Instrument fault diagnosis method, system, electronic device and readable storage medium

Abstract

The present invention relates to an instrument fault diagnosis method, system, electronic device, and readable storage medium. The method comprises obtaining self-test data and detection data of an industrial instrument, wherein the self-test data is the operating data of the industrial instrument, and the detection data is the data of the industrial instrument detecting equipment or products in the production process; filtering the self-test data according to data selection rules to determine fault analysis data; determining fluctuation data of the fault analysis data according to the fault analysis data and data fluctuation calculation rules; determining abnormal parameters according to the fluctuation data and the fault analysis rules; and outputting abnormal prompt information according to the abnormal parameters and abnormal prompt rules. By analyzing the fluctuation of the data, the present invention improves the problem of false positives and missed negatives of abnormal conditions of the industrial instrument itself.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and in particular to an instrument fault diagnosis method, system, electronic device, and readable storage medium. Background Art

[0002] With the development of technology, the number of industrial instruments used in industrial production processes is increasing. Factories use industrial instruments to detect production processes, product quality, operating conditions, environmental protection indicators, etc., thereby providing a data basis for the control system.

[0003] At present, industrial instruments tend to be intelligent. In addition to detection functions, intelligent industrial instruments also have self-diagnosis functions. They can detect their own faults while detecting data from other equipment. At present, intelligent industrial instruments can only detect faults when a certain parameter of the intelligent industrial instrument is not within the preset threshold range. The fault detection is relatively simple, which may lead to false alarms and missed alarms of abnormal conditions of intelligent industrial instruments.

[0004] The above-mentioned existing technical solutions have the following defects: the self-diagnosis function of the industrial instrument has the problem of false alarms and missed alarms for its own abnormal conditions. Summary of the Invention

[0005] In order to improve the problem of false alarms and missed alarms of abnormal conditions of industrial instruments, the present application provides an instrument fault diagnosis method, system, electronic device and readable storage medium.

[0006] In a first aspect of the present application, a method for diagnosing instrument faults is provided. The method comprises:

[0007] Acquire self-test data and test data of industrial instruments, wherein the self-test data is the working operation data of the industrial instruments, and the test data is the data of the industrial instruments testing equipment or products in the production process;

[0008] Screening the self-test data according to data selection rules to determine fault analysis data;

[0009] Determining fluctuation data of the fault analysis data according to the fault analysis data and a data fluctuation calculation rule;

[0010] Determining abnormal parameters based on the fluctuation data and fault analysis rules;

[0011] Output abnormal prompt information according to the abnormal parameters and abnormal prompt rules.

[0012] As can be seen from the above technical solution, after obtaining the self-test data and detection data of the industrial instrument, a preliminary screening of the data is performed. By screening the data, the accuracy of subsequent calculations can be improved while reducing the amount of calculation. The fluctuation calculation is performed on the screened data to determine the fluctuation data. Then, the fault condition of the industrial instrument is analyzed based on the fluctuation data. Each fault condition has a corresponding abnormal parameter. The corresponding abnormal parameter is determined by analyzing the fluctuation data. The corresponding fault abnormality processing method is called based on the abnormal parameter and the corresponding prompt information is output. By analyzing the fluctuation of the fault analysis data, the corresponding fault condition can be obtained, which to a certain extent reduces the problem of false alarms or omissions of abnormal conditions of the industrial instrument itself.

[0013] In a possible implementation, screening the self-test data according to a data selection rule to determine the fault analysis data includes:

[0014] Classifying the self-inspection data according to preset classification rules;

[0015] According to the preset data time range, each type of self-test data is screened to determine the fault analysis data.

[0016] From the above technical solution, it can be seen that the self-test data obtained is first classified according to the data type, and the classified data is filtered according to the preset filtering rules to determine the fault analysis data. The classification and filtering of the data can reduce the subsequent data calculation amount. At the same time, the filtered data can make the final calculated result closer to the data situation in the real-time state, providing a data basis for improving the accuracy of fault analysis.

[0017] In a possible implementation, determining the fluctuation data of the fault analysis data according to the fault analysis data and a data fluctuation calculation rule includes:

[0018] The fluctuation data includes parameter fluctuation data and overall fluctuation data;

[0019] Calculating the standard deviation of each type of fault analysis data, wherein the standard deviation is the parameter fluctuation data;

[0020] Calculate the parameter dispersion coefficient of each type of fault analysis data;

[0021] The overall fluctuation data is calculated based on the preset coefficient selection rules and the parameter dispersion coefficient.

[0022] In a possible implementation, determining abnormal parameters according to the fluctuation data and fault analysis rules includes:

[0023] The abnormal parameters include a first abnormal parameter and a second abnormal parameter;

[0024] When the parameter fluctuation data is not within the preset fluctuation range, determining whether the overall fluctuation data is within the overall fluctuation range;

[0025] If not, the detection module corresponding to the parameter fluctuation data has a first abnormality;

[0026] If so, then the production process corresponding to the fluctuation data has a second anomaly;

[0027] According to a preset abnormal parameter correspondence table, the first abnormality and the second abnormality, a first abnormality parameter and a second abnormality parameter are determined.

[0028] As can be seen from the above technical solution, by using parameter fluctuation data to determine the fluctuation of this type of data, it is possible to determine whether there is a sudden change in the data of a certain parameter. When there is a sudden change, it indicates that there may be a problem with the module detecting this type of data. The overall fluctuation data is then determined. If the above overall fluctuation data indicates that the data has not fluctuated significantly, it means that all data may have changed. In this case, it may indicate that all self-test data has changed due to changes in the process flow of industrial instrument detection. By calculating the fluctuation of a certain type of data and the overall fluctuation of all data to analyze possible faults of industrial instruments, the predicted fault results are made more accurate, and to a certain extent, the problem of false positives and missed negatives can be reduced.

[0029] In a possible implementation, the method further includes:

[0030] The abnormal parameters include a third abnormal parameter;

[0031] When the parameter fluctuation data is within the preset fluctuation range, determining whether the self-test data acquired in real time is within the self-test threshold range;

[0032] If not, a third abnormality exists in the detection module corresponding to the self-test data;

[0033] According to the preset abnormal parameter correspondence table and the third abnormality, a third abnormal parameter is determined.

[0034] In a possible implementation, outputting abnormal prompt information according to the abnormal parameters and abnormal prompt rules includes:

[0035] According to the abnormal parameters, the corresponding prompt strategy is called;

[0036] According to the prompt strategy, the self-test data and the test data are marked and corresponding abnormal prompt information is output.

[0037] In a possible implementation, the mark is a credibility label for the self-test data and the test data.

[0038] In a second aspect of the present application, an instrument fault diagnosis system is provided. The system comprises:

[0039] Data acquisition module, used to obtain self-test data and detection data of industrial instruments;

[0040] A data screening module, configured to determine fault analysis data based on data selection rules and the self-test data;

[0041] a fluctuation calculation module, configured to determine fluctuation data of the fault analysis data according to the fault analysis data and a data fluctuation calculation rule;

[0042] an abnormality determination module, configured to determine abnormal parameters based on the fluctuation data and fault analysis rules;

[0043] The abnormality prompt module is used to mark the self-test data and the detection data according to the abnormal parameters and abnormality prompt rules and output abnormality prompt information.

[0044] In a third aspect of the present application, an electronic device is provided, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor implements the above method when executing the program.

[0045] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect of the present application is implemented.

[0046] In summary, this application includes at least one of the following beneficial technical effects:

[0047] 1. First, obtain the self-test data and test data of the industrial instrument. After obtaining the self-test data and test data, perform a preliminary screening of the data, perform fluctuation calculation on the screened data, determine the fluctuation data, and then analyze the fault conditions of the industrial instrument based on the fluctuation data. Each fault condition has a corresponding abnormal parameter. The corresponding abnormal parameter is determined by analyzing the fluctuation data. The corresponding fault abnormality processing method is called based on the abnormal parameter and the corresponding prompt information is output. By analyzing the fluctuation of the fault analysis data, the corresponding fault condition can be obtained, which to a certain extent reduces the problem of false alarms or omissions of abnormal conditions of the industrial instrument itself;

[0048] 2. Parameter fluctuation data is used to determine the fluctuation of this type of data. Significant fluctuations indicate a possible problem with the module detecting this type of data. The overall fluctuation data is then determined. If the overall fluctuation data indicates no significant fluctuations, it indicates that all data may have changed. This may indicate that changes in the process flow of industrial instrumentation have caused changes in all self-test data. By calculating the fluctuation of a specific type of data and the overall fluctuation of all data, possible fault predictions for industrial instruments can be analyzed, making the predicted fault results more accurate and, to a certain extent, reducing the problem of false positives and missed negatives. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of the instrument fault diagnosis method provided by this application.

[0050] Figure 2 It is a structural diagram of the instrument fault diagnosis system provided by this application.

[0051] Figure 3 It is a structural diagram of the electronic device provided in this application.

[0052] In the figure, 200, instrument fault diagnosis system; 201, data acquisition module; 202, data screening module; 203, fluctuation calculation module; 204, abnormality determination module; 205, abnormality prompt module; 301, CPU; 302, ROM; 303, RAM; 304, I / O interface; 305, input part; 306, output part; 307, storage part; 308, communication part; 309, drive; 310, removable medium. DETAILED DESCRIPTION

[0053] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0055] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0056] An embodiment of the present application provides an instrument fault diagnosis method, and the main process of the above method is described as follows.

[0057] like Figure 1 As shown:

[0058] Step S101: Acquire self-test data and test data of industrial instruments.

[0059] Specifically, the above method is applied to an instrumentation and control system comprising one or more industrial instruments. The parameters of these industrial instruments include not only data detecting the status of certain process flows within the system, but also fault detection data of the industrial instruments themselves. The self-test data represents instrument fault data related to the industrial instrument itself, such as voltage, current, resistance, temperature, humidity, amplitude, and effective power. The detection data represents instrument detection data related to the status of the process flow within which the instrument resides, such as measurement high and low limit alarms, measurement rate alarms, measurement deviation alarms, and output high and low limit alarms. In one example, the self-test data and detection data are acquired by receiving data output by the industrial instrument via a wired or wireless transmission method. The data is transmitted via a bus such as Modbus, CANopen, EtherCAT, or PROFIBUS. In this example, the data transmission method is not strictly limited; any method capable of collecting data output by the industrial instrument is sufficient. Both the self-test data and detection data are updated in real time. That is, the industrial instrument outputs detected data in real time while it is operating, and data acquisition is based on the latest data.

[0060] Step S102: Determine fault analysis data according to data selection rules and self-test data.

[0061] Specifically, the self-test data is categorized based on the content monitored. Each category of self-test data is then screened based on the corresponding time range to determine fault analysis data. For example, if the self-test data includes the operating voltage and operating temperature of an industrial instrument, the operating voltage requires analysis of the most recent two hours of data, while the operating temperature requires analysis of the most recent three hours of data. Therefore, all self-test data is screened to determine operating voltage fault analysis data and operating temperature fault analysis data, as needed.

[0062] By screening the data, the calculated data is limited to a certain range. On the one hand, the amount of calculation in the fault determination process is reduced. On the other hand, different selection ranges correspond to different types of data, which can make the final calculated results closer to the data situation in real time, providing a data basis for improving the accuracy of fault analysis.

[0063] Step S103: determining fluctuation data of the fault analysis data according to the fault analysis data and data fluctuation calculation rules.

[0064] Specifically, the above-mentioned fluctuation data includes parameter fluctuation data and overall fluctuation data. For each type of fault analysis data, the corresponding standard deviation is calculated. The standard deviation is the parameter fluctuation data. The coefficient of dispersion of each type of fault analysis data is calculated. The coefficient of dispersion is the parameter dispersion coefficient. Based on all the parameter dispersion coefficients, the coefficient of dispersion of all parameter dispersion coefficients is calculated. The coefficient of dispersion is the overall fluctuation data. For each type of fault analysis data, the standard deviation is used to determine the fluctuation of this type of data, because the dimensions of the same type of data are the same. For the fluctuation of multiple types of data, the coefficient of dispersion is calculated to determine the overall fluctuation of the multiple types of data. Because the coefficient of dispersion is a dimensionless quantity, when comparing multiple groups of data with different dimensions, the coefficient of dispersion should be used to determine the fluctuation of the data. For example, the standard deviation of the operating voltage and the standard deviation of the operating temperature are determined. The standard deviation can reflect the fluctuation of the operating voltage and operating temperature data. By calculating the coefficient of dispersion of the operating voltage and operating temperature coefficient of dispersion, the coefficient of dispersion can reflect the fluctuation of the operating voltage and operating temperature data. The calculation method of the above-mentioned standard deviation and coefficient of dispersion is well known to those skilled in the art and will not be described in detail here.

[0065] Step S104: Determine abnormal parameters based on the fluctuation data and fault analysis rules.

[0066] Specifically, based on the parameter fluctuation data and the overall fluctuation data, abnormal parameters are determined. The abnormal parameters include a first abnormal parameter, a second abnormal parameter, and a third abnormal parameter. When the parameter fluctuation data is within the preset fluctuation range, it indicates that the data change of a certain parameter is relatively stable. Then, the latest data corresponding to the above parameter is obtained to determine whether the above latest data is within the self-test threshold range. If so, it indicates that the detection module corresponding to the above parameter has no abnormality. If not, it indicates that the detection module corresponding to the above parameter has an abnormality and the abnormality has lasted for a long time. The above abnormality is the third abnormality, and the abnormal parameter corresponding to the third abnormality is the third abnormal parameter. When the parameter fluctuation data is not within the preset fluctuation range, it indicates that the data change of a certain parameter has suddenly changed. Then, it is determined whether the overall fluctuation data is within the overall fluctuation range. If so, it indicates that other parameters have experienced data changes of similar magnitude, indicating that the above abnormal change may be related to changes in the process flow of industrial instrument detection. If the above abnormality is the second abnormality, the abnormal parameter corresponding to the second abnormality is the second abnormal parameter. If not, it indicates that only the data of the corresponding parameter has undergone a large change, while other data have not undergone the same degree of data change, indicating that the detection module detecting the corresponding parameter has an abnormality. The above abnormality is the first abnormality, and the abnormal parameter corresponding to the first abnormality is the first abnormal parameter. Each abnormality has a corresponding abnormal parameter. According to the preset abnormal parameter corresponding table, the abnormal parameter corresponding table includes abnormal conditions and their corresponding abnormal parameters. The corresponding abnormal conditions are returned according to the difference in abnormal parameters.

[0067] In one embodiment, the determination of the self-test threshold range further includes obtaining historical operating data, and determining a target prediction model based on the historical operating data and a preset training model. The above-mentioned historical operating data includes monitoring conditions, monitoring data, whether the data is abnormal, and an abnormality threshold. The above-mentioned monitoring conditions indicate that the industrial instrument needs to monitor the process flow and its working conditions. The monitoring data indicates the data monitored by the industrial instrument under the monitoring conditions. Whether the data is abnormal indicates whether the monitoring data is abnormal. The abnormality threshold indicates the abnormality threshold corresponding to the monitoring data under the monitoring conditions. The above-mentioned historical operating data is input into the preset training model, and the target prediction model can be obtained through model training. The target prediction model includes the corresponding relationship between the monitoring conditions, monitoring data, whether the data is abnormal, and the abnormality threshold. The corresponding abnormality threshold is determined by inputting the monitoring conditions, monitoring data, and whether the data is abnormal into the target prediction model. In this embodiment, the above-mentioned preset training model is a neural network model. In other embodiments, other training models can also be used, which is not limited here.

[0068] By training the target prediction model, the corresponding abnormal threshold can be determined according to the monitoring conditions, monitoring data and abnormal conditions of the industrial instrument. The abnormal threshold can be adaptively changed according to different detection conditions, thereby improving the accuracy of industrial instrument fault detection and reducing false alarms and missed faults to a certain extent.

[0069] In another embodiment, determining the self-test threshold range further includes obtaining historical abnormality data and determining the self-test threshold range based on the historical abnormality data and threshold calculation rules. The historical abnormality data includes monitoring conditions, abnormal data, monitoring time, abnormality data type, and instrument age. The monitoring conditions indicate that the industrial instrument needs to monitor the process flow and its operating conditions. Abnormal data refers to abnormal data detected by the industrial instrument under the monitoring conditions. Abnormal data type refers to the type of abnormal data detected, for example, the monitored data type may be current, voltage, power, etc. The monitoring time indicates the time when the abnormal data was acquired. The instrument age indicates the age of the industrial instrument. For example, if an industrial instrument has been in use for three years, the instrument age is three years. Abnormal data is classified based on the monitoring conditions, abnormality data type, and instrument age. Specifically, abnormal data with the same monitoring conditions, abnormality data type, and instrument age are processed. The abnormal data is sliced ​​according to the monitoring time, and the maximum and minimum values ​​of the abnormal data in each data slice are obtained. The minimum value among all maximum values ​​is used to obtain the maximum threshold value, and the maximum value among all minimum values ​​is used to obtain the minimum threshold value. The above maximum and minimum thresholds constitute the self-test threshold range.

[0070] By obtaining historical abnormal data and classifying the abnormal data according to the monitoring conditions, abnormal data type and instrument service life, and performing threshold calculation on the classified data, the impact of monitoring conditions and instrument service life on the detected abnormal data is reduced to a certain extent, and the accuracy of fault detection is improved to a certain extent.

[0071] By calculating the standard deviation of each type of data, namely the parameter fluctuation data, to determine the fluctuation of this type of data, we can determine whether there is a sudden change in the data of a certain parameter. When there is a sudden change, it means that there may be a problem with the module detecting this type of data. Then, the dispersion coefficient of each type of data, namely the parameter dispersion coefficient, is calculated. The dispersion coefficient of all parameter dispersion coefficients, namely the overall fluctuation data, is calculated. If the above overall fluctuation data indicates that the data has not fluctuated significantly, it means that all data may have changed. In this case, it may mean that all self-test data has changed due to changes in the process flow of industrial instrument detection. By calculating the fluctuation of a certain type of data and the overall fluctuation of all data to analyze the possible faults of industrial instruments, the predicted fault results are made more accurate and the problem of false positives and false negatives can be reduced to a certain extent.

[0072] Step S105: Output abnormal prompt information according to abnormal parameters and abnormal prompt rules.

[0073] Specifically, the corresponding prompt strategy is retrieved according to the abnormal parameters. When an abnormality occurs, the data detected by the industrial instrument is unavailable. The data detected by the industrial instrument is tagged with a credibility mark by different abnormal parameters. The self-test data and the detection data are tagged by the abnormal situation and the correlation between various data. In the subsequent use of the data, the data is filtered according to different needs by the credibility mark. Different abnormal prompt methods, i.e., the above-mentioned abnormal prompt information, are adopted for different abnormal situations, i.e., different abnormal parameters. A corresponding table of prompt information of abnormal parameters is pre-stored in the database. When an abnormality occurs, the corresponding prompt information is retrieved according to the abnormal parameters and a prompt is given. For example, when the working current has the first abnormality, the corresponding prompt information is retrieved and output, and then the data detected in the abnormal stage is tagged with credibility. The first abnormality in the working current may be due to a fault in the working current detection module of the working instrument, but it cannot be determined based solely on data analysis that the module is abnormal. However, when the current is abnormal, the voltage data may also be affected. In addition to marking the credibility of the current data, the voltage data in the same time period also needs to be marked with credibility. Depending on the fluctuation conditions reflected by the above-mentioned parameter fluctuation data, the credibility marking of its related data is also different. The correspondence between the above-mentioned fluctuation conditions and the data credibility of the corresponding parameters and their related parameters is pre-stored in a corresponding table in the database.

[0074] Instrument failures are identified through fluctuation data. Each instrument failure is assigned a corresponding fault parameter. Once the instrument failure type is determined based on data analysis, the fault parameter is also determined. Fault parameters and corresponding fault handling rules are pre-stored in the database. The corresponding fault handling rules are retrieved based on the fault parameters to provide abnormality prompts and data tagging. Based on the analysis results, the data from industrial instruments is labeled for credibility, providing a data foundation for future fault analysis or process data analysis.

[0075] The present application embodiment provides an instrument fault diagnosis system 200, referring to Figure 2 , the instrument fault diagnosis system 200 includes:

[0076] Data acquisition module 201, used to acquire self-test data and detection data of industrial instruments;

[0077] A data screening module 202 is configured to determine fault analysis data based on data selection rules and the self-test data;

[0078] Fluctuation calculation module 203, used to determine fluctuation data of the fault analysis data according to the fault analysis data and data fluctuation calculation rules;

[0079] An abnormality determination module 204 is used to determine abnormal parameters based on the fluctuation data and fault analysis rules;

[0080] The abnormality prompt module 205 is used to mark the self-test data and the detection data according to the abnormal parameters and abnormality prompt rules and output abnormality prompt information.

[0081] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0082] The embodiment of the present application discloses an electronic device. Figure 3 The electronic device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 307 to the random access memory (RAM) 303. Various programs and data required for system operation are also stored in the RAM 303. The CPU 301, ROM 302, and RAM 303 are connected to each other via a bus. An input / output (I / O) interface 304 is also connected to the bus.

[0083] The following components are connected to the I / O interface 304: an input section 305 including a keyboard, a mouse, and the like; an output section 306 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 307 including a hard disk; and a communication section 308 including a network interface card such as a LAN card or a modem. The communication section 308 performs communication processing via a network such as the Internet. A drive 309 is also connected to the I / O interface 304 as needed. Removable media 310, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 309 as needed, so that computer programs read therefrom can be installed into the storage section 307 as needed.

[0084] In particular, according to the embodiment of the present application, the above reference flow chart Figure 1 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product comprising a computer program carried on a machine-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 308 and / or installed from a removable medium 310. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the apparatus of the present application are performed.

[0085] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0086] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of application involved in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the aforementioned application concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions applied for in this application.

Claims

1. A method for diagnosing instrument faults, characterized in that: include: Acquire self-test data and test data of industrial instruments, wherein the self-test data is the working operation data of the industrial instruments, and the test data is the data of the industrial instruments testing equipment or products in the production process; Screening the self-test data according to data selection rules to determine fault analysis data; Determining fluctuation data of the fault analysis data according to the fault analysis data and a data fluctuation calculation rule; Determining abnormal parameters based on the fluctuation data and fault analysis rules; Outputting abnormal prompt information according to the abnormal parameters and abnormal prompt rules; The step of screening the self-test data according to the data selection rules to determine the fault analysis data includes: Classifying the self-inspection data according to preset classification rules; According to the preset data time range, each type of self-test data is screened to determine the fault analysis data; The determining, based on the fault analysis data and a data fluctuation calculation rule, fluctuation data of the fault analysis data includes: The fluctuation data includes parameter fluctuation data and overall fluctuation data; Calculating the standard deviation of each type of fault analysis data, wherein the standard deviation is the parameter fluctuation data; Calculate the parameter dispersion coefficient of each type of fault analysis data; Calculate overall fluctuation data based on preset coefficient selection rules and the parameter dispersion coefficient; According to the dispersion coefficients of all parameters, the dispersion coefficients of all parameter dispersion coefficients are calculated as the overall fluctuation data; Determining abnormal parameters according to the fluctuation data and fault analysis rules includes: The abnormal parameters include a first abnormal parameter and a second abnormal parameter; When the parameter fluctuation data is not within the preset fluctuation range, determining whether the overall fluctuation data is within the overall fluctuation range; If not, the detection module corresponding to the parameter fluctuation data has a first abnormality; If so, then the production process corresponding to the fluctuation data has a second anomaly; Determine a first abnormal parameter and a second abnormal parameter according to a preset abnormal parameter correspondence table, the first abnormality, and the second abnormality; The method further includes: The abnormal parameters include a third abnormal parameter; When the parameter fluctuation data is within the preset fluctuation range, determining whether the self-test data acquired in real time is within the self-test threshold range; If not, a third abnormality exists in the detection module corresponding to the self-test data; According to the preset abnormal parameter correspondence table and the third abnormality, a third abnormal parameter is determined.

2. The instrument fault diagnosis method according to claim 1, characterized in that: Outputting abnormal prompt information according to the abnormal parameters and abnormal prompt rules includes: According to the abnormal parameters, the corresponding prompt strategy is called; According to the prompt strategy, the self-test data and the test data are marked and corresponding abnormal prompt information is output.

3. The instrument fault diagnosis method according to claim 2, characterized in that: The mark is a credibility label for the self-test data and the test data.

4. An instrument fault diagnosis system, applied to the instrument fault diagnosis method according to any one of claims 1 to 3, characterized in that: include: A data acquisition module (201) is used to acquire self-test data and detection data of industrial instruments; A data screening module (202) is used to determine fault analysis data based on data selection rules and the self-test data; A fluctuation calculation module (203) is used to determine fluctuation data of the fault analysis data based on the fault analysis data and a data fluctuation calculation rule; An abnormality determination module (204), configured to determine abnormality parameters based on the fluctuation data and fault analysis rules; The abnormality prompt module (205) is used to mark the self-test data and the detection data according to the abnormality parameters and the abnormality prompt rules and output abnormality prompt information.

5. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 3.

Images