Compressor fault tree construction method and device, compressor fault tree display method and device and related equipment

Abstract

The invention discloses a compressor fault tree construction method, a compressor fault tree display method, a compressor fault tree construction device, a compressor fault tree display device and related equipment, relates to the technical field of compressor fault detection, and aims to at least solve the limitation of less fault data volume in the use process of industrial equipment in related technologies. And therefore, the fault identification capability of a related machine algorithm is limited, and the accuracy of an identification result is poor. The method comprises the steps that the influence of pneumatic data on compressor performance degradation is analyzed, and the first fault probability of each first fault event is obtained; according to the association relationship between the characteristic value of the high-frequency data and the probability of occurrence of the second fault event, obtaining the second fault probability of each second fault event; and determining a target logic association relationship between each first fault event and each second fault event from the fault tree, and correspondingly associating and storing the target logic association relationship with the first fault probability and the second fault probability in the fault tree.

Description

Technical Field

[0001] The present application relates to the technical field of compressor fault detection, and in particular to a compressor fault tree construction method, display method, device and related equipment. Background Art

[0002] With the development of industrial technology, compressors, as high-speed rotating equipment, have very high requirements for manufacturing, installation, use and maintenance. Problems in any link may cause the compressor to fail. The resulting losses are not only the loss of profits caused by unplanned downtime, but may even cause environmental and personal safety problems. Therefore, it is necessary to diagnose compressor faults in order to provide early warning of industrial equipment failures to avoid accidents. The commonly used method for compressor fault diagnosis is to identify equipment faults based on a fault recognition model trained with a machine learning algorithm. However, due to the small amount of fault data during the use of industrial equipment, the fault recognition model trained by the above machine algorithm has limited fault recognition capabilities and poor accuracy of the recognition results. Summary of the invention

[0003] The present invention provides a compressor fault tree construction method, display method, device and related equipment to at least solve the technical problem in the related art that the fault identification model obtained by the training of the related machine algorithm has limited fault identification ability and poor identification result accuracy due to the limitation of the small amount of fault data during the use of industrial equipment. The technical solution of the present invention is as follows:

[0004] According to a first aspect of an embodiment of the present invention, a method for constructing a compressor fault tree is provided, which is applied to a cloud server that is communicatively connected to the compressor, and the method includes: acquiring pneumatic data and high-frequency data of the compressor; the high-frequency data represents shaft displacement data of a vibration signal, including time domain characteristic data and frequency domain characteristic data of the vibration signal; analyzing the effect of the pneumatic data on the performance degradation of the compressor to obtain a first fault probability of each first fault event; and, based on the correlation between the characteristic value of the high-frequency data and the probability of the occurrence of a second fault event, obtaining a second fault probability of each second fault event; from a fault tree that constitutes a causal logical relationship of multiple fault events, determining a target logical correlation relationship between each first fault event and each second fault event, and storing the target logical correlation relationship in the fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event.

[0005] The multiple fault events in the fault tree include respective first fault events and respective second fault events.

[0006] The compressor mentioned above may be a centrifugal compressor.

[0007] Pneumatic data is also called process data, and high-frequency data is also called vibration data. Pneumatic data includes temperature, pressure, flow rate, valve opening, etc.

[0008] Each data dimension in the above pneumatic data is associated with a first fault event. Specifically, the first fault event associated with temperature, pressure, flow and valve opening can be equipment performance degradation, pipeline blockage, pipeline leakage, impeller damage and other fault events.

[0009] The second fault event includes different fault events corresponding to feature values ​​of feature dimensions of different high-frequency data.

[0010] In one possible implementation, the effect of pneumatic data on compressor performance degradation is analyzed to obtain a first failure probability of each first failure event, including: determining each first failure event and a first performance indicator of the compressor based on each outlet temperature, each inlet temperature, each outlet pressure, and each inlet pressure of the compressor in the pneumatic data; predicting the performance indicator of the compressor in a fault-free state using the rotation speed and flow rate of the compressor in the pneumatic data to obtain a second performance indicator; and determining the first failure probability of each first failure event according to the indicator difference between the second performance indicator and the first performance indicator.

[0011] In another possible implementation, each first fault event is determined based on each outlet temperature, each inlet temperature, each outlet pressure and each inlet pressure of the compressor in the pneumatic data, including: based on the parameter differences between each outlet temperature, each inlet temperature, each outlet pressure and each inlet pressure and the corresponding aerodynamic parameter threshold value exceeding the corresponding preset parameter threshold value, determining each first fault event represented by the pneumatic data.

[0012] In another possible implementation, the first fault probability of each first fault event is determined according to the indicator difference between the second performance indicator and the first performance indicator, including: obtaining multiple first standard performance indicators corresponding to each data dimension consistent with the data dimension of each first fault event in the pneumatic data under normal operation of the compressor, and determining the first standard deviation of the multiple first standard performance indicators and the corresponding first standard performance threshold; constructing a first mapping relationship between the characterization indicator difference and the first fault probability based on the first standard deviation and the corresponding first standard performance threshold to obtain the first fault probability.

[0013] In another possible implementation, a second fault probability of each second fault event is obtained based on a correlation between a characteristic value of the high-frequency data and a probability of a second fault event occurring, including: determining each second fault event represented by the high-frequency data based on a mapping relationship between each characteristic value of the high-frequency data and different types of second fault events; obtaining a plurality of standard characteristic values ​​corresponding to each data dimension consistent with the data dimension of each second fault event in the high-frequency data under normal operation of the compressor, and determining a second standard deviation of the plurality of standard characteristic values ​​and a corresponding second standard performance threshold; constructing a second mapping relationship between the characteristic value and the second fault probability based on the second standard deviation and the corresponding second standard performance threshold to obtain the second fault probability of each second fault event.

[0014] In another possible implementation, obtaining the pneumatic data and high-frequency data of the compressor includes: sending a data acquisition instruction to the requesting-end device according to a preset period; the data acquisition instruction is used to instruct the requesting-end device to send the pneumatic data and high-frequency data of the compressor to the cloud server, so that the cloud server obtains the pneumatic data and high-frequency data of the compressor; wherein, during the process of the requesting-end device sending the pneumatic data and high-frequency data of the compressor to the cloud server, when it is detected that the amount of data sent exceeds a quantity threshold, the data transmission speed is increased according to a preset speed increase rule; wherein the requesting-end device includes a terminal device or a compressor of the compressor.

[0015] In another possible implementation, after the target logical association relationship is stored in a fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event, the method further includes: receiving a display request for displaying the fault tree sent by a requesting end device, identifying the target logical association relationship, each first fault event and the corresponding first fault probability, each second fault event and the corresponding second fault probability in the fault tree, and sending them to the requesting end device, the requesting end device including a terminal device or a compressor of the compressor.

[0016] According to a second aspect of an embodiment of the present invention, a compressor fault tree display method is provided, which is applied to a terminal device or a compressor including a compressor, and the terminal device or the compressor is communicatively connected to a cloud server to exchange information with each other, and the method comprises: sending a display request for displaying a fault tree to the cloud server communicatively connected to the compressor, and displaying the target logical association relationship identified in the fault tree, each first fault event and the corresponding first fault probability, each second fault event and the corresponding second fault probability in the form of a fault tree, wherein the fault tree cloud server is constructed according to the compressor fault tree construction method such as the first aspect and any possible implementation thereof; in response to a user's configuration request, changing the fault events and logical association relationships of the fault tree according to the configuration request; wherein changing the fault events and logical association relationships of the fault tree comprises one or more of the following: adding fault events and logical association relationships of the fault tree, modifying the fault events and logical association relationships of the fault tree, and deleting the fault events and logical association relationships of the fault tree.

[0017] According to a third aspect of an embodiment of the present invention, a compressor fault tree construction device is provided, which is applied to a cloud server communicatively connected to the compressor, and the device includes: an acquisition unit for acquiring pneumatic data and high-frequency data of the compressor; the high-frequency data represents shaft displacement data of a vibration signal, including time domain characteristic data and frequency domain characteristic data of the vibration signal; an analysis unit for analyzing the influence of the pneumatic data on the performance degradation of the compressor to obtain a first fault probability of each first fault event; and, based on the correlation between the characteristic value of the high-frequency data and the probability of the occurrence of a second fault event, obtaining a second fault probability of each second fault event; a construction unit for determining a target logical association relationship between each first fault event and each second fault event from a fault tree constituting a causal logical relationship of multiple fault events, and storing the target logical association relationship in the fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event.

[0018] According to a fourth aspect of an embodiment of the present invention, a compressor fault tree display device is provided, which is applied to a terminal device or a compressor including a compressor, and the device includes: a display unit, which is used to send a display request for displaying a fault tree to a cloud server that is communicatively connected to the compressor, and display the target logical association relationship identified in the fault tree returned by the received cloud server, each first fault event and the corresponding first fault probability, each second fault event and the corresponding second fault probability in the form of a fault tree, wherein the fault tree cloud server is constructed according to the compressor fault tree construction method such as the first aspect and any possible implementation method thereof; a configuration unit is used to, in response to a user's configuration request, change the fault events and logical association relationships of the fault tree according to the configuration request, and changing the fault events and logical association relationships of the fault tree includes one or more of the following: adding fault events and logical association relationships of the fault tree, modifying fault events and logical association relationships of the fault tree, and deleting fault events and logical association relationships of the fault tree.

[0019] According to a fourth aspect of an embodiment of the present invention, a compressor is provided, which is communicatively connected to a cloud server, the cloud server is used to execute the compressor fault tree construction method such as the first aspect and any possible implementation thereof, and the compressor is used to execute the compressor fault tree display method such as the second aspect and any possible implementation thereof.

[0020] According to a fifth aspect of an embodiment of the present invention, a device terminal is provided, which includes a compressor and is communicatively connected to a cloud server, the cloud server being used to execute a compressor fault tree construction method as described in the first aspect and any possible implementation thereof, and the compressor being used to execute a compressor fault tree display method as described in the second aspect and any possible implementation thereof.

[0021] According to a sixth aspect of an embodiment of the present invention, a compressor fault detection system is provided, the compressor fault detection system comprising a compressor and a cloud server, the compressor being communicatively connected to the cloud server, the cloud server being used to execute the compressor fault tree construction method as described in the first aspect and any possible implementation thereof, and the compressor being used to execute the compressor fault tree display method as described in the second aspect and any possible implementation thereof.

[0022] According to the seventh aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a processor of a medical device, the medical device is enabled to execute a compressor fault tree construction method such as the first aspect and any possible implementation thereof.

[0023] According to an eighth aspect of an embodiment of the present application, a computer program product is provided, the computer program product comprising computer instructions. When the computer instructions are executed on a compressor fault detection system, the compressor fault detection system executes the compressor fault tree construction method of the first aspect and any possible implementation thereof.

[0024] The technical solution provided by the embodiment of the present invention brings at least the following beneficial effects: multiple fault events of different fault types including each first fault event and each second fault event are constructed in a fault tree according to a causal logical relationship. Based on the data characteristics of the pneumatic data and high-frequency data of the compressor, each first fault event, each second fault event and the fault probability of each fault event represented by different data dimensions are obtained respectively. At the same time, the obtained fault probabilities of each first fault event and each second fault event are associated and stored in the above-constructed fault tree, so that the fault tree can directly display the target causal relationship between each first fault event and each second fault event and the fault probability of each fault event. The above-mentioned directly based on the different feature dimensions represented by different data can accurately determine the occurrence probability of different fault events and each fault event.

[0025] In the above-mentioned method for determining the fault probability, the fault event and the fault probability are determined based on the characteristic properties of the data and the correlation between the fault event and the fault probability. It is not limited by the small amount of fault data during the use of industrial equipment, and its fault detection results are more accurate. At the same time, the control logic between its fault events and the corresponding fault probability are associated and stored in the form of a fault tree, so as to facilitate a more intuitive display of the fault result data such as the control logic between the fault events and the corresponding fault probability obtained during the fault detection process.

[0026] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0028] Figure 1 is a schematic diagram of a compressor fault detection system according to an exemplary embodiment;

[0029] Figure 2 is a flow chart showing a method for constructing a compressor fault tree according to an exemplary embodiment;

[0030] Figure 3 is a schematic diagram of a waveform spectrum of high-frequency data according to an exemplary embodiment;

[0031] Figure 4 is a schematic diagram of an axis trajectory of high-frequency data according to an exemplary embodiment;

[0032] Figure 5 is a schematic diagram showing a high frequency data and its characteristic value and the probability of a second fault event according to an exemplary embodiment;

[0033] Figure 6 is a flow chart of a compressor fault tree display method according to an exemplary embodiment;

[0034] Figure 7 is a schematic diagram of a fault tree configuration page according to an exemplary embodiment;

[0035] Figure 8 is a schematic diagram of a fault tree on a configuration page according to an exemplary embodiment;

[0036] Fig. 9 is a block diagram of a compressor fault tree construction device according to an exemplary embodiment;

[0037] Fig.10 is a block diagram of a compressor fault tree display device according to an exemplary embodiment;

[0038] Fig.11 It is a schematic diagram of a device terminal according to an exemplary embodiment. DETAILED DESCRIPTION

[0039] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0041] In addition, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0042] Before introducing in detail the compressor fault tree construction method provided in the embodiment of the present application, a brief introduction is first given to the application scenarios and implementation framework involved in the embodiment of the present application.

[0043] First, the application scenarios of the embodiments of the present application are described below.

[0044] The compressor is a high-end power equipment that relies on a rotating impeller to work on the gas and converts the velocity energy of the gas into pressure energy through a diffuser. It is known as the "heart of industry" and is widely used in important fields such as energy, chemical industry, metallurgy, electric power, environmental protection, air separation, and national defense.

[0045] With the development of industrial technology, compressors, as high-speed rotating equipment, have very high requirements for manufacturing, installation, use and maintenance. Problems in any link may cause the compressor to fail. The resulting losses are not only the loss of profits caused by unplanned downtime, but may even cause environmental and personal safety problems. Therefore, it is necessary to diagnose compressor faults in order to provide early warning of industrial equipment failures to avoid accidents. The commonly used method for compressor fault diagnosis is to identify equipment faults based on a fault recognition model trained with a machine learning algorithm. However, due to the small amount of fault data during the use of industrial equipment, the fault recognition model trained by the above machine algorithm has limited fault recognition capabilities and poor accuracy of the recognition results.

[0046] Industrial equipment fault diagnosis has developed into a mature theoretical system, and the diagnostic content varies for different equipment. As a high-speed rotating device, the centrifugal compressor's shaft, impeller, bearings, couplings, gears, seals and guide vanes are key monitoring components. The lubrication system can ensure the continuous and stable operation of the rotor in the bearing, and it is also a necessary monitoring content. Rotating stall and surge, two unsteady working conditions, will cause abnormal vibration of the rotor, which also needs to be avoided. There are more or less some methods to monitor the above content.

[0047] Research has found that expert systems are based on expert knowledge, data, or a combination of the two. The basic components of a typical expert system include: knowledge base, reasoning system, user interface, knowledge acquisition part, and reasoning interpreter. In an expert system, reasoning is to draw corresponding conclusions based on existing knowledge and input problems.

[0048] Bayesian network is a probabilistic network that combines graph theory and probability theory. It is an expert system model based on machine learning. Bayesian probabilistic logic can be used for reasoning. Bayesian probabilistic logic realizes reasoning about uncertainty by updating the posterior probability based on prior probability and new evidence. By calculating probabilities and conditional probabilities, various possible conclusions can be obtained. The expert system analysis method based on the fault tree is a method of deducing the causes of the fault from the whole to the part in a tree-like graph step by step. First, analyze the causes of the system failure and draw an accident tree according to the causal logic relationship. Then deduce the fault from the whole to the part in a tree-like graph step by step to determine the cause of the fault and its probability of occurrence.

[0049] Based on this, the present application provides a method for constructing a compressor fault tree, which constructs multiple fault events of different fault types including each first fault event and each second fault event in a fault tree according to a causal logical relationship. Based on the data characteristics of the pneumatic data and high-frequency data of the compressor, each first fault event, each second fault event and the fault probability of each fault event represented by different data dimensions are obtained respectively. At the same time, the obtained fault probabilities of each first fault event and each second fault event are associated and stored in the above-constructed fault tree, so that the fault tree can directly display the target causal relationship between each first fault event and each second fault event and the fault probability of each fault event. The above-mentioned characteristics directly represented by different data are different in dimensions, and the occurrence probability of different fault events and each fault event can be accurately determined.

[0050] In the above-mentioned method for determining the fault probability, the fault event and the fault probability are determined based on the characteristic properties of the data and the correlation between the fault event and the fault probability. It is not limited by the small amount of fault data during the use of industrial equipment, and its fault detection results are more accurate. At the same time, the control logic between its fault events and the corresponding fault probability are associated and stored in the form of a fault tree, so as to facilitate a more intuitive display of the fault result data such as the control logic between the fault events and the corresponding fault probability obtained during the fault detection process.

[0051] Secondly, the implementation architecture involved in this application is briefly introduced below.

[0052] Figure 1 Schematic diagram of a compressor fault detection system provided by the present application. The compressor fault detection system comprises a compressor 11 and a cloud server 12, wherein the compressor 11 is communicatively connected with the cloud server 12 so that information can be exchanged between the compressor 11 and the cloud server 12.

[0053] As an implementation mode, the cloud server 12 is in communication connection with a plurality of compressors 11, and at least one edge server 13 is correspondingly provided for each compressor 11. At least one edge server 13 performs data processing operations such as clustering, classification and calculation on the pneumatic data and high-frequency data from the corresponding compressor 11, and obtains data of each characteristic dimension respectively included in the pneumatic data and the high-frequency data, as well as data characteristic values ​​that require data calculation and conversion. At least one edge server 13 transmits the processed pneumatic data and high-frequency data to the cloud server 12, so that the cloud server 12 executes the compressor fault tree construction method to construct a fault tree. The compressor 11 or a terminal device including the compressor 11 obtains the control logic and corresponding fault probability between the fault events represented by the current pneumatic data and the high-frequency data in the fault tree from the cloud server 12, so that the compressor 11 or a terminal device including the compressor 11 displays the current compressor fault condition in the form of a fault tree.

[0054] The compressor fault tree construction method provided in the embodiment of the present application can be applied to the above compressor fault detection system. For ease of understanding, the compressor fault tree construction method provided in the present application is specifically introduced below in conjunction with the accompanying drawings.

[0055] Figure 2 is a flow chart of a method for constructing a compressor fault tree according to an exemplary embodiment. Figure 2 As shown, the compressor fault tree construction method includes the following steps.

[0056] S21, obtaining the pneumatic data and high-frequency data of the compressor.

[0057] The high-frequency data represents the shaft displacement data of the vibration signal, including the time domain characteristic data and the frequency domain characteristic data of the vibration signal.

[0058] The compressor mentioned above may be a centrifugal compressor.

[0059] Pneumatic data is also called process data, and high-frequency data is also called vibration data.

[0060] Among them, pneumatic data includes temperature, pressure, flow and valve opening, etc.

[0061] Specifically, pneumatic data includes temperature, pressure, flow, valve opening, etc., and its sampling frequency is generally around 1 Hz. High-frequency data generally refers to shaft displacement data, and a single sensor will collect thousands of points per second. Centrifugal compressors are generally equipped with 6 eddy current sensors, two of which are arranged at the drive end, perpendicular to the shaft and 90° to each other, to monitor the lateral displacement of the shaft drive end. Similarly, two sensors are arranged at the free end, perpendicular to the shaft and 90° to each other, to monitor the lateral displacement of the shaft free end. One sensor monitors axial displacement, and one sensor collects key phase data. Among them, the waveform spectrum and axis trajectory of the high-frequency data corresponding to the drive end shaft displacement are as follows: Figure 3 The waveform spectrum diagram of the high-frequency data shown in Figure 4 The schematic diagram of the axis trajectory of the high-frequency data is shown. In addition, the characteristic values ​​calculated based on the high-frequency data waveform and spectrum, where the rotation speed is calculated from the key phase data, the pressure peak and valley values ​​are calculated from the high-frequency pressure signal, and the time domain characteristic data and the frequency domain characteristic data correspond to the lateral displacement signal and the axial displacement signal. The high-frequency data is divided by seconds, and the number of high-frequency sensors corresponds to the number of data, and each data can calculate multiple characteristic values, which can ensure that the timestamps of the pneumatic data and the characteristic values ​​are consistent, which is convenient for subsequent storage and calculation.

[0062] Optionally, in order to ensure that the initial phase of the high-frequency data of the shaft displacement data is consistent, the shaft displacement data needs to be clipped according to the key phase data before calculating the eigenvalue.

[0063] S22, analyzing the impact of pneumatic data on compressor performance degradation to obtain a first fault probability for each first fault event; and obtaining a second fault probability for each second fault event based on a correlation between a characteristic value of high-frequency data and the probability of a second fault event occurring.

[0064] Each data dimension in the above-mentioned pneumatic data is correspondingly associated with the first fault event.

[0065] Specifically, the first fault event associated with the temperature, pressure, flow rate and valve opening may be a fault event such as equipment performance degradation, pipeline blockage, pipeline leakage, impeller damage, etc.

[0066] The second fault event includes different fault events corresponding to feature values ​​of feature dimensions of different high-frequency data.

[0067] Specifically, the time domain characteristic data includes the maximum value of vibration displacement, the minimum value of vibration displacement, the average value of vibration displacement, the average value of vibration displacement, the peak-to-valley value of vibration displacement, and the standard deviation value of vibration displacement. Each data dimension in the above time domain characteristic data is respectively associated with the second fault event.

[0068] The frequency domain characteristic data include: 0.5 times the frequency amplitude, 0.5 times the frequency phase, 1 times the frequency amplitude, 1 times the frequency phase, 2 times the frequency amplitude, 2 times the frequency phase, 3 times the frequency amplitude, 4 times the frequency amplitude, main frequency, main frequency in the low frequency area, main frequency amplitude in the low frequency area and 1 times the frequency amplitude ratio.

[0069] As an implementation method, the high-frequency data may also include the waveform of the vibration signal, the spectrum obtained by Fourier transforming the waveform, and the axis trajectory.

[0070] Optionally, an initial performance model of the mapping relationship between the waveform of the vibration signal, the spectrum and the axis trajectory obtained by Fourier transform of the waveform, and the performance indicators of the second fault events of different fault types is constructed. The initial performance model is trained to obtain a preset performance prediction model, so that the preset performance prediction model characterizes the correlation mapping relationship between the waveform of the vibration signal, the spectrum and the axis trajectory obtained by Fourier transform of the waveform, and the performance indicators of the second fault events of different fault types. The waveform of the vibration signal, the spectrum and the axis trajectory obtained by Fourier transform of the waveform are input into the correlation mapping relationship to obtain the target performance indicator of the second fault event of the target fault type. Multiple standard feature values ​​corresponding to each data dimension consistent with the data dimension of the second fault event of the target fault type in the high-frequency data under normal operation of the compressor are obtained, and the second standard deviation and the corresponding second standard performance threshold of the multiple standard feature values ​​are determined; based on the second standard deviation and the corresponding second standard performance threshold, a second mapping relationship characterizing the feature value and the second fault probability is constructed to obtain the second fault probability of each second fault event.

[0071] As shown in Figure 5, the correlation between high-frequency data and the characteristic values ​​of high-frequency data and fault events of different fault types. Among them, the second fault events corresponding to the vibration displacement peak-to-valley value, vibration displacement standard deviation value, 0.5 frequency amplitude, 0.5 frequency phase, 1 frequency amplitude, 1 frequency phase, 2 frequency amplitude, 2 frequency phase, 3 frequency amplitude, 4 frequency amplitude, 1 frequency amplitude ratio, main frequency, low frequency area main frequency, low frequency area main frequency amplitude, horizontal range, vertical range and mean are: system fault, system fault, fluid faults such as oil film vortex and surge, fluid faults such as oil film vortex and surge, unbalance fault, unbalance fault (transient or gradual), misalignment fault, misalignment fault, misalignment fault, unbalance fault, system fault, fluid faults such as oil film vortex and surge, fluid faults such as oil film vortex and surge, bearing wear fault, bearing wear fault, bearing wear fault.

[0072] S23, from the fault tree constituting the causal logical relationship of multiple fault events, determine the target logical association relationship between each first fault event and each second fault event, and store the target logical association relationship in the fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event.

[0073] It is understandable that the target logical association relationship, the first fault probability of each first fault event and the second fault probability of each second fault event are correspondingly associated with each first fault event and each second fault event in the fault tree and stored in the fault tree.

[0074] The multiple fault events in the fault tree include first fault events and second fault events. The logical association between the fault events in the fault tree is represented based on logic gates. The logic gates include AND gates, NOT gates, OR gates, etc.

[0075] Optionally, in order to further highlight the above-mentioned target logical association relationship, the target logical association relationship, each first fault event and the corresponding first fault probability, and each second fault event are marked in the fault tree, so as to facilitate subsequent acquisition based on the marking and highlight the marked target fault information for user query.

[0076] In the above implementation steps, after the fault probability, the corresponding fault event and the causal relationship are associated and stored, the target association relationship and the related fault events and probability dynamic identification in the fault tree are displayed in the fault tree, so as to ensure that the fault probability and fault events identified and displayed in the fault tree change dynamically with the change of equipment status.

[0077] Through the above implementation, multiple fault events of different fault types including each first fault event and each second fault event are constructed in a fault tree according to a causal logic relationship. Based on the data characteristics of the pneumatic data and high-frequency data of the compressor, each first fault event, each second fault event and the fault probability of each fault event represented by different data dimensions are obtained respectively. At the same time, the obtained fault probabilities of each first fault event and each second fault event are associated and stored in the above constructed fault tree, so that the fault tree can directly display the target causal relationship between each first fault event and each second fault event and the fault probability of each fault event. The above directly based on the different feature dimensions represented by different data can accurately determine the occurrence probability of different fault events and each fault event.

[0078] In the above-mentioned method for determining the fault probability, the fault event and the fault probability are determined based on the characteristic properties of the data and the correlation between the fault event and the fault probability. It is not limited by the small amount of fault data during the use of industrial equipment, and its fault detection results are more accurate. At the same time, the control logic between its fault events and the corresponding fault probability are associated and stored in the form of a fault tree, so as to facilitate a more intuitive display of the fault result data such as the control logic between the fault events and the corresponding fault probability obtained during the fault detection process.

[0079] As a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, the embodiment of the present application provides other implementation methods of compressor fault tree construction.

[0080] Optionally, the specific execution process of the above step S22 of analyzing the impact of aerodynamic data on compressor performance degradation is as follows.

[0081] Step S221, determining each first fault event and a first performance indicator of the compressor according to each outlet temperature, each inlet temperature, each outlet pressure and each inlet pressure of the compressor in the pneumatic data.

[0082] It can be understood that the pneumatic data includes the outlet temperatures, inlet temperatures, outlet pressures and inlet pressures of each outlet and each inlet of the compressor.

[0083] As a method for determining a first fault event, each first fault event represented by the pneumatic data is determined based on the parameter differences between each outlet temperature, each inlet temperature, each outlet pressure and each inlet pressure and the corresponding aerodynamic parameter threshold exceeding the corresponding preset parameter threshold.

[0084] Step S222, using the speed and flow rate of the compressor in the pneumatic data, predicting the performance index of the compressor in a fault-free state, and predicting a second performance index.

[0085] In view of the large amount of healthy sample data under normal operation, that is, sufficient training samples, a neural network model can be used to train the correlation mapping relationship between the speed and flow of the compressor in the pneumatic data and the performance indicators of the equipment to obtain a preset model.

[0086] Step S223: determining a first failure probability of each first failure event according to the indicator difference between the second performance indicator and the first performance indicator.

[0087] As a method for determining the first fault probability, a plurality of first standard performance indicators corresponding to each data dimension consistent with each first fault event in the pneumatic data under normal operation of the compressor are obtained, and a first standard deviation of the plurality of first standard performance indicators and a first standard performance threshold corresponding to the first standard deviation are determined. A first mapping relationship between the characterization indicator difference and the first fault probability is constructed based on the first standard deviation and the corresponding first standard performance threshold to obtain the first fault probability.

[0088] It is understandable that the indicator difference between the second performance indicator and the first performance indicator is substituted into the first mapping relationship to obtain the first failure probability.

[0089] Optionally, the specific execution process of determining the second failure probability in the above step S22 is as follows.

[0090] First, according to the association mapping relationship between each characteristic value of the high-frequency data and different types of second fault events, each second fault event represented by the high-frequency data is determined.

[0091] Secondly, multiple standard feature values ​​corresponding to each data dimension consistent with the data dimension of each second fault event in the high-frequency data under normal operation of the compressor are obtained, and the second standard deviation of the multiple standard feature values ​​and the corresponding second standard performance threshold are determined.

[0092] Thirdly, a second mapping relationship between the characterizing characteristic value and the second fault probability is constructed based on the second standard deviation and the corresponding second standard performance threshold, so as to obtain the second fault probability of each second fault event.

[0093] As an implementation manner, the second mapping relationship and the first mapping relationship are further explained by the Sigmoid function in the following formula 1.

[0094]

[0095] Among them, σ i Characterizes the first standard deviation or the second standard deviation, i th Characterize the first standard performance threshold or the second standard performance threshold, p tauit represents the first failure probability or the second failure probability.

[0096] Optionally, the specific steps of obtaining the pneumatic data and high-frequency data of the compressor in the above step S21 are as follows: according to a preset period, a data acquisition instruction is sent to the request end device. The data acquisition instruction is used to instruct the request end device to send the pneumatic data and high-frequency data of the compressor to the cloud server, so that the cloud server obtains the pneumatic data and high-frequency data of the compressor; wherein, when the request end device sends the pneumatic data and high-frequency data of the compressor to the cloud server, if it is detected that the amount of data sent exceeds the quantity threshold, the data transmission speed is increased according to the preset speed increase rule; wherein, the request end device includes the terminal device of the compressor or the compressor.

[0097] In the above implementation, in order to alleviate the pressure of high-frequency data transmission, storage, calculation and display, a transmission and storage method combining fixed-point and supplementary can be adopted. Fixed-point means transmitting and storing high-frequency data at a specific time point, such as transmitting and storing one second of high-frequency data every half an hour. There are as many high-frequency data as there are high-frequency sensors. When the early warning index exceeds the threshold, the transmission volume of high-frequency data will be increased on the original basis. Generally, the increased high-frequency data corresponds to a higher early warning index.

[0098] Optionally, after the target logical association relationship is stored in the fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event, the following steps can also be performed: a display request for displaying the fault tree is received from a requesting end device, and the target logical association relationship, each first fault event and the corresponding first fault probability, and each second fault event and the corresponding second fault probability in the fault tree are identified and sent to the requesting end device, where the requesting end device includes a terminal device or a compressor of the compressor.

[0099] The present application also provides a method Figure 6 The compressor fault tree display method shown is applied to a terminal device or a compressor including a compressor. The terminal device or the compressor is communicatively connected to a cloud server to exchange information with each other. The method includes the following steps.

[0100] S61, sending a display request for displaying the fault tree to the cloud server connected to the compressor in communication, and displaying the target logical association relationship identified in the fault tree returned by the cloud server, each first fault event and the corresponding first fault probability, each second fault event and the corresponding second fault probability in the form of a fault tree.

[0101] The fault tree is constructed by the cloud server according to the compressor fault tree construction method in any of the above embodiments.

[0102] In this implementation step, the compressor fault conditions represented by data from different data sources are described in the form of a fault tree.

[0103] S62, in response to the user's configuration request, modify the fault events and logical associations of the fault tree according to the configuration request.

[0104] Among them, changing the fault events and logical association relationships of the fault tree includes one or more of the following: adding fault events and logical association relationships of the fault tree, modifying fault events and logical association relationships of the fault tree, and deleting fault events and logical association relationships of the fault tree.

[0105] In this implementation step, the fault events and logical associations in the fault tree can be flexibly set based on the user configuration request.

[0106] As a specific embodiment, the diagnostic algorithm is first deployed in the software platform, that is, the algorithm is associated with the data, and real-time calculations are performed according to certain data reading and calculation logic to obtain the probability results of different faults.

[0107] Secondly, the configuration process is described as follows, taking the configuration page of the centrifugal compressor fault diagnosis expert system based on the fault tree designed in this application as an example. Figure 7 On the fault tree configuration page shown in the schematic diagram of the fault tree configuration page, drag and connect the fault probability results and logic gates according to the logical relationship to build the fault events and logical association relationships of the fault tree. In the fault tree model, the event that the system least wants to happen is the top event, the various possible causes that lead to the top event are the intermediate events, and all the possible causes that lead to the intermediate event and cannot be divided are the bottom events. Logic gates are used to represent the relationship between events. Intermediate events and top events can also be added by adding new events. Supports custom logic gates, that is, customizing the functional relationship between bottom events and intermediate events, and the functional relationship between intermediate events and top events.

[0108] Finally, the configuration process is further explained by taking the configuration page of the centrifugal compressor fault diagnosis expert system based on the fault tree designed in this application as an example. Figure 8 The diagram of the fault tree on the configuration page is shown. The list of faults configured above and their probability of occurrence are displayed on the left, and the fault tree is displayed in the middle. Each event has a different color, indicating the probability of occurrence. The recent probability results of different faults are displayed below the fault tree.

[0109] Through the above implementation, on the one hand, the control logic between the fault events and the corresponding fault probability are displayed in the form of a fault tree, so as to more intuitively display the fault result data such as the control logic between the fault events and the corresponding fault probability obtained during the fault detection process. On the other hand, the fault events and logical associations of the fault tree can be customized to meet user needs.

[0110] In order to achieve the above functions, the compressor fault tree construction device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0111] The present application also provides a method Fig. 9 The compressor fault tree construction device shown is applied to a cloud server that is communicatively connected to the compressor. The device includes: an acquisition unit 901 , an analysis unit 902 , and a construction unit 903 .

[0112] The acquisition unit 901 is used to acquire the pneumatic data and high-frequency data of the compressor; the high-frequency data represents the shaft displacement data of the vibration signal, including the time domain characteristic data and frequency domain characteristic data of the vibration signal.

[0113] The analysis unit 902 is used to analyze the impact of pneumatic data on compressor performance degradation to obtain a first fault probability of each first fault event; and to obtain a second fault probability of each second fault event based on a correlation between a characteristic value of high-frequency data and a probability of a second fault event occurring.

[0114] The construction unit 903 is used to determine the target logical association relationship between each first fault event and each second fault event from the fault tree constituting the causal logical relationship of multiple fault events, and store the target logical association relationship in the fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event.

[0115] In one embodiment, the analysis unit 902 is specifically used to: determine each first fault event and a first performance indicator of the compressor based on each outlet temperature, each inlet temperature, each outlet pressure and each inlet pressure of the compressor in the pneumatic data; use the speed and flow rate of the compressor in the pneumatic data to predict the performance indicator of the compressor in a fault-free state, and predict the second performance indicator; determine the first fault probability of each first fault event according to the indicator difference between the second performance indicator and the first performance indicator.

[0116] In another embodiment, the analysis unit 902 is specifically used to determine each first fault event represented by the pneumatic data based on the parameter differences between each outlet temperature, each inlet temperature, each outlet pressure and each inlet pressure and the corresponding aerodynamic parameter threshold exceeding the corresponding preset parameter threshold.

[0117] In another embodiment, the analysis unit 902 is specifically used to: obtain multiple first standard performance indicators corresponding to each data dimension consistent with the data dimension of each first fault event in the pneumatic data under normal operation of the compressor, and determine the first standard deviation of the multiple first standard performance indicators and the corresponding first standard performance threshold; construct a first mapping relationship between the characterization indicator difference and the first fault probability based on the first standard deviation and the corresponding first standard performance threshold to obtain the first fault probability.

[0118] In another embodiment, the analysis unit 902 is further specifically used to: determine each second fault event represented by the high-frequency data based on a mapping relationship between each characteristic value of the high-frequency data and different types of second fault events; obtain multiple standard characteristic values ​​corresponding to each data dimension consistent with the data dimension of each second fault event in the high-frequency data under normal operation of the compressor, and determine the second standard deviation of the multiple standard characteristic values ​​and the corresponding second standard performance threshold; construct a second mapping relationship between the characteristic value and the second fault probability based on the second standard deviation and the corresponding second standard performance threshold to obtain the second fault probability of each second fault event.

[0119] In another embodiment, the acquisition unit 901 is specifically used to: send a data acquisition instruction to the requesting end device according to a preset period; the data acquisition instruction is used to instruct the requesting end device to send the pneumatic data and high-frequency data of the compressor to the cloud server, so that the cloud server obtains the pneumatic data and high-frequency data of the compressor; wherein, in the process of the requesting end device sending the pneumatic data and high-frequency data of the compressor to the cloud server, when it is detected that the amount of data sent exceeds the quantity threshold, the data transmission speed is increased according to the preset speed increase rule; wherein the requesting end device includes a terminal device or a compressor of the compressor.

[0120] In another embodiment, after the target logical association relationship is stored in the fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event, the device is also used to: receive a display request for displaying the fault tree sent by a requesting end device, identify the target logical association relationship, each first fault event and the corresponding first fault probability, each second fault event and the corresponding second fault probability in the fault tree, and send them to the requesting end device, the requesting end device includes a terminal device or a compressor of the compressor.

[0121] The present application also provides a method Fig.10The compressor fault tree display device shown is applied to a terminal device or a compressor including a compressor. The device includes: a display unit 101 and a configuration unit 102 .

[0122] The display unit 101 is used to send a display request for displaying a fault tree to a cloud server that is communicatively connected to the compressor, and display the target logical association relationship identified in the fault tree returned by the cloud server, each first fault event and the corresponding first fault probability, each second fault event and the corresponding second fault probability in the form of a fault tree, wherein the fault tree cloud server is constructed according to the compressor fault tree construction method of any of the above-mentioned embodiments.

[0123] The configuration unit 102 is used to respond to a user's configuration request and change the fault events and logical associations of the fault tree according to the configuration request. Changing the fault events and logical associations of the fault tree includes one or more of the following: adding fault events and logical associations of the fault tree, modifying fault events and logical associations of the fault tree, and deleting fault events and logical associations of the fault tree.

[0124] Regarding the device in the above embodiment, the specific manner in which each unit module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0125] Fig.11 is a schematic diagram of a device terminal provided by this application. Fig.11 The device terminal 60 may include a compressor and at least one processor 601 and a memory 603 for storing processor executable instructions. The processor 601 is configured to execute instructions in the memory 603 to implement the compressor fault tree construction method in the following embodiment.

[0126] In addition, the device terminal 60 may further include a communication bus 602 , at least one communication interface 604 , an input device 606 , and an output device 605 .

[0127] The processor 601 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0128] Communication bus 602 may include a pathway for transmitting information between the above-mentioned components.

[0129] The communication interface 604 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0130] The input device 606 is used to receive input signals and the output device 605 is used to output signals.

[0131] The memory 603 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit through a bus. The memory may also be integrated with the processing unit.

[0132] The memory 603 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 601. The processor 601 is used to execute the instructions stored in the memory 603, so as to realize the functions in the method of the present application.

[0133] In a specific implementation, as an embodiment, the processor 601 may include one or more CPUs, such as Fig.11 CPU0 and CPU1 in.

[0134] In a specific implementation, as an embodiment, the device terminal 60 may include multiple processors, such as Fig.11 601 and processor 607 in FIG. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0135] The device terminal is Fig.11The system includes: a processor 601 and a memory 603 for storing executable instructions of the processor 601; wherein the processor 601 is configured to execute the executable instructions to implement a compressor fault tree construction method or a compressor fault tree display method as any of the above possible implementations. The same technical effect can be achieved, and to avoid repetition, it will not be described here.

[0136] The embodiment of the present application also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a compressor fault tree construction device, the compressor fault tree construction device can execute a compressor fault tree construction method as described in any possible implementation method described above. Alternatively, when the instructions in the computer-readable storage medium are executed by a compressor fault tree display method device, the compressor fault tree display method device can execute a compressor fault tree display method as described in any possible implementation method described above. The same technical effects can be achieved, and to avoid repetition, they will not be described here.

[0137] The embodiment of the present application also provides a computer program product, including a computer program or an instruction, which is executed by a processor to implement a compressor fault tree construction method or a compressor fault tree display method in any of the above possible implementations. The same technical effect can be achieved, and to avoid repetition, it will not be described here.

[0138] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0139] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for constructing a compressor fault tree, characterized in that: Applied to a cloud server in communication with a compressor, the method includes: Acquiring pneumatic data and high-frequency data of the compressor; wherein the high-frequency data represents shaft displacement data of the vibration signal, including time-domain characteristic data and frequency-domain characteristic data of the vibration signal; Analyzing the effect of the aerodynamic data on compressor performance degradation to obtain a first failure probability for each first failure event; and obtaining a second failure probability for each second failure event based on a correlation between a characteristic value of the high-frequency data and a probability of the second failure event occurring; From a fault tree constituting a causal logical relationship of multiple fault events, a target logical association relationship between each first fault event and each second fault event is determined, and the target logical association relationship is correspondingly associated with the first fault probability of each first fault event and the second fault probability of each second fault event and stored in the fault tree.

2. The compressor fault tree construction method according to claim 1, characterized in that: Analyzing the effect of the aerodynamic data on the compressor performance degradation to obtain a first failure probability of each first failure event includes: determining the first fault events and the first performance indicator of the compressor according to the outlet temperatures, inlet temperatures, outlet pressures, and inlet pressures of the compressor in the pneumatic data; Using the rotation speed and flow rate of the compressor in the pneumatic data, predicting a performance index of the compressor in a fault-free state, and predicting a second performance index; A first failure probability of each first failure event is determined according to an indicator difference between the second performance indicator and the first performance indicator.

3. The compressor fault tree construction method according to claim 2, characterized in that: The determining of each first fault event according to each outlet temperature, each inlet temperature, each outlet pressure, and each inlet pressure of the compressor in the pneumatic data includes: According to the parameter differences between the respective outlet temperatures, the respective inlet temperatures, the respective outlet pressures and the respective inlet pressures and the corresponding aerodynamic parameter thresholds exceeding the corresponding preset parameter thresholds, the respective first fault events represented by the aerodynamic data are determined.

4. A compressor fault tree display method, characterized in that: Applied to a terminal device or a compressor including a compressor, the terminal device or the compressor is communicatively connected to a cloud server for mutual information exchange, the method comprising: Sending a display request for a fault tree to a cloud server in communication with the compressor, and displaying the target logical association relationships, each first fault event and its corresponding first fault probability, and each second fault event and its corresponding second fault probability identified in the fault tree returned by the cloud server in the form of a fault tree, wherein the fault tree cloud server is constructed according to the compressor fault tree construction method according to any one of claims 1 to 3; In response to a user's configuration request, the fault events and logical associations of the fault tree are changed according to the configuration request; wherein the changes to the fault events and logical associations of the fault tree include one or more of the following: adding fault events and logical associations of the fault tree, modifying fault events and logical associations of the fault tree, and deleting fault events and logical associations of the fault tree.

5. A compressor fault tree construction device, characterized in that: Applicable to a cloud server in communication with a compressor, the device comprising: The acquisition unit is used to acquire pneumatic data and high-frequency data of the compressor; the high-frequency data represents shaft displacement data of the vibration signal, including time domain characteristic data and frequency domain characteristic data of the vibration signal; The analysis unit is configured to analyze the effect of the aerodynamic data on compressor performance degradation to obtain a first failure probability for each first failure event; and obtain a second failure probability for each second failure event based on a correlation between a characteristic value of the high-frequency data and a probability of the second failure event occurring. The construction unit is used to determine the target logical association relationship between each first fault event and each second fault event from a fault tree that constitutes a causal logical relationship of multiple fault events, and store the target logical association relationship in the fault tree in correspondence with the first fault probability of each first fault event and the second fault probability of each second fault event.

6. A compressor fault tree display device, characterized in that: Applicable to a terminal device or a compressor including a compressor, the device comprises: a display unit, configured to send a display request for a fault tree to a cloud server in communication with the compressor, and display the target logical association relationships, each first fault event and its corresponding first fault probability, each second fault event and its corresponding second fault probability, identified in the fault tree returned by the cloud server in the form of a fault tree, wherein the fault tree cloud server is constructed according to the compressor fault tree construction method according to any one of claims 1 to 3; The configuration unit is used to, in response to a user's configuration request, change the fault events and logical association relationships of the fault tree according to the configuration request, wherein the change of the fault events and logical association relationships of the fault tree includes one or more of the following: adding the fault events and logical association relationships of the fault tree, modifying the fault events and logical association relationships of the fault tree, and deleting the fault events and logical association relationships of the fault tree.

7. A compressor, characterized in that: The compressor is communicatively connected to a cloud server, the cloud server is used to execute the compressor fault tree construction method according to any one of claims 1 to 3, and the compressor is used to execute the compressor fault tree display method according to claim 4.

8. A device terminal, characterized in that: The device terminal includes a compressor and is communicatively connected to a cloud server. The cloud server is used to execute the compressor fault tree construction method according to any one of claims 1 to 4. The terminal device is used to execute the compressor fault tree display method according to claim 4.

9. A compressor fault detection system, characterized in that: The compressor fault detection system includes a compressor and a cloud server, the compressor is communicatively connected to the cloud server, the cloud server is used to execute the compressor fault tree construction method according to any one of claims 1 to 3, and the terminal device is used to execute the compressor fault tree display method according to claim 4.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor, the compressor fault tree construction method according to any one of claims 1 to 3 or the compressor fault tree display method according to claim 4 can be executed.

Images