A device fault diagnosis dynamic modeling method, device and storage medium

Abstract

The application discloses a kind of equipment fault diagnosis dynamic modeling method, equipment and storage medium.The dynamic modeling method includes the following steps: constructing data interface table, for real-time acquisition and storage of data information to be processed, and the data information to be processed is obtained directly by connecting data interface to the diagnosed equipment;Construct a diagnosis model table, the diagnosis model table includes fault name, diagnosis standard and the data source information corresponding to the diagnosis standard.The application improves the flexibility of the equipment fault diagnosis system, while reducing the threshold for manufacturing enterprises to participate in intelligent manufacturing and equipment fault diagnosis, suitable for most discrete manufacturing enterprises.

Description

Technical Field

[0001] This invention relates to the field of equipment fault diagnosis technology, and in particular to a dynamic modeling method, equipment and storage medium for equipment fault diagnosis. Background Technology

[0002] Modern discrete manufacturing involves frequent business changes, high equipment acquisition frequency, and flexible and ever-changing production tasks and environments. However, most existing equipment fault diagnosis systems are only designed for a specific type of equipment, and their diagnostic models are singular and fixed and cannot be modified. This makes it difficult for the system to adapt to changes in production tasks, environments, and equipment, resulting in insufficient system flexibility and limiting its applicability to various situations. Summary of the Invention

[0003] In view of the above-mentioned defects or deficiencies in the existing technology, it is desirable to provide a dynamic modeling method, device and storage medium for equipment fault diagnosis, which improves the flexibility of the equipment fault diagnosis system, and at the same time lowers the threshold for manufacturing enterprises to participate in intelligent manufacturing and equipment fault diagnosis, and is applicable to most discrete manufacturing enterprises.

[0004] The present invention provides a dynamic modeling method for equipment fault diagnosis, comprising the following steps:

[0005] A data interface table is constructed to acquire and store data information to be processed in real time. The data information to be processed is obtained directly from the data interface connected to the device being diagnosed.

[0006] A diagnostic model table is constructed, comprising a fault name, diagnostic criteria, and data source information corresponding to the criteria. The diagnostic criteria include defined indicator information, defined diagnostic rules, and defined standard information. The data source information includes the name of the data interface table containing the data to be processed related to the indicator information, the field information in the data interface table containing the data to be processed related to the indicator information, and the calculation method information for calculating the result value of the indicator information. The diagnostic rules include basic rules and correlation rules. The basic rules are rules for diagnosing equipment faults based on the result value of one of the indicator information. The correlation rules are rules for diagnosing equipment faults based on the result value of a primary indicator when the result value of a correlation indicator meets the requirements. The correlation indicator is at least one item from the indicator information, and the primary indicator is at least one item from the indicator information.

[0007] A diagnostic rule standard table is constructed, comprising a dedicated diagnostic rule standard table and a general diagnostic rule standard table. The dedicated diagnostic rule standard table includes equipment name information, fault name, diagnostic rule, standard information, and corresponding fault level, and is used only for calling the diagnostic model table for a specific type of equipment. The general diagnostic rule standard table includes fault name, diagnostic rule, standard information, and corresponding fault level, and is used for calling the diagnostic model table for multiple types of equipment. When constructing the diagnostic model table, the fault name, diagnostic rule, standard information, and corresponding fault level from the dedicated diagnostic rule standard table and / or the general diagnostic rule standard table selected by the user are imported into the diagnostic model table.

[0008] Furthermore, the modeling method also includes the following steps:

[0009] Construct a preprocessing index table; the preprocessing index table stores index information that is related to the calculation of the result values ​​of the index information in the diagnostic model table but is not included in the diagnostic model table;

[0010] The preprocessing index table includes the set index information and the data source information corresponding to the index information.

[0011] Furthermore, the modeling method also includes the following steps:

[0012] Several calculation models are constructed. When constructing the diagnostic model table, the calculation method information corresponding to the indicator information is determined by the name of the calculation model selected by the user. That is, the result value of the indicator information is obtained by the calculation of the data information to be processed or the result value of other indicator information through the calculation model selected by the user.

[0013] Furthermore, the calculation model includes a maximum value model, a minimum value model, a mean value model, a summation model, a root mean square error model, and a formula calculation model.

[0014] Furthermore, the indicator information in the preprocessing indicator table and the diagnostic model table includes indicator name information and corresponding indicator number information; the formula calculation model is represented by the indicator number information and calculation symbols.

[0015] Furthermore, the field information includes a device information field and a data source identifier field.

[0016] Additionally, the present invention provides a device including a memory and a processor; the memory stores a computer program that can run on the processor, and when the processor executes the computer program, it implements the steps of the above-described dynamic modeling method for device fault diagnosis.

[0017] In addition, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described dynamic modeling method for equipment fault diagnosis.

[0018] Compared with the prior art, the beneficial effects of the present invention are:

[0019] Addressing the characteristics of frequent business changes and high equipment introduction frequency in modern discrete manufacturing, this invention can dynamically configure the required models for different equipment types. Based on actual equipment diagnostic needs, a fault diagnosis model is constructed using applicable threshold judgment rules, character comparison rules, and custom function rules, among other diagnostic standards. This improves the flexibility of the equipment fault diagnosis system while lowering the barrier to entry for intelligent manufacturing and equipment fault diagnosis in the manufacturing industry, making it suitable for most discrete manufacturing enterprises.

[0020] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of the present invention, nor is it intended to restrict the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0022] Figure 1 A flowchart for a dynamic modeling method for equipment fault diagnosis. Detailed Implementation

[0023] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] Please refer to Figure 1 The embodiments of the present invention provide a dynamic modeling method for equipment fault diagnosis. Taking the fault diagnosis modeling of a type A motor as an example, the method includes the following steps:

[0026] A data interface table is constructed to acquire and store data information to be processed in real time. The data information to be processed is obtained directly from the device being diagnosed by connecting the data interface. The data information to be processed includes the real-time temperature and real-time speed of the A-type motor during operation.

[0027] Construct a diagnostic model table, which includes the fault name, diagnostic criteria, and data source information corresponding to the diagnostic criteria. For example, the fault name is: abnormal high temperature; the diagnostic criterion is the result value of the average temperature > 60℃; and the data source information is: data interface table; see Table 1 for details.

[0028] Table 1: Fault Diagnosis Model for Type A Motors

[0029]

[0030] The diagnostic criteria include the set indicator information (average temperature), the set diagnostic rules (>), and the set standard information (60℃).

[0031] The data source information includes the name of the data interface table (data interface table) where the data to be processed related to the indicator information is located, the field information (temperature) in the data interface table where the data to be processed related to the indicator information is located, and the calculation method information (mean calculation model) used to calculate the result value of the indicator information.

[0032] In a preferred embodiment, the diagnostic rules include basic rules and associated rules; the basic rules are rules for diagnosing equipment faults based on the result value of an indicator; the associated rules are rules for diagnosing equipment faults based on the result value of a main indicator when the result value of an associated indicator meets the requirements; the associated indicator is at least one of the indicator information, and the main indicator is at least one of the indicator information.

[0033] In this embodiment, some faults can be diagnosed using the result value of an indicator, which is called the basic rule, as detailed in Table 2.

[0034] Table 2: Basic Rule Definition Table

[0035]

[0036] The same diagnostic rule can be set with different standard information according to needs. For example, the basic rule 1, the result value of the average temperature is >60℃, can also be set to the result value of the average temperature is >50℃.

[0037] Other fault diagnoses require the results of two or more indicators, including related indicators and primary indicators. Taking the abnormal fault of excessive vibration frequency in a type A motor as an example, the related indicators are average speed and running time, and the primary indicator is the highest vibration frequency. If the temperature result of the related indicator meets the standard information (average speed result < 60 rpm and running time result > 20 h), the fault is diagnosed by the result of the primary indicator (whether the highest vibration frequency result is greater than 100 μm), as detailed in Table 3.

[0038] Table 3: Association Rule Definition Table

[0039]

[0040] In a preferred embodiment, the modeling method further includes the following steps:

[0041] Construct a diagnostic rule standard table, which includes a dedicated diagnostic rule standard table and a general diagnostic rule standard table;

[0042] The dedicated diagnostic rule standard table includes equipment name information, fault name, diagnostic rule, standard information and corresponding fault level. It is only used for calling the diagnostic model table for one corresponding equipment. See Table 4 for details. The general diagnostic rule standard table includes fault name, diagnostic rule, standard information and corresponding fault level. It is used for calling the diagnostic model table for multiple types of equipment.

[0043] When constructing the diagnostic model table, the rule names, fault names, diagnostic rules, standard information, and corresponding fault levels from the user-selected dedicated diagnostic rule standard table and / or general diagnostic rule standard table are imported into the diagnostic model table.

[0044] Table 4: Standard Table of Special Diagnostic Rules

[0045]

[0046] In this embodiment, a dedicated diagnostic rule standard table and a general diagnostic rule standard table are pre-built, allowing them to be directly called when building the diagnostic model table. This enables the reuse of information from the general diagnostic rule standard table, improving the modeling efficiency of the diagnostic model.

[0047] In a preferred embodiment, the modeling method further includes the following steps:

[0048] Construct a preprocessing index table; the preprocessing index table stores index information that is related to the calculation of the result values ​​of the index information in the diagnostic model table but is not included in the diagnostic model table. The preprocessing index table includes the set index information and the data source information corresponding to the index information, as detailed in Table 5.

[0049] Table 5: Preprocessing Indicators

[0050]

[0051] Taking the abnormal low resistance in the diagnostic model table as an example, it needs to be obtained through the calculation of average voltage and average current. However, the average voltage and average current are not in the diagnostic model table. Therefore, the average voltage and average current information are defined in the preprocessing index table for the diagnostic model table to call.

[0052] In a preferred embodiment, the modeling method further includes the following steps:

[0053] Several calculation models are constructed. When constructing the diagnostic model table, the result value of the corresponding indicator information is determined by the name of the calculation model selected by the user. The result value of the data information to be processed or other indicator information is obtained by the calculation model selected by the user. The calculation models include the maximum value model, the minimum value model, the mean value model, the summation model, the standard deviation model, and the formula calculation model.

[0054] The maximum value model involves calculating the maximum value in a set of data.

[0055] The minimum value model is to calculate the minimum value in a set of data;

[0056] The mean-finding model calculates the average of a set of data.

[0057] The summation model calculates the sum of a set of data;

[0058] The mean squared error model is used to calculate the mean squared error of a set of data.

[0059] The formula calculation model allows users to customize calculation formulas according to their calculation needs.

[0060] In a preferred embodiment, the indicator information in the preprocessing indicator table and the diagnostic model table includes indicator name information and corresponding indicator number information; the formula calculation model is represented by indicator number information and calculation symbols.

[0061] In a preferred embodiment, the field information includes a device name information field and a data source identifier field.

[0062] Additionally, embodiments of the present invention also provide a device, including a memory and a processor; the memory stores a computer program that can run on the processor, and when the processor executes the computer program, it implements the steps of the above-described dynamic modeling method for device fault diagnosis.

[0063] Furthermore, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described dynamic modeling method for equipment fault diagnosis.

[0064] In the description of this specification, the terms "one embodiment," "some embodiments," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0065] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A dynamic modeling method for equipment fault diagnosis, characterized in that, The method comprises the following steps: a data interface table is constructed for real-time acquisition and storage of to-be-processed data information, which is obtained directly from a diagnosed device through a data interface connection; a diagnosis model table is constructed, which comprises fault names, diagnosis standards, and data source information corresponding to the diagnosis standards; the diagnosis standards comprise set index information, set diagnosis rules, and set standard information; the data source information comprises a data interface table name where to-be-processed data information related to the index information is located, field information in the data interface table where to-be-processed data information related to the index information is located, and calculation method information for calculating a result value of the index information; the diagnosis rules comprise a basic rule and an associated rule; the basic rule is a rule for diagnosing a fault of a device through a result value of one of the index information; the associated rule is a rule for diagnosing a fault of a device according to a result value of a main index when a result value of an associated index meets a requirement; the associated index is at least one of the index information, and the main index is at least one of the index information; a diagnosis rule standard table is constructed, which comprises a special diagnosis rule standard table and a general diagnosis rule standard table; the special diagnosis rule standard table comprises device name information, fault names, diagnosis rules, standard information, and corresponding fault levels, and is used only for calling a diagnosis model table of one corresponding device; the general diagnosis rule standard table comprises fault names, diagnosis rules, standard information, and corresponding fault levels, and is used for calling diagnosis model tables of multiple devices; when the diagnosis model table is constructed, the fault names, diagnosis rules, standard information, and corresponding fault levels in the diagnosis rule standard table are imported into the diagnosis model table by acquiring user-selected special diagnosis rule standard tables and / or general diagnosis rule standard tables.

2. The dynamic modeling method for equipment fault diagnosis according to claim 1, characterized in that, The method further comprises the following steps: a preprocessing index table is constructed; the preprocessing index table stores index information related to calculation of result values of index information in the diagnosis model table and not contained in the diagnosis model table; the preprocessing index table comprises set index information and data source information corresponding to the index information.

3. The dynamic modeling method for equipment fault diagnosis according to claim 2, characterized in that, The method further comprises the following steps: a plurality of calculation models are constructed; when the diagnosis model table is constructed, calculation method information corresponding to index information is determined by a user-selected name of a calculation model, that is, a result value of the index information is obtained by calculation of to-be-processed data information or result values of other index information through the user-selected calculation model.

4. The device failure diagnosis dynamic modeling method according to claim 3, characterized by, The calculation models comprise a maximum value calculation model, a minimum value calculation model, a mean value calculation model, a sum calculation model, a mean square deviation calculation model, and a formula calculation model.

5. The device failure diagnosis dynamic modeling method according to claim 4, characterized in that, The index information in the preprocessing index table and the diagnosis model table comprises index name information and corresponding index number information; the formula calculation model is represented by the index number information and a calculation symbol.

6. The method of claim 1, wherein, The field information comprises device name information fields and data source identification fields.

7. An apparatus, comprising: An equipment fault diagnosis dynamic modeling method comprises a memory and a processor; the memory stores a computer program executable on the processor; when the processor executes the computer program, the steps of the equipment fault diagnosis dynamic modeling method according to any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program; when the processor executes the computer program, the steps of the equipment fault diagnosis dynamic modeling method according to any one of claims 1 to 6 are implemented.

Images