on the actual working parameters of the compressor;

[0219] When the winding temperature rise model has been calibrated and the training samples meet the target conditions, the winding temperature rise model is updated based on the training samples.

[0220] In this embodiment, the training samples may be sample data extracted from actual working parameters for model training.

[0221] The training samples include: sample winding temperature rise values, and sample compressor power corresponding to the sample winding temperature rise values, sample refrigerant outlet pressure, sample refrigerant inlet pressure, sample refrigerant outlet temperature and sample refrigerant inlet temperature, etc.

[0222] The target condition is used to determine whether the training sample can effectively train the winding temperature rise model.

[0223] In some embodiments, the target conditions may include at least one of: whether the data volume of the training sample exceeds a set value, whether the training sample covers the minimum operating range of the unit, whether the training sample exceeds the winding temperature rise model range, and whether the training sample is within a valid grid.

[0224] Continue to refer Figure 2 In some embodiments, when the winding temperature rise model has been calibrated and the training samples meet the target conditions, updating the winding temperature rise model based on the training samples may include:

[0225] When the data volume of the training samples does not exceed the set value, the training samples do not cover the minimum operating range of the unit, and the training samples exceed the range of the winding temperature rise model, the winding temperature rise model is updated based on the training samples;

[0226] When the data volume of the training samples does not exceed the set value, the training samples do not cover the minimum operating range of the unit, the training samples do not exceed the range of the winding temperature rise model, and the training samples are not within the valid grid, the winding temperature rise model is updated based on the training samples.

[0227] In this embodiment, during the actual execution process, the collected working parameters may be cleaned first to remove data without physical meaning to obtain actual winding temperature information; then a threshold-based abnormality detection module is executed, which compares the actual winding temperature with the winding temperature alarm threshold to determine whether the winding temperature is abnormal;

[0228] If the winding temperature detection is abnormal, the motor cooling fault is determined, and the fault isolation module is further executed to analyze the most likely cause of the fault (internal short circuit, abnormal pressure difference or abnormal cooling flow);

[0229] If it is an internal short circuit, the fault identification module is further executed to analyze the severity of the internal short circuit (mild, moderate or severe).

[0230] If the winding temperature detection is normal, it is determined whether there is a calibrated winding temperature rise model.

[0231] If there is no calibrated winding temperature rise model, the acquired actual operating parameters are used to calibrate the winding temperature rise model, and the adaptive threshold value of the winding temperature is updated.

[0232] Continue to refer Figure 2 , if a calibrated winding temperature rise model already exists, determine whether the model needs to be updated;

[0233] When the accumulated training data volume does not reach the set value or the accumulated training data volume reaches the set value but does not cover the minimum operating range of the unit, and the current collected data range exceeds the model range or the current collected data is not within the effective range of the model, the winding temperature rise model is updated;

[0234] If the updated model fitting error is too large, the update fails, otherwise the update succeeds.

[0235] If a calibrated winding temperature rise model already exists and the model does not need to be updated, the model-based anomaly detection module is executed, which compares the actual winding temperature rise value with the predicted winding temperature rise value predicted by the model to determine whether the winding temperature rise is abnormal.

[0236] If the winding temperature rise detection is abnormal, the motor cooling fault is determined, and the fault isolation module is further executed to analyze the most likely cause of the fault (internal short circuit, abnormal voltage difference or abnormal cooling flow);

[0237] If it is an internal short circuit, the fault identification module is further executed to analyze the severity of the internal short circuit (mild, moderate or severe); otherwise, the motor cooling function is determined to be normal, the processing of the current operating data is exited, and the processing of the next batch of operating data is waited for.

[0238] According to the compressor fault diagnosis method provided in the embodiment of the present application, the working parameters of the unit are calibrated online and the winding temperature rise model is updated online and automatically, without the need for manual settings, and has good versatility.

[0239] The compressor fault diagnosis method provided in the embodiment of the present application can be executed by a compressor fault diagnosis device. The compressor fault diagnosis method is executed by the compressor fault diagnosis device in the embodiment of the present application as an example to illustrate the compressor fault diagnosis device provided in the embodiment of the present application.

[0240] An embodiment of the present application also provides a compressor fault diagnosis device.

[0241] like Figure 3 As shown, the compressor fault diagnosis device includes: a first processing module 310 , a second processing module 320 and a third processing module 330 .

[0242] A first processing module 310 is used to obtain actual winding temperature information of a motor in a compressor and a first target threshold;

[0243] A second processing module 320 is used to determine the fault type of the compressor based on at least one of the power information and the pressure difference information of the motor when the motor cooling fault is determined based on the actual winding temperature information and the first target threshold;

[0244] The third processing module 330 is used to determine the fault level of the compressor based on the fault type.

[0245] According to the compressor fault diagnosis device provided in the embodiment of the present application, the motor cooling fault is detected by measuring the actual winding temperature information, and the influence of the refrigerant flow rate and the ambient temperature is fully considered, and the detection precision and accuracy are high; on the basis of the motor cooling fault detection, the fault type is further diagnosed and the fault level is determined based on the fault type, which can provide effective guidance for post-fault operation and maintenance, and effectively improve the reliability and safety of the compressor motor operation.

[0246] In some embodiments, the apparatus may further include a fourth processing module, configured to:

[0247] Based on the actual winding temperature information and the first target threshold, a target abnormality detection algorithm is determined; the target abnormality detection algorithm is a rule-based abnormality detection algorithm or a model-based abnormality detection algorithm;

[0248] Based on the targeted anomaly detection algorithm, motor cooling faults are identified.

[0249] In some embodiments, the actual winding temperature information includes the actual winding temperature, and the first target threshold includes a winding temperature alarm threshold; the fourth processing module may also be used to:

[0250] When the actual winding temperature is greater than the winding temperature alarm threshold, determining the target anomaly detection algorithm to be a rule-based anomaly detection algorithm;

[0251] When the actual winding temperature is not greater than the winding temperature alarm threshold, the target abnormality detection algorithm is determined to be a model-based abnormality detection algorithm.

[0252] In some embodiments, the fourth processing module may also be used to:

[0253] In the case of fault alarm based on the target anomaly detection algorithm, the fault alarm information is determined based on the number of fault alarms;

[0254] When the fault alarm information is greater than the second target threshold, a motor cooling fault is determined.

[0255] In some embodiments, the actual winding temperature information includes at least one of the actual winding temperature and the actual winding temperature rise value, and the first target threshold includes at least one of the winding temperature alarm threshold and the winding temperature rise alarm threshold; the fourth processing module can also be used to:

[0256] When the actual winding temperature is greater than the winding temperature alarm threshold, a fault alarm is issued;

[0257] When the target abnormality detection algorithm is a model-based abnormality detection algorithm, the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value is obtained; the predicted winding temperature rise value is obtained based on the winding temperature rise model;

[0258] When the absolute value of the difference is greater than the winding temperature rise alarm threshold, a fault alarm is issued.

[0259] In some embodiments, the fourth processing module can also be used to: when the target abnormality detection algorithm is a model-based abnormality detection algorithm, determine the motor cooling fault based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold; the predicted winding temperature rise value is obtained based on the winding temperature rise model.

[0260] In some embodiments, the fourth processing module may also be used to: determine a motor cooling fault when the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value is greater than the winding temperature rise alarm threshold.

[0261] In some embodiments, the second processing module 320 may also be used to:

[0262] When the power information is greater than the first threshold, determining the fault type is an internal short circuit;

[0263] When the pressure difference information is less than the second threshold, the fault type is determined to be a pressure difference abnormality.

[0264] In some embodiments, the third processing module 330 may also be used to: when the fault type is an internal short circuit, determine the fault level based on at least one of the actual winding temperature information and the power information.

[0265] In some embodiments, the third processing module 330 may also be used to:

[0266] When the actual winding temperature information is greater than the severe internal short circuit temperature threshold, or the power information is greater than the severe internal short circuit power percentage threshold, the fault level is determined to be a severe fault;

[0267] When the actual winding temperature information is greater than the moderate internal short circuit temperature threshold and not greater than the severe internal short circuit temperature threshold, or the power information is greater than the moderate internal short circuit power percentage threshold and not greater than the severe internal short circuit power percentage threshold, the fault level is determined to be a moderate fault;

[0268] When the actual winding temperature information is not greater than the moderate internal short circuit temperature threshold, and the power information is not greater than the moderate internal short circuit power percentage threshold, the fault level is determined to be a mild fault.

[0269] In some embodiments, the apparatus may further include a fifth processing module, configured to:

[0270] Input the actual operating parameters of the compressor into the winding temperature rise model to obtain the predicted winding temperature rise value output by the temperature rise model;

[0271] Among them, the winding temperature rise model includes a fitting polynomial model, a machine learning model or a physical model, and the actual working parameters include at least one of the actual compressor power, the actual refrigerant outlet pressure, the actual refrigerant inlet pressure, the actual refrigerant outlet temperature and the actual refrigerant inlet temperature.

[0272] In some embodiments, the apparatus may further include:

[0273] a sixth processing module, configured to calibrate the winding temperature rise model based on actual operating parameters of the compressor before determining the motor cooling fault information based on the actual winding temperature rise value, the winding temperature rise alarm threshold and the predicted winding temperature rise value, if the winding temperature rise model is not calibrated;

[0274] The seventh processing module is used to update the winding temperature rise model based on the training samples before determining the motor cooling fault information based on the actual winding temperature rise value, the winding temperature rise alarm threshold and the predicted winding temperature rise value, when the winding temperature rise model has been calibrated and the training samples meet the target conditions, and the training samples are obtained from the actual working parameters.

[0275] The compressor fault diagnosis device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0276] The compressor fault diagnosis device provided in the embodiment of the present application can achieve Figure 1 to Figure 2 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0277] The embodiment of the present application also provides a chiller.

[0278] like Figure 4 As shown, the chiller includes: a compressor, a motor and a compressor fault diagnosis device as described in any of the above embodiments.

[0279] Wherein, the motor is connected with the compressor.

[0280] The compressor fault diagnosis device is electrically connected to the compressor and the motor respectively, and is used to execute the compressor fault diagnosis method as described in any of the above embodiments.

[0281] According to the chiller provided in the embodiment of the present application, the motor cooling fault is detected by measuring the actual winding temperature information, and the influence of the refrigerant flow rate and the ambient temperature is fully considered, and the detection precision and accuracy are high; on the basis of the motor cooling fault detection, the fault type is further diagnosed and the fault level is determined based on the fault type, which can provide effective guidance for post-fault operation and maintenance, effectively improve the reliability and safety of the compressor motor operation, thereby improving the reliability and safety of the chiller operation.

[0282] Continue to refer Figure 4 In some embodiments, the chiller may further include a perforated plate.

[0283] An embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned compressor fault diagnosis method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0284] The processor is the processor in the chiller described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0285] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned compressor fault diagnosis method when executed by a processor.

[0286] The processor is the processor in the chiller described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0287] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned compressor fault diagnosis method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0288] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0289] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0290] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0291] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0292] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0293] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A compressor fault diagnosis method, characterized in that: include: Acquiring actual winding temperature information and a first target threshold value of a motor in a compressor; In the case where a motor cooling fault is determined based on the actual winding temperature information and the first target threshold, determining a fault type of the compressor based on at least one of power information and pressure difference information of the motor; Based on the fault type, a fault level of the compressor is determined.

2. The compressor fault diagnosis method according to claim 1, characterized in that: The determining of a motor cooling fault based on the actual winding temperature information and the first target threshold comprises: Based on the actual winding temperature information and the first target threshold, determining a target abnormality detection algorithm; the target abnormality detection algorithm is a rule-based abnormality detection algorithm or a model-based abnormality detection algorithm; Based on the target abnormality detection algorithm, the motor cooling fault is determined.

3. The compressor fault diagnosis method according to claim 2, characterized in that: The actual winding temperature information includes an actual winding temperature, and the first target threshold includes a winding temperature alarm threshold; and determining a target abnormality detection algorithm based on the actual winding temperature information and the first target threshold includes: In a case where the actual winding temperature is greater than the winding temperature alarm threshold, determining that the target abnormality detection algorithm is the rule-based abnormality detection algorithm; When the actual winding temperature is not greater than the winding temperature alarm threshold, the target abnormality detection algorithm is determined to be the model-based abnormality detection algorithm.

4. The compressor fault diagnosis method according to claim 2, characterized in that: The determining the motor cooling fault based on the target abnormality detection algorithm includes: In the case of performing a fault alarm based on the target abnormality detection algorithm, determining the fault alarm information based on the number of fault alarms; When the fault alarm information is greater than the second target threshold, the motor cooling fault is determined.

5. The compressor fault diagnosis method according to claim 4, characterized in that: The actual winding temperature information includes at least one of the actual winding temperature and the actual winding temperature rise value, and the first target threshold includes at least one of the winding temperature alarm threshold and the winding temperature rise alarm threshold; Performing a fault alarm based on the target anomaly detection algorithm includes: When the actual winding temperature is greater than the winding temperature alarm threshold, a fault alarm is issued; In the case where the target abnormality detection algorithm is the model-based abnormality detection algorithm, obtaining an absolute value of a difference between the actual winding temperature rise value and the predicted winding temperature rise value; the predicted winding temperature rise value is obtained based on a winding temperature rise model; When the absolute value of the difference is greater than the winding temperature rise alarm threshold, a fault alarm is issued.

6. The compressor fault diagnosis method according to claim 2, characterized in that: In a case where the target abnormality detection algorithm is the model-based abnormality detection algorithm, determining the motor cooling fault based on the target abnormality detection algorithm includes: The motor cooling fault is determined based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold; the predicted winding temperature rise value is obtained based on a winding temperature rise model.

7. The compressor fault diagnosis method according to claim 6, characterized in that: The determining the motor cooling fault based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold comprises: When the absolute value of the difference between the actual winding temperature rise value and the predicted winding temperature rise value is greater than the winding temperature rise alarm threshold, the motor cooling fault is determined.

8. The compressor fault diagnosis method according to claim 6, characterized in that: The predicted winding temperature rise value is determined based on the following steps: Inputting the actual operating parameters of the compressor into a winding temperature rise model to obtain the predicted winding temperature rise value output by the temperature rise model; Among them, the winding temperature rise model includes a fitting polynomial model, a machine learning model or a physical model, and the actual working parameters include at least one of the actual compressor power, the actual refrigerant outlet pressure, the actual refrigerant inlet pressure, the actual refrigerant outlet temperature and the actual refrigerant inlet temperature.

9. The compressor fault diagnosis method according to claim 6, characterized in that: Before determining the motor cooling fault based on the actual winding temperature rise value, the predicted winding temperature rise value and the winding temperature rise alarm threshold, the method further includes: When the winding temperature rise model is not calibrated, calibrating the winding temperature rise model based on actual operating parameters of the compressor; When the winding temperature rise model has been calibrated and the training samples meet the target conditions, the winding temperature rise model is updated based on the training samples, and the training samples are obtained from the actual working parameters.

10. The compressor fault diagnosis method according to any one of claims 1 to 9, characterized in that: The determining the fault type of the compressor based on at least one of the power information and the pressure difference information of the motor includes: When the power information is greater than a first threshold, determining that the fault type is an internal short circuit; When the pressure difference information is less than a second threshold, the fault type is determined to be a pressure difference abnormality.

11. The compressor fault diagnosis method according to any one of claims 1 to 9, characterized in that: The determining the fault type of the compressor based on at least one of the power information and the pressure difference information of the motor comprises: when the power information is greater than a first threshold, determining that the fault type is an internal short circuit; When the power information is not greater than the first threshold and the pressure difference information is less than a second threshold, determining that the fault type is a pressure difference abnormality; When the power information is not greater than the first threshold and the pressure difference information is not less than the second threshold, it is determined that the fault type is abnormal cooling flow.

12. The compressor fault diagnosis method according to any one of claims 1 to 9, characterized in that: The determining the fault level of the compressor based on the fault type includes: When the fault type is an internal short circuit, the fault level is determined based on at least one of the actual winding temperature information and the power information.

13. The compressor fault diagnosis method according to claim 12, characterized in that: The determining the fault level based on at least one of the actual winding temperature information and the power information comprises: When the actual winding temperature information is greater than a severe internal short circuit temperature threshold, or the power information is greater than a severe internal short circuit power percentage threshold, determining that the fault level is a severe fault; When the actual winding temperature information is greater than the moderate internal short-circuit temperature threshold and not greater than the severe internal short-circuit temperature threshold, or the power information is greater than the moderate internal short-circuit power percentage threshold and not greater than the severe internal short-circuit power percentage threshold, the fault level is determined to be a moderate fault; When the actual winding temperature information is not greater than the moderate internal short-circuit temperature threshold, and the power information is not greater than the moderate internal short-circuit power percentage threshold, the fault level is determined to be a mild fault.

14. A compressor fault diagnosis device, characterized in that: include: A first processing module, used for obtaining actual winding temperature information of a motor in the compressor and a first target threshold; a second processing module, configured to determine a fault type of the compressor based on at least one of power information and pressure difference information of the motor, when a motor cooling fault is determined based on the actual winding temperature information and the first target threshold; The third processing module is used to determine the fault level of the compressor based on the fault type.

15. A chiller, characterized in that: include: compressor; a motor connected to the compressor; The compressor fault diagnosis device as claimed in claim 14, wherein the compressor fault diagnosis device is electrically connected to the compressor and the motor, respectively.

16. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the compressor fault diagnosis method according to any one of claims 1 to 13 is implemented.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the fault diagnosis method for the compressor as described in any one of claims 1-13 is implemented.

Images