Fault information generation method and device, storage medium and computing equipment

Abstract

The embodiment of the invention provides a fault information generation method and device, a storage medium and computing equipment, fault information is information involved in fault analysis, the fault information comprises characteristic quantity information and / or action chain information, and information layer data is acquired in an information source range corresponding to a diagnosis object; performing feature extraction on the information layer data to generate feature quantity information; and / or according to a preset action chain and the information layer data, action chain information is generated, and the fault is analyzed by using the characteristic quantity information and / or the action chain information, so that the computing device can obtain data from multiple dimensions in an information source range corresponding to the diagnosis object in real time to obtain the information layer data; and performing multi-dimensional analysis on the information layer data, capturing changes and tendentiousness of the data, and obtaining characteristic quantity information and / or action chain information for analyzing the fault.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of equipment status monitoring and fault diagnosis, and in particular to a method for generating fault information. Background Art

[0002] Since its birth, fault diagnosis technology has gone through decades of development, and many analysis methods and diagnostic strategies have emerged, showing a diversified development trend. However, in practical applications, its results are not ideal. The main problem is that it only focuses on the fault itself, resulting in the data used for diagnosis being only the data points of the fault location, and the data involved in fault analysis is one-sided. Summary of the invention

[0003] In view of this, the embodiments of this specification provide a method for generating fault information. One or more embodiments of this specification also relate to a device for generating fault information, a computing device, a computer-readable storage medium and a computer program to solve the technical defects existing in the prior art.

[0004] According to a first aspect of an embodiment of this specification, a method for generating fault information is provided, where the fault information is information involved in analyzing a fault, and the fault information includes feature quantity information and / or action chain information. The method includes: Acquire information layer data within the scope of the information source corresponding to the diagnosis object; Extract features from the information layer data to generate feature quantity information; and / or generate action chain information based on the information layer data according to a preset action chain, so as to analyze the fault using the feature quantity information and / or the action chain information.

[0005] In a possible implementation, after extracting features from the information layer data to generate feature quantity information, and generating action chain information according to the information layer data according to a preset action chain, the method further includes: When a fault occurs, the cause of the fault of the diagnosis object is analyzed according to the feature quantity information and the action chain information to generate the fault cause.

[0006] In a possible implementation manner, after generating the feature quantity information, the method further includes: A fault of the diagnosis object is predicted based on the feature quantity information to generate a fault prediction result.

[0007] In a possible implementation manner, the information layer data includes at least one of host layer data, auxiliary machine layer data, and environment layer data.

[0008] In one possible implementation, the feature extraction includes at least one of time domain feature extraction, frequency domain feature extraction, amplitude domain feature extraction, operating condition feature extraction, stability tendency feature extraction, environmental feature extraction, baseline parameter feature extraction, current value feature extraction, change rate feature extraction, cumulative change rate feature extraction and numerical tendency feature extraction.

[0009] In one possible implementation, the action chain includes at least one of a timing action chain of rotating stall and surge, a timing action chain of turbine water hammer, a mass defect type unbalance fault action chain, a material adhesion unbalance action chain, a misalignment fault action chain, a rolling bearing poor lubrication action chain, a rolling bearing local fault action chain, a gear meshing fault action chain and a general timing action chain.

[0010] In a possible implementation, the information layer data includes compressor inlet flow, the action chain includes rotating stall and surge action chains, and the action chain information includes rotating stall and surge action chain information; Correspondingly, generating action chain information according to the information layer data according to the preset action chain includes: Based on the compressor inlet flow being less than a critical value, determining that the compressor is in rotational stall, and determining that the compressor inlet flow is data corresponding to the rotational stall and surge action chain; The compressor inlet flow is added to the rotating stall and surge action chain information.

[0011] According to a second aspect of an embodiment of this specification, a device for generating fault information is provided, where the fault information is information involved in analyzing a fault, and the fault information includes feature quantity information and / or action chain information, and the device includes: An acquisition module is configured to acquire information layer data within the range of information sources corresponding to the diagnosis object; The generation module is configured to extract features from the information layer data, generate feature quantity information, and / or generate action chain information based on the information layer data according to a preset action chain, so as to analyze the fault using the feature quantity information and / or the action chain information.

[0012] According to a third aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned fault information generation method are implemented.

[0013] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned method for generating fault information are implemented.

[0014] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for generating fault information.

[0015] An embodiment of the present specification implements a method, apparatus, storage medium and computing device for generating fault information, wherein the fault information is information involved in analyzing a fault, and the fault information includes characteristic quantity information and / or action chain information. Within the information source range corresponding to the diagnosis object, information layer data is obtained; features are extracted from the information layer data to generate characteristic quantity information; and / or, according to a preset action chain, action chain information is generated based on the information layer data to analyze the fault using the characteristic quantity information and / or action chain information, so that the computing device can obtain data from multiple dimensions in real time within the information source range corresponding to the diagnosis object to obtain information layer data; multi-dimensional analysis is performed on the information layer data to capture changes and tendencies of these data, and obtain characteristic quantity information and / or action chain information for analyzing the fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a method for generating fault information provided by an embodiment of this specification; Figure 2 is a schematic diagram of a diagnostic object provided by an embodiment of this specification; Figure 3 It is a structural schematic diagram of a device for generating fault information provided by an embodiment of this specification; Figure 4 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0017] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0018] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0019] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0020] In the related technologies, the lack of diagnostic accuracy, including missed diagnosis and misdiagnosis, has become the main obstacle to the widespread application of this technology. In the field of traditional dynamic equipment fault diagnosis, information acquisition mainly relies on mechanical vibration data, and then various fault mechanism analysis and diagnostic logic frameworks are constructed. Although these mechanisms and logics have achieved certain results in solving some dynamic equipment fault diagnosis problems, their accuracy and objectivity are still insufficient, and the accuracy rate in fault diagnosis is even lower. The reason for the low accuracy rate is incomplete data acquisition.

[0021] In order to improve the accuracy of fault diagnosis, it is necessary to obtain rich information. In this specification, a method for generating fault information is provided. The fault information is the information involved in analyzing the fault. The fault information includes characteristic quantity information and / or action chain information. This specification also involves a device for generating fault information, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0022] Figure 1 is a flow chart of a method for generating fault information provided by an embodiment of this specification, such as Figure 1 As shown, the method includes: Step 101: The computing device obtains information layer data within the information source range corresponding to the diagnosis object.

[0023] In some embodiments, the computing device includes but is not limited to servers, computing modules, and computer devices, and may also be a combination of servers, computing modules, and computer devices. The diagnostic object includes but is not limited to vehicles, equipment modules, or ships, etc. The equipment module is a partial module of the equipment, including a compressor, a fan, or a wheel hub, etc.

[0024] A sensor is installed on the diagnostic object, and the sensor can collect data when the diagnostic object is running, shut down or on standby. The diagnostic object can also be connected to a data collector, and the data collector uploads the information layer data to the computing device. Alternatively, the data collector includes a computing module, and after the data collector receives the information layer data sent by the diagnostic object, the computing module executes step 101. Alternatively, the data collector includes a computing module, and the computing device includes a computing module and a server. After the data collector receives the information layer data sent by the diagnostic object, the computing module and the server jointly implement the steps of the method for generating fault information, wherein the steps executed by the computing module and the steps executed by the server can be allocated according to actual needs, computing power, etc.

[0025] The scope of the information source corresponding to the diagnostic object is bounded by the process flow scope of the diagnostic object. For example, when the diagnostic object includes a moving equipment unit, the moving equipment unit is an important node in process production, and its process flow scope is determined. Within the scope of the process flow, the input and output operating conditions of the diagnostic equipment are an important basis for affecting the operation of the equipment, and the abnormal state caused (some abnormal states are not actual faults) are affected by the mechanical state, operating state and performance state of the diagnostic equipment, and are also affected by environmental factors. The scope of the information source corresponding to the diagnostic object is usually determined by factors such as the composition of the diagnostic object and the environment in which the diagnostic object is located, where the environment includes the weather environment and / or the operating state of the vehicle. The weather environment includes but is not limited to a strong electromagnetic environment, and the operating state includes but is not limited to a load adjustment state, a start-stop process or an accident state. For example, the composition of the diagnostic object includes the main machine and the auxiliary machine, the environment refers to the weather environment and operating status of the main machine and the auxiliary machine, the weather environment is a strong electromagnetic environment, and the operating status is an accident state. The information sources corresponding to the diagnostic object include the main machine, the auxiliary machine, the weather environment and the operating status; the sensor installed on the diagnostic object collects the data of the main machine, the data of the auxiliary machine, the data of the weather environment and the data of the operating status, and the data of the main machine, the data of the auxiliary machine, the data of the weather environment and the data of the operating status constitute the information layer data. Alternatively, the diagnostic object is only composed of the main machine, and there is no auxiliary machine. The information layer data is composed of the data of the main machine, the data of the weather environment and the data of the operating status.

[0026] The host is the main body of the diagnostic object, and the auxiliary machine is the auxiliary equipment required for the normal operation of the host. For example, the host includes at least one of the driving machine, transmission mechanism and working machine, and the auxiliary machine includes at least one of the condensing equipment, cooling equipment, lubrication equipment, sewage discharge equipment and separation equipment required for the operation of the host.

[0027] Information layer data may include data of the information source within the time and space range of the front and back, vertical and horizontal directions, including not only the current data of the information source, but also the data before the information source; and the various modules of the diagnosis object are spatially related, and the data collected from each module are also spatially related, so that data of multiple dimensions can be obtained as completely as possible in time and space to obtain information layer data.

[0028] Step 102: The computing device extracts features from the information layer data to generate feature quantity information; and / or generates action chain information based on the information layer data according to a preset action chain, so as to analyze the fault using the feature quantity information and / or action chain information.

[0029] In some embodiments, when the computing device extracts features from the information layer data, it may process the information layer data from at least one of the time domain, frequency domain, amplitude domain, working conditions, tendency, and environmental impact to obtain feature quantity information. For example, the tendency of the information layer data may be calculated from the time perspective to obtain feature quantity information.

[0030] When diagnosing object failures, any type of failure must have one or more action chains. When diagnosing object failures or normal operation, action chain information is generated based on information layer data. The action chain information contains data that can fully describe the dynamic process of the failure. When a failure is generated, it is convenient to directly obtain the action chain information corresponding to the failure type based on the failure type, which makes it easier to trace and identify the root cause of the failure, and also makes it easier for relevant personnel to view the generation of action chain information.

[0031] An embodiment of the present specification provides a method for generating fault information, wherein the fault information is information involved in analyzing a fault, and the fault information includes characteristic quantity information and / or action chain information. Within the information source range corresponding to the diagnosis object, information layer data is obtained; features are extracted from the information layer data to generate characteristic quantity information; and / or, according to a preset action chain, action chain information is generated based on the information layer data to analyze the fault using the characteristic quantity information and / or action chain information, so that the computing device can obtain data from multiple dimensions in real time within the information source range corresponding to the diagnosis object to obtain information layer data; multi-dimensional analysis is performed on the information layer data to capture changes and tendencies of these data, and obtain characteristic quantity information and / or action chain information for analyzing the fault.

[0032] The following combination Figure 1 , the method for generating fault information is further explained.

[0033] In a possible implementation manner, the information layer data includes at least one of host layer data, auxiliary machine layer data, and environment layer data.

[0034] In some embodiments, the host layer data includes mechanical state monitoring indicators; the mechanical state monitoring indicators include but are not limited to at least one of mechanical vibration, shaft displacement, eccentricity, differential expansion, bearing type, gear speed change type and mechanical reference information. Different types of hosts require different mechanical state monitoring indicators, which mainly depends on the type of sensor equipped by the host, the type of signal output and the preprocessing strategy of the data collector for the signal.

[0035] The auxiliary machine layer data includes operating status monitoring indicators; the operating status monitoring indicators include but are not limited to at least one of the indicators such as medium temperature, inlet pressure, inlet flow, outlet pressure, outlet flow, stage pressure difference, stage temperature difference and operating benchmark information.

[0036] Environmental layer data includes environmental status monitoring indicators; environmental status monitoring indicators include but are not limited to at least one of the load adjustment state, start-up and shutdown process, accident state, medium change state, and strong electromagnetic environment or extreme weather state. Among them, load adjustment state: centrifugal compressor units have a load critical point. When the inlet flow of the compressor is lower than the critical point, it is easy to cause rotational stall, which may then evolve into surge; under the load adjustment state, the load critical point becomes a key performance indicator. Start-up and shutdown process: steam turbine-driven units require specific monitoring technology during the start-up and shutdown process; when starting, the actual speed-up process (including the stable time length and speed-up gradient of each speed segment) should be compared with the specified speed-up process (i.e., the standard speed-up curve), especially in the critical speed area, which requires rapid passage; the difference between the measured critical speed and the standard critical speed reflects the change in the dynamic characteristics of the rotor-bearing system. By comparing the Bode diagrams during the two start-up or shutdown processes, the nature and degree of the change can be confirmed, and the nature and degree of rotor imbalance can be determined at the same time. Accident state: In the accident state, the diagnostic object is in an abnormal operating state, and the main engine and auxiliary engine are therefore in low-load operation or medium circulation operation. The working state at this time is abnormal. Medium change state: For the working machine of process gas compression, the change of medium components will cause the change of its working state, and then cause the change of mechanical state such as mechanical vibration; for steam turbines, when the steam inlet temperature is lower than the standard limit, it may cause water hammer failure; for motor-driven units, when the three-phase power supply is not in good condition, it will also cause the mechanical state of the unit to change. Strong electromagnetic environment or extreme weather conditions: Dynamic equipment units usually do not work in this environment, but for some fan equipment, under extreme weather conditions, it may affect the state of the inlet air, and then cause changes in the mechanical state; the working state of the air preheater at the fan inlet is a key factor affecting the mechanical state of the equipment, especially in extremely cold weather conditions.

[0037] Figure 2 is a schematic diagram of a diagnostic object provided by an embodiment of this specification, such as Figure 2As shown, the diagnostic objects include the main machine and the auxiliary machine. The main machine includes the driving machine, the transmission mechanism and the working machine; the auxiliary machine of the transmission mechanism includes the condensing equipment, lubrication equipment and separation equipment required for the operation of the main machine; the auxiliary machine of the driving machine assists the driving machine in operation, and the auxiliary machine of the working machine assists in work and operation. The sensor will collect the driving input and driving output of the driving machine, and the driving state is the operating state of the driving machine. The sensor will also collect the input state and output state of the working machine; the input state includes at least one of pressure, valve position, flow, properties and medium; the output state includes at least one of pressure, flow, valve position and temperature. The mechanical state of the main machine includes at least one of vibration, displacement, temperature, differential expansion, eccentricity, noise, looseness and friction. Environmental factors include at least one of preload, vibration transmission, extreme weather, strong magnetic field, high humidity and corrosive environment. The driving machine includes at least one of an electric motor, a steam turbine, a gas turbine, an internal combustion engine and a water turbine, the working machine includes at least one of a pump, a compressor, a grinder, a rolling mill, a fan, a generator and a centrifuge, and the driving medium includes at least one of steam, gas, fuel oil, waste heat gas, water, wind and electricity.

[0038] The diagnostic object itself will have multiple sensors, which collect the mechanical status data of the diagnostic object. The diagnostic object also includes an automatic control system, which includes data other than the mechanical status data in the information layer data. When the computing device obtains the information layer data, there is no need to add other devices to the diagnostic object, and no additional economic burden is brought. In this way, comprehensive and accurate information layer data can be obtained, and then in the subsequent fault analysis, the accuracy and efficiency of fault diagnosis can be effectively improved, thereby ensuring the stable operation and reliability of the diagnostic object.

[0039] In a possible implementation, before step 102, the process further includes: a computing device performing standardization processing on the information layer data to generate standardized information layer data.

[0040] In some embodiments, standardization processing includes data cleaning, which refers to the process of re-examining and verifying data with the purpose of deleting duplicate information, correcting existing errors, and providing data consistency. The means of data cleaning may vary depending on the data.

[0041] In one possible implementation, feature extraction includes at least one of time domain feature extraction, frequency domain feature extraction, amplitude domain feature extraction, operating condition feature extraction, stability tendency feature extraction, environmental feature extraction, baseline parameter feature extraction, current value feature extraction, change rate feature extraction, cumulative change rate feature extraction and numerical tendency feature extraction.

[0042] In some embodiments, the feature quantity information includes at least one of time domain feature extraction results, frequency domain feature extraction results, amplitude domain feature extraction results, operating condition feature extraction results, stability tendency feature extraction results, environmental feature extraction results, baseline parameter feature extraction results, current value feature extraction results, change rate feature extraction results, cumulative change rate feature extraction results and numerical tendency feature extraction results.

[0043] Feature extraction usually includes time domain feature extraction, frequency domain feature extraction, amplitude domain feature extraction, working condition feature extraction, stability tendency feature extraction, environmental feature extraction and reference parameter feature extraction. As an extension of feature extraction, feature extraction can also include current value feature extraction, rate of change feature extraction, cumulative rate of change feature extraction and numerical tendency feature extraction. However, depending on the information source, the content of feature extraction may be different, and the content of feature quantity information may also be different.

[0044] The information layer data includes time domain data; time domain feature extraction refers to extracting peak values ​​and / or effective values ​​from time domain data within a preset time period. When feature extraction includes time domain feature extraction, the computing device compares the time domain data within the preset time period to obtain the maximum value of the time domain data and the minimum value of the time domain data; the maximum value of the time domain data and the minimum value of the time domain data are taken as the peak value. And / or, the computing device calculates the time domain data within the preset time period to generate the effective value of the time domain data. The time domain feature extraction result includes the peak value and / or the effective value of the time domain data. For example, the time domain data includes vibration acceleration, vibration velocity, vibration displacement, full-band integrated vibration velocity and envelope acceleration. The computing device compares the vibration acceleration within the preset time period to obtain the maximum value of the vibration acceleration and the minimum value of the vibration acceleration; the peak value of the vibration acceleration and the minimum value of the vibration acceleration are taken as the peak value of the vibration acceleration. The computing device calculates the root mean square value of the vibration acceleration within the preset time period to generate the effective value of the vibration acceleration. Similarly, the vibration velocity peak value, the vibration velocity effective value, the vibration displacement peak value, the full-band integrated vibration velocity peak value and the envelope acceleration peak value can be obtained.

[0045] Frequency domain feature extraction: For shell vibration, it is recommended to follow the narrowband division and alarm threshold setting recommended by the American Society for Nondestructive Testing (ASNT) standard; for phase vibration, it can be divided into: vibration amplitude and precession amplitude less than 1X; 1X vibration vector and precession amplitude; 2X vibration vector and precession amplitude; 3X to 12X amplitude and precession amplitude. Then, based on the divided vibration amplitude, precession amplitude and vibration vector, the computing device performs at least one of the following steps: extracting data corresponding to vibration amplitude and precession amplitude less than 1X from the information layer, extracting data corresponding to 1X vibration vector and precession amplitude from the information layer, extracting data corresponding to 2X vibration vector and precession amplitude from the information layer, and extracting data corresponding to 3X to 12X amplitude and precession amplitude from the information layer. The frequency domain feature extraction results include at least one of data corresponding to vibration amplitudes and precession amplitudes less than 1X, data corresponding to 1X vibration vectors and precession amplitudes, data corresponding to 2X vibration vectors and precession amplitudes, and data corresponding to amplitudes and precession amplitudes from 3X to 12X.

[0046] Amplitude domain feature extraction: including but not limited to the calculation of at least one of the kurtosis index, the skewness index, the mean and the standard deviation. The amplitude domain feature extraction result includes at least one of the kurtosis index calculation result, the skewness index calculation result, the mean calculation result and the standard deviation calculation result.

[0047] Working condition feature extraction: including but not limited to extracting the value of at least one working condition among current, speed, flow, pressure, temperature and load. The working condition feature extraction result includes at least one of current extraction result, speed extraction result, flow extraction result, pressure extraction result, temperature extraction result and load extraction result.

[0048] Stable tendency feature extraction: The information layer data includes stable tendency data; the computing device evaluates the stability of the stable tendency data within a preset time period. The stable tendency feature extraction result includes a stable tendency evaluation result. The stable tendency evaluation result includes stable and within the limit; or, the stable tendency evaluation result includes within the limit but the data tends to increase; or, the stable tendency evaluation result includes within the limit but the data tends to decrease; or, the stable tendency evaluation result includes a significant increase or a significant decrease; or, the stable tendency evaluation result includes a significant increase or a significant decrease, etc.

[0049] Environmental feature extraction: refers to extracting at least one of the accident state, load adjustment state, start-up (speed increase) process, shutdown process and medium change state. The environmental feature extraction result includes at least one of the accident state, load adjustment state, start-up (speed increase) process, shutdown process and medium change state.

[0050] Benchmark parameter feature extraction: refers to the extraction of standard limits for data such as speed, initial gap voltage, bearing clearance, rolling bearing type, number of gear teeth and speed. The benchmark parameter feature extraction results include standard limits for data such as speed, initial gap voltage, bearing clearance, rolling bearing type, number of gear teeth and speed.

[0051] Current value feature extraction: refers to the extraction of data at the current time point; the current value feature extraction result includes the current value or current state of the information in the information layer. The data at the current time point is the reference point for fault diagnosis.

[0052] Change rate feature extraction: refers to calculating the rate of change of the current value relative to the previous set of values, where the previous set of values ​​is the previous set of current values ​​relative to the current value; it can measure the change state of data, such as the percentage of data increase or decrease.

[0053] Cumulative change rate feature extraction: refers to the calculation of the change rate of the current value relative to the standard operating value. The standard operating value is the value of the diagnostic object in a normal state and the first operation after installation or maintenance.

[0054] Numerical tendency feature extraction: refers to calculating the degree to which the calculated data deviates from the continuous data points corresponding to the calculated data in the total data points. The total data points are located on the standard line, and the calculated data corresponds to the continuous data points on one side of the standard line. The calculated data can be data calculated from the information layer data, and the calculated data includes at least one of the mean, variance and fitting curve type. The degree to which the calculated data deviates from the continuous data points corresponding to the calculated data in the total data points can be reflected by the proportion of continuous data points in the total data points, positive kurtosis, negative kurtosis, positive skewness, negative skewness, etc.

[0055] In one possible implementation, the action chain includes at least one of a timing action chain of rotating stall and surge, a timing action chain of turbine water hammer, a mass defect type unbalance fault action chain, a material adhesion unbalance action chain, a misalignment fault action chain, a rolling bearing poor lubrication action chain, a rolling bearing local fault action chain, a gear meshing fault action chain and a general timing action chain.

[0056] In some embodiments, the action chain information includes at least one of the timing action chain information of rotating stall and surge, the timing action chain information of turbine water hammer, the action chain information of mass defect type imbalance fault, the action chain information of material adhesion imbalance, the action chain information of misalignment fault, the action chain information of poor rolling bearing lubrication, the action chain information of local rolling bearing fault, the action chain information of gear meshing fault, and the general timing action chain information. Depending on the diagnosis object, the preset action chain will also be different, and the action chain information will change with the change of the action chain. The action chain information covers data that can describe the dynamic process of the fault in detail. The action chain information includes the data where the problem occurs, and can also include the time corresponding to the data where the problem occurs; it is convenient to directly obtain the action chain information corresponding to the fault type based on the fault type when the fault is generated, so as to facilitate tracing and identifying the root cause of the fault.

[0057] Rotating stall is an unstable flow phenomenon that significantly reduces the performance of equipment such as turbofan engines or compressors. Usually, when the inlet flow rate of the equipment is lower than the critical value, the amplitude of the mechanical vibration will increase, and it is considered that the equipment has experienced rotating stall; and it is generally believed that rotating stall is a precursor to surge. When the inlet flow rate continues to decrease, rotating stall will evolve into surge, and surge is a resonant state in which rotating stall develops into a more intense vibration. The timing action chain of rotating stall and surge: the inlet flow rate is lower than the critical value → rotating stall → the inlet flow rate continues to be lower than the critical value → surge. When the information layer data includes the compressor inlet flow rate, the action chain includes the rotating stall and surge action chain, and the action chain information includes the rotating stall and surge action chain information, step 102 may specifically include: the computing device determines the compressor rotating stall based on the compressor inlet flow rate being less than the critical value, and determines that the compressor inlet flow rate is the data corresponding to the rotating stall and surge action chain; and adds the compressor inlet flow rate to the rotating stall and surge action chain information. The basis for judging the rotating stall is that the compressor inlet flow is less than the critical value, and the rotating stall and surge vibration chain information is used as the information set of the rotating stall and surge vibration chain. When the compressor is rotating stalled, the computing device adds the compressor inlet flow to the rotating stall and surge vibration chain information. The computing device determines that the compressor is surging based on the fact that the multiple compressor inlet flows in the first time period are all less than the critical value. The first time period can be any preset time period. The computing device can also add at least one of the target compressor inlet flow acquisition time point corresponding to the target compressor inlet flow, the rotating stall time point corresponding to the compressor rotating stall, and the surge time point corresponding to the compressor surge to the rotating stall and surge vibration chain information, wherein the target compressor inlet flow is the compressor inlet flow less than the critical value. For a multi-stage centrifugal compressor, each stage may experience rotating stall or surge, and the compressor inlet flow includes multiple stage inlet flows. The computing device can compare the multiple stage inlet flows with the critical value. When any stage inlet flow is less than the critical value, it is considered that the stage corresponding to the target stage inlet flow is rotating stall, wherein the target stage inlet flow is the stage inlet flow less than the critical value. In this embodiment, only the compressor is used as an example for explanation. Rotational stall or surge may also occur in equipment other than the compressor. This application does not limit the equipment that may experience rotational stall or surge.

[0058] If the steam inlet temperature is too low, it will cause water hammer in the steam turbine. The sequential action chain of steam turbine water hammer is: steam inlet temperature is lower than the standard value → water hammer. When the information layer data includes steam inlet temperature, the action chain includes the sequential action chain of steam turbine water hammer, and the action chain information includes the sequential action chain information of steam turbine water hammer, step 102 may specifically include: the computing device determines that the steam turbine has water hammer based on the steam inlet temperature being lower than the standard value of the steam inlet temperature, and determines that the steam inlet temperature is the data corresponding to the sequential action chain of steam turbine water hammer; and adds the steam inlet temperature to the sequential action chain information of steam turbine water hammer. The computing device may also add the target steam inlet temperature acquisition time point corresponding to the target steam inlet temperature and / or the steam turbine water hammer time point corresponding to the steam turbine water hammer to the sequential action chain information of steam turbine water hammer, wherein the target steam inlet temperature is the steam inlet temperature lower than the standard value of the steam inlet temperature.

[0059] The mass defect of the rotor will cause the rotor mass to be unbalanced, and the rotor will also rotate unbalanced when it rotates. The action chain of the mass defect type unbalance fault: mass defect → rotor mass imbalance, the mass defect type unbalance fault is sudden. The data corresponding to the mass defect type unbalance fault action chain can be determined according to the type of rotor and the state of the rotor. For example, the type of rotor includes rigidity or flexibility, and the state of the rotor includes stationary or rotating. When the rotor is a rigid rotor and the rotor is in a stationary state, the information layer data includes the rotor mass, the action chain includes the mass defect type unbalance fault action chain, and the action chain information includes the mass defect type unbalance fault action chain information. Step 102 may specifically include: the computing device determines that the rotor mass is unbalanced based on the rotor mass being less than the rotor mass standard value, and determines that the rotor mass is the data corresponding to the mass defect type unbalance fault action chain; the rotor mass is added to the mass defect type unbalance fault action chain information. The computing device may also add the target rotor mass collection time point corresponding to the target rotor mass and / or the rotor mass unbalance time point corresponding to the rotor mass unbalance to the quality defect type unbalance fault action chain information, wherein the target rotor mass is the rotor mass that is less than the rotor mass standard value. Alternatively, when the rotor is a rigid rotor and the rotor is in a stationary state, the information layer data includes the corresponding relationship between the rotor mass center and the rotation center line, and the corresponding relationship between the rotor mass center and the rotation center line includes that the rotor mass center is on the rotation center line or the rotor mass center is not on the rotation center line; when the rotor mass center is on the rotation center line, the rotor mass is balanced; when the rotor mass center is not on the rotation center line, the rotor mass is unbalanced; the computing device may determine whether the corresponding relationship between the rotor mass center and the rotation center line is data corresponding to the quality defect type unbalance fault action chain information based on the corresponding relationship between the rotor mass center and the rotation center line. Alternatively, when the rotor is a rigid rotor and the rotor is in a rotating state, the information layer data includes a vibration value, and when the rotor mass is unbalanced, the vibration value will increase significantly, and the computing device may determine whether the vibration value is data corresponding to the quality defect type unbalance fault action chain information based on the vibration value. The data corresponding to the mass defect type unbalance fault action chain includes data such as rotor mass, the correspondence between the rotor center of mass and the rotation center line, or vibration value. Other data may also correspond based on the rotor type and rotor state, and this application is not limited to this.

[0060] If there is material attached to the rotor, it will cause the rotor mass to be unbalanced, and it will also cause rotational imbalance when the rotor rotates; if the material is still attached to the rotor, it will cause the rotor mass imbalance to decrease or the rotor mass imbalance to increase, and it will also cause the rotational imbalance to decrease or increase when the rotor rotates. Material adhesion imbalance action chain: material adhesion → rotor mass imbalance → continued adhesion → ① the rotor mass imbalance decreases or ② the rotor mass imbalance increases. The data corresponding to the material adhesion imbalance action chain can be determined according to the type of rotor and the state of the rotor. When the rotor is a rigid rotor and the rotor is in a stationary state, the information layer data includes the correspondence between the rotor center of mass and the rotation center line. If the rotor mass is balanced, the correspondence between the rotor center of mass and the rotation center line is completely corresponding; if the rotor mass is unbalanced, the degree of imbalance can be divided. For example, when the first level is unbalanced, the rotor center of mass and the rotation center line are slightly inconsistent, and the correspondence between the rotor center of mass and the rotation center line is the first level of non-correspondence; when the second level is unbalanced, the non-correspondence between the rotor center of mass and the rotation center line increases, and the correspondence between the rotor center of mass and the rotation center line is the second level of non-correspondence, etc. The computing device can determine whether the correspondence between the multiple rotor mass centers and the rotation center line is data corresponding to the material adhesion unbalanced action chain based on the correspondence between the multiple rotor mass centers and the rotation center line in the second time period. When the correspondence between the multiple rotor mass centers and the rotation center line tends to increase gradually in time sequence, it indicates that the rotor mass imbalance increases, and the correspondence between the multiple rotor mass centers and the rotation center line is data corresponding to the material adhesion unbalanced action chain; or, when the correspondence between the multiple rotor mass centers and the rotation center line tends to decrease gradually in time sequence, it indicates that the rotor mass imbalance decreases, and the correspondence between the multiple rotor mass centers and the rotation center line is data corresponding to the material adhesion unbalanced action chain; or, the correspondence between the multiple rotor mass centers and the rotation center line is a complete correspondence, indicating that the correspondence between the multiple rotor mass centers and the rotation center line is not data corresponding to the material adhesion unbalanced action chain. When the rotor is a rigid rotor and the rotor is in a rotating state, the information layer data includes multiple vibration values ​​in the second time period, and the computing device can determine whether the multiple vibration values ​​are data corresponding to the material adhesion unbalanced action chain based on the multiple vibration values ​​in the second time period. The data corresponding to the material adhesion unbalanced action chain includes data such as the correspondence between the rotor center of mass and the rotation center line or the vibration value, and can also correspond to other data based on the type of rotor and the state of the rotor, which is not limited in this application.

[0061] Rotor misalignment includes the misalignment of the connection between the rotors, which is mainly reflected in the alignment of the coupling, and the signal characteristics on both sides of the coupling are the strongest. When the rotor is unbalanced and the imbalance increases, the rotor alignment state will be destroyed, and finally the rotor misalignment fault will occur. Misalignment fault action chain: If there is rotor imbalance, the imbalance increases → the alignment state is destroyed → misalignment. Rotor misalignment can be divided into at least one of parallel misalignment, angular misalignment, concurrent misalignment or skew misalignment. The data corresponding to the misalignment fault action chain information can be determined based on the rotor misalignment situation. For example, frequency analysis and phase measurement are used to diagnose the misalignment situation. The information layer data includes at least one of frequency characteristic data, vibration direction characteristic data, amplitude relationship data and vibration phase data. The amplitude relationship data includes amplitude and load relationship data, and / or the amplitude relationship data includes amplitude and speed relationship.

[0062] When the rolling bearing is poorly lubricated, there is too much or too little grease in the rolling bearing, which causes the bearing vibration (effective value) to increase, and then causes the bearing temperature to rise. The action chain of poor rolling bearing lubrication: too much or too little grease → increased bearing vibration (effective value) → increased bearing temperature. The information layer data includes rolling bearing vibration data and rolling bearing temperature, and vibration and temperature are used to jointly monitor the status of the rolling bearing. The action chain information of poor rolling bearing lubrication includes rolling bearing vibration data that is not within the normal rolling bearing vibration threshold range and rolling bearing temperature that is not within the normal rolling bearing temperature threshold range.

[0063] When a rolling bearing has a local fault, the characteristic frequency of the rolling bearing will change from ultra-high frequency to high frequency, and then from high frequency to low frequency. The action chain of the local fault of the rolling bearing: ultra-high frequency characteristic → high frequency characteristic (characteristic frequency component of the bearing) → low frequency characteristic (failure stage). The information layer data includes the characteristic frequency of the rolling bearing. The action chain information of the local fault of the rolling bearing includes at least one of the characteristic frequency of the ultra-high frequency rolling bearing, the characteristic frequency of the high frequency rolling bearing and the characteristic frequency of the low frequency rolling bearing.

[0064] When there are defects in the gear, the amplitude of the meshing frequency and its higher harmonics will increase, that is, the amplitude will increase; and its vibration signal will be modulated to form a sideband centered on the meshing frequency. The shape and distribution of the sideband reflect the type and degree of gear defects. As the gear meshing becomes worse, especially when the gear is damaged by pitting, spalling, etc., these damages will manifest themselves in the meshing frequency and its harmonic components, resulting in an increase in the amplitude of the sideband, and the energy of the sidefrequency family will continue to increase. Gear meshing fault action chain: gear meshing fault → gear meshing frequency and its harmonics → gear meshing frequency and sidefrequency family → sidefrequency family energy continues to increase. Gear meshing fault action chain information includes at least one of abnormal gear meshing frequency, abnormal harmonics and abnormal sidefrequency family energy.

[0065] During the operation of the diagnostic object, there will be unstable operation and vibration. For example, the diagnostic object includes gears. If the lubricating oil quality of the gear is poor, the gear will heat up and the gear temperature will rise. When the fault increases, abnormal noise will be generated. The gear temperature will rise to a high temperature, and finally, the gear will fail completely. The general timing action chain: vibration → oil quality → temperature → abnormal noise → high temperature → failure. The information sources include vibration signals, temperature and operating sounds. The general timing action chain information includes abnormal vibration signals, abnormal temperature and abnormal operating sounds.

[0066] In a possible implementation, step 102 also includes: step 103: when a fault occurs in the computing device, the cause of the fault of the diagnosis object is analyzed according to the characteristic quantity information and the action chain information to generate the fault cause.

[0067] In some embodiments, when a fault occurs in a diagnostic object, at least one target action chain information corresponding to the fault point is determined; at least one target characteristic quantity information corresponding to the fault point is determined; the fault is analyzed based on at least one target action chain information and at least one target characteristic quantity information, and based on the action chain information, the data of the problem at the beginning of the fault, the evolution process of the fault, and the time of the fault can be obtained; based on the characteristic quantity information, the time domain, tendency, change rate, etc. of the data can be obtained.

[0068] In a possible implementation, step 102 further includes: step 104: the computing device predicts the fault of the diagnosis object according to the feature quantity information and generates a fault prediction result.

[0069] In some embodiments, when it is necessary to predict faults of a diagnostic object, the computing device predicts the evolution of the diagnostic object data based on characteristic information to obtain a fault prediction result to diagnose at least one of the equipment's potential mechanical faults, operational faults, and performance faults.

[0070] An embodiment of the present specification provides a method for generating fault information, wherein the fault information is information involved in analyzing a fault, and the fault information includes characteristic quantity information and / or action chain information. Within the information source range corresponding to the diagnosis object, information layer data is obtained; features are extracted from the information layer data to generate characteristic quantity information; and / or, according to a preset action chain, action chain information is generated based on the information layer data to analyze the fault using the characteristic quantity information and / or action chain information, so that the computing device can obtain data from multiple dimensions in real time within the information source range corresponding to the diagnosis object to obtain information layer data; multi-dimensional analysis is performed on the information layer data to capture changes and tendencies of these data, and obtain characteristic quantity information and / or action chain information for analyzing the fault.

[0071] Corresponding to the above method embodiment, this specification also provides an embodiment of a device for generating fault information. Figure 3 is a schematic diagram of a structure of a device for generating fault information provided by an embodiment of the present specification, wherein the fault information is information involved in analyzing a fault, and the fault information includes feature quantity information and / or action chain information, such as Figure 3 As shown, the device comprises: The acquisition module 301 is configured to: acquire information layer data within the information source range corresponding to the diagnosis object; the generation module 302 is configured to: extract features from the information layer data, generate feature quantity information, and / or, according to a preset action chain, generate action chain information based on the information layer data, so as to analyze the fault using the feature quantity information and / or action chain information.

[0072] In a possible implementation, the device further includes: an analysis module 303. The analysis module 303 is connected to the generation module 302. The analysis module 303 is configured to: when a fault occurs, analyze the cause of the fault of the diagnosis object according to the feature quantity information and the action chain information, and generate the fault cause.

[0073] In a possible implementation, the device further includes: a prediction module 304. The prediction module 304 is connected to the generation module 302. The prediction module 304 is configured to: predict the fault of the diagnosis object according to the feature quantity information, and generate a fault prediction result.

[0074] In a possible implementation manner, the information layer data includes at least one of host layer data, auxiliary machine layer data, and environment layer data.

[0075] In one possible implementation, feature extraction includes at least one of time domain feature extraction, frequency domain feature extraction, amplitude domain feature extraction, operating condition feature extraction, stability tendency feature extraction, environmental feature extraction, baseline parameter feature extraction, current value feature extraction, change rate feature extraction, cumulative change rate feature extraction and numerical tendency feature extraction.

[0076] In one possible implementation, the action chain includes at least one of a timing action chain of rotating stall and surge, a timing action chain of turbine water hammer, a mass defect type unbalance fault action chain, a material adhesion unbalance action chain, a misalignment fault action chain, a rolling bearing poor lubrication action chain, a rolling bearing local fault action chain, a gear meshing fault action chain and a general timing action chain.

[0077] In one possible implementation, the information layer data includes compressor inlet flow, the action chain includes rotating stall and surge action chains, and the action chain information includes rotating stall and surge action chain information; the generation module 302 is configured to: determine the compressor rotational stall based on the compressor inlet flow being less than a critical value, and determine the compressor inlet flow as data corresponding to the rotating stall and surge action chain; add the compressor inlet flow to the rotating stall and surge action chain information.

[0078] An embodiment of the present specification provides a device for generating fault information, wherein the fault information is information involved in analyzing a fault, and the fault information includes characteristic quantity information and / or action chain information. The acquisition module is configured to acquire information layer data within the information source range corresponding to the diagnostic object; the generation module is configured to extract features from the information layer data, generate characteristic quantity information, and / or, according to a preset action chain, generate action chain information based on the information layer data, so as to analyze the fault using the characteristic quantity information and / or the action chain information. Thus, the computing device can acquire data from multiple dimensions in real time within the information source range corresponding to the diagnostic object to obtain information layer data; perform multi-dimensional analysis on the information layer data, capture the changes and tendencies of these data, and obtain characteristic quantity information and / or action chain information for analyzing the fault.

[0079] The above is a schematic scheme of a fault information generation device of this embodiment. It should be noted that the technical scheme of the fault information generation device and the technical scheme of the fault information generation method described above belong to the same concept, and the details not described in detail in the technical scheme of the fault information generation device can be referred to the description of the technical scheme of the fault information generation method described above.

[0080] Figure 4 4 is a block diagram of a computing device 400 provided in one embodiment of the present specification. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and a database 450 is used to store data.

[0081] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0082] In one embodiment of the present specification, the above components of the computing device 400 and Figure 4 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 4 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0083] The computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 400 may also be a mobile or stationary server.

[0084] The processor 420 is used to execute the following computer executable instructions, which implement the steps of the above-mentioned method for generating fault information when the computer executable instructions are executed by the processor. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned method for generating fault information belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be found in the description of the technical scheme of the above-mentioned method for generating fault information.

[0085] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for generating fault information.

[0086] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned method for generating fault information belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned method for generating fault information.

[0087] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for generating fault information.

[0088] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned method for generating fault information are of the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above-mentioned method for generating fault information.

[0089] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0091] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0092] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0093] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A method for generating fault information, characterized in that: Fault information is information involved in analyzing a fault, and the fault information includes feature quantity information and / or action chain information. The method includes: Acquire information layer data within the scope of the information source corresponding to the diagnosis object; Extract features from the information layer data to generate feature quantity information; and / or generate action chain information based on the information layer data according to a preset action chain, so as to analyze the fault using the feature quantity information and / or the action chain information.

2. The method according to claim 1, characterized in that After extracting features from the information layer data to generate feature quantity information, and generating action chain information according to the information layer data according to a preset action chain, the method further includes: When a fault occurs, the cause of the fault of the diagnosis object is analyzed according to the feature quantity information and the action chain information to generate the fault cause.

3. The method according to claim 1, characterized in that After generating the feature information, the method further includes: A fault of the diagnosis object is predicted based on the feature quantity information to generate a fault prediction result.

4. The method according to claim 1, characterized in that The information layer data includes at least one of host layer data, auxiliary layer data and environment layer data.

5. The method according to claim 1, characterized in that The feature extraction includes at least one of time domain feature extraction, frequency domain feature extraction, amplitude domain feature extraction, operating condition feature extraction, stability tendency feature extraction, environmental feature extraction, reference parameter feature extraction, current value feature extraction, change rate feature extraction, cumulative change rate feature extraction and numerical tendency feature extraction.

6. The method according to claim 1, characterized in that The action chain includes at least one of a timing action chain of rotating stall and surge, a timing action chain of turbine water hammer, a mass defect type unbalance fault action chain, a material adhesion unbalance action chain, a misalignment fault action chain, a rolling bearing poor lubrication action chain, a rolling bearing local fault action chain, a gear meshing fault action chain and a general timing action chain.

7. The method according to claim 1, characterized in that The information layer data includes compressor inlet flow, the action chain includes rotating stall and surge action chain, and the action chain information includes rotating stall and surge action chain information; Correspondingly, generating action chain information according to the information layer data according to the preset action chain includes: Based on the compressor inlet flow being less than a critical value, determining that the compressor is in rotational stall, and determining that the compressor inlet flow is data corresponding to the rotational stall and surge action chain; The compressor inlet flow is added to the rotating stall and surge action chain information.

8. A device for generating fault information, characterized in that: Fault information is information involved in analyzing a fault, and the fault information includes feature quantity information and / or action chain information. The device includes: An acquisition module is configured to acquire information layer data within the range of information sources corresponding to the diagnosis object; The generation module is configured to extract features from the information layer data, generate feature quantity information, and / or generate action chain information based on the information layer data according to a preset action chain, so as to analyze the fault using the feature quantity information and / or the action chain information.

9. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for generating fault information according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method for generating fault information according to any one of claims 1 to 7.

Images