Multi-process equipment operation and maintenance knowledge base construction and management method

Abstract

The invention discloses a multi-process equipment operation and maintenance knowledge base construction management method, which belongs to the technical field of equipment operation and maintenance, and comprises the following steps of: establishing a multi-process equipment operation and maintenance knowledge base by taking an equipment name entity, a fault phenomenon and a processing method as attributes; acquiring attribute value information accumulated in a free state within a period of time; summing the attribute values of the occurrence frequency of the fault phenomena of the entities from high to low in a preset proportion of the total number of faults of the equipment name entities as common faults, and performing knowledge fusion on the attribute values of the processing methods and the fault phenomena in a common fault range in a knowledge base; in combination with actual maintenance historical skill and experience of a factory, a plurality of maintenance processing methods and courses of common faults are sorted into processing method attribute value information according to a knowledge fusion method, and the processing method attribute value information is pushed and guided after being scored. According to the method, the factory maintenance efficiency, the equipment efficiency and the skill quality of people can be improved, visualization, datamation and informatization of experience knowledge are realized, intelligent manufacturing is promoted, the cost is reduced, and the enterprise competitiveness is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation and maintenance, and in particular to a method for building and managing a knowledge base for multi-process equipment operation and maintenance. Background Art

[0002] Recently, with the rapid development of my country's economy and society, the manufacturing industry, which has always been "people-oriented" in equipment management, has problems such as over-reliance on people's quality and skills, heavy and unsystematic maintenance and repair work, low efficiency, serious waste, and lack of traceability and analysis. These problems have been affecting the comprehensive operating efficiency and equipment health of domestic manufacturing equipment. Therefore, it is urgent to seek informationization, systematization, standardization of equipment management, and lean management of equipment operation. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a multi-process equipment operation and maintenance knowledge base construction and management method in response to the above-mentioned defects of the existing technology, thereby improving the factory maintenance efficiency and equipment efficiency, and the skill quality of people, breaking the status quo of traditional maintenance skills and processes that are taught by word of mouth and by example, realizing the visualization, dataization and informatization of experiential knowledge, promoting intelligent manufacturing to reduce costs, and improving corporate competitiveness.

[0004] In a first aspect, the present invention provides a method for building and managing a multi-process equipment operation and maintenance knowledge base, comprising:

[0005] According to the actual situation of the factory, a multi-process equipment operation and maintenance knowledge base architecture is established in advance with the equipment name as the entity and the fault phenomenon, treatment method, etc. as the attributes;

[0006] Obtain attribute value information of the fault phenomenon, the treatment method, etc. accumulated in a free state over a period of time through a repair processing and acceptance work order system;

[0007] Obtain the occurrence frequency attribute values of the fault phenomenon attribute of the device name entity and sort them in descending order; the sum of the attribute values from high to low accounting for a preset proportion of the total number of faults of the device name entity is defined as a common fault; and the attribute values of each fault phenomenon, treatment method, etc. within the common fault range are subjected to data integration, disambiguation, processing, and other steps under the knowledge base architecture to achieve knowledge fusion;

[0008] Based on the knowledge base of knowledge fusion and combined with the factory's actual maintenance history and skills experience, several maintenance and treatment methods and tutorials for the common faults are organized into treatment method attribute value information according to the knowledge fusion method, and scored and ranked from best to worst according to a certain evaluation method, and pushed and guided in the repair processing and acceptance work order system.

[0009] In some instances, the knowledge base entity also includes: process number, part number. The process number-equipment name classification-equipment number, the equipment number-part name classification-the part number constitute an entity-relationship-entity triple, and the fault phenomenon entity-the fault phenomenon-fault phenomenon attribute value constitutes an entity-attribute-attribute value triple, which can be expanded and optimized according to actual conditions.

[0010] In some instances, in addition to the attributes under the equipment number entity, it also includes a fault cause attribute, a standard working time attribute, a safety matter attribute, and a maintenance type attribute.

[0011] In some examples, the knowledge base includes a triple of fault phenomenon-fault cause-handling method, and the triple is represented by a production rule knowledge representation method to perform forward reasoning from the fault phenomenon to the fault cause.

[0012] In some examples, the certain evaluation method of the attribute value of the treatment method attribute is a membership function matrix evaluation method. The index set of the evaluation method includes effect index, efficiency index, and cost index, which is recorded as W = [w1w2w3]. The membership function matrix of the treatment method attribute value under a certain fault phenomenon attribute value classification is r ij represents the membership degree of the i-th indicator of the j-th processing method attribute value, c j Indicates the membership degree of the j-th processing method attribute value, and is sorted in descending order according to the membership degree.

[0013] In some examples, the repair processing and acceptance work order system includes three steps: fault reporting, repair processing, and completion acceptance, and the steps are operated by three types of personnel with different roles and permissions.

[0014] In some instances, the maintenance processing link records the maintenance start time and maintenance end time, and based on this, collects the time-consuming data of the processing methods in the knowledge base, sorts them from low to high, and takes the multiple of 5 of the time required for 80% of the maintenance personnel to complete the processing method as the attribute value of the standard working time attribute of the processing method, and adds it to the knowledge base.

[0015] In some instances, the fourth step also includes a fifth step, in which a matching mechanism is added to the repair processing and acceptance work order system, unmatched items are regularly summarized, and the system is iteratively upgraded according to the method of the third step.

[0016] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0017] Improving the management level of equipment and its spare parts, ensuring the quality of equipment use, improving its reliability and safety, while also avoiding major accidents and reducing the harm of accidents can obtain potential and huge economic benefits of economic management, tap the potential of equipment life, maximize the effectiveness of equipment, provide decision-making basis, and solve the problem of full-process maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a schematic diagram of a method for constructing and managing a multi-process equipment operation and maintenance knowledge base provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] In the following description, specific embodiments of the present invention will be described with reference to steps and symbols performed by one or more computers, unless otherwise specified. Therefore, these steps and operations will be mentioned several times as being performed by a computer, and computer execution as referred to herein includes operations by a computer processing unit that represents electronic signals of data in a structured form. This operation converts the data or maintains it at a location in the computer's memory system, which can be reconfigured or otherwise change the operation of the computer in a manner familiar to testers in the field. The data structure in which the data is maintained is a physical location in the memory, which has specific characteristics defined by the data format. However, the principles of the present invention are described in the above text, which does not represent a limitation, and testers in the field will understand that the various steps and operations below can also be implemented in hardware.

[0022] As used herein, the terms "module" or "unit" may be considered software objects executed on the computing system. The various components, modules, engines, and services herein may be considered implementation objects on the computing system. While the devices and methods herein are preferably implemented in software, they may also be implemented in hardware and remain within the scope of protection of the present invention.

[0023] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0024] In an embodiment of the present invention, a method for building and managing a multi-process equipment operation and maintenance knowledge base is provided, such as Figure 1 As shown, the following steps are included:

[0025] S1: Based on the actual situation of the factory, a multi-process equipment operation and maintenance knowledge base architecture is established in advance with the equipment name as the entity and the fault phenomenon, treatment process, etc. as the attributes;

[0026] S2: Obtain attribute value information of fault phenomena and processing processes accumulated in a free state over a period of time through the repair processing and acceptance work order system;

[0027] S3: Obtain the occurrence frequency attribute values of the fault phenomenon attribute of the device name entity and sort them in descending order. The attribute values from high to low that account for 80% of the total number of faults of the device name entity are defined as common faults. The attribute values of each fault phenomenon, treatment process, etc. within the common fault range are integrated, disambiguated, and processed in the knowledge base architecture to achieve knowledge fusion.

[0028] S4: Based on the knowledge base of knowledge fusion and the actual maintenance history and experience of the factory, several maintenance treatment methods and tutorials for common faults are organized into treatment method attribute value information according to the knowledge fusion method, and scored and ranked from best to worst according to a certain evaluation method, and pushed and guided in the repair processing and acceptance work order system.

[0029] The following is an illustration using a specific example.

[0030] (1) System architecture and implementation process

[0031] The implementation of the present invention is based on the following core modules: knowledge base construction module, data acquisition and processing module, fault analysis and knowledge fusion module, intelligent push and guidance module. The overall process is as follows Figure 1 shown.

[0032] (2) Specific implementation steps

[0033] Step 1: Construction of multi-process equipment operation and maintenance knowledge base architecture

[0034] 1. Entity and attribute definition

[0035] Entity: The core entity is the name of the equipment in the factory (such as "taking over bed 1#", "sawing machine 5#").

[0036] Attributes: Each device entity is associated with the following attributes:

[0037] Fault phenomenon: Specific abnormal performance that occurs during equipment operation (such as "abnormal bearing noise" and "excessive temperature").

[0038] Handling process: Record of maintenance operations for the fault (such as "replace bearing", "clean heat sink").

[0039] Maintenance history: maintenance time, maintenance personnel, spare parts replacement list, etc.

[0040] Knowledge base storage format: Uses a graph database (such as Neo4j) or a relational database (such as MySQL), with device names as nodes and fault symptoms and processing procedures as edge attributes, supporting multi-dimensional retrieval.

[0041] 2. Knowledge base initialization

[0042] Manually enter initial data through equipment manuals and historical maintenance records to ensure the completeness of basic data.

[0043] Step 2: Data collection and attribute extraction from the repair work order system

[0044] 1. Data Source

[0045] Extract the following fields from the factory's repair processing and acceptance work order system (such as SAP, Maximo):

[0046] Equipment name, fault description (natural language), processing process record, maintenance result (success / failure), maintenance time, etc.

[0047] 2. Data preprocessing

[0048] Natural language parsing: Use NLP technology (such as the BERT model) to perform entity recognition and structured extraction of fault descriptions. For example, mapping "abnormal spindle vibration" to the "spindle vibration" fault phenomenon.

[0049] Data cleaning: Eliminate duplicate, incomplete or invalid work orders (such as those without records of the processing process).

[0050] Attribute value standardization: Convert unstructured text into pre-set standardized labels (e.g. “bearing replacement” is classified as “spare part replacement” process type).

[0051] Step 3: Fault frequency analysis and knowledge fusion

[0052] 1. Frequency statistics and threshold definition

[0053] Count the number of occurrences of each fault phenomenon by device entity, sort them in descending order, and then calculate the cumulative percentage.

[0054] Threshold rule: Fault phenomena that cumulatively account for 80% of the total number of faults are defined as common faults of the device.

[0055] Example: A device has a total of 100 faults, and the total number of the first five fault phenomena is 82. These five faults are marked as "common faults."

[0056] 2. Knowledge Fusion and Disambiguation

[0057] Data integration: Merge different descriptions of the same fault phenomenon (e.g., “bearing abnormal noise” and “bearing noise” are unified into “bearing abnormal noise”).

[0058] Process association: Match a corresponding process to each common fault, and verify its effectiveness through historical work orders (for example, the success rate of "bearing abnormal noise" corresponding to "bearing replacement" is 95%).

[0059] Knowledge base update: The fused data is written into the knowledge base to form a structured fault-handling mapping relationship.

[0060] Step 4: Intelligent push and optimization of maintenance plans

[0061] 1. Maintenance plan generation and scoring

[0062] Historical experience mining: Extract high-frequency processing processes from maintenance records and combine them with expert experience to generate standardized maintenance tutorials (such as videos and graphic guides).

[0063] Scoring rules: Score the solution based on the following dimensions (out of 10 points):

[0064] Success rate (weight 40%): number of historical repair successes / total number of applications.

[0065] Time consumption (weight 30%): average repair time (the shorter the higher the score).

[0066] Cost (weight 30%): spare parts and labor costs (the lower the higher the score).

[0067] Example: Plan A has a success rate of 95%, takes 2 hours, and costs 500 yuan, so its score is 9.5×0.4+8×0.3+7×0.3=8.5.

[0068] 2. Intelligent push and guidance

[0069] Real-time matching: When a new work order is triggered, the system retrieves the top three solutions with the highest scores from the knowledge base based on the device name and fault phenomenon.

[0070] Push form: Displayed in the work order system interface in the form of a drop-down menu, pop-up window or link, and marked with the score, time and cost.

[0071] Feedback mechanism: Maintenance personnel need to fill in the actual results after execution, and the system will dynamically update the score (if the actual success rate of Plan B is lower than expected, the score will be downgraded).

[0072] 3. Implementation Effect

[0073] Through this method, the factory can achieve:

[0074] (1) Improved fault handling efficiency: The time required to match repair solutions for common faults is shortened by more than 50%.

[0075] (2) Reduced maintenance costs: By optimizing the selection of solutions, spare parts waste is reduced by 20%-30%.

[0076] (3) Knowledge accumulation: Convert scattered maintenance experience into a structured knowledge base to support new employees to learn quickly.

[0077] 4. Take the “takeover bed 1#” of a chemical plant as an example:

[0078] 1. The common faults recorded in the knowledge base are "bearing overheating" (accounting for 35%), "seal leakage" (accounting for 25%), and "abnormal vibration" (accounting for 20%).

[0079] 2. For "bearing overheating", the system pushes the highest-scoring solution: "Cleaning the heat dissipation channel + replacing grease" (score 9.2), replacing the original manual troubleshooting process.

[0080] After implementation, the average handling time for this fault was reduced from 4 hours to 1.5 hours, and the success rate increased from 80% to 98%.

[0081] The above is a detailed introduction to a multi-process equipment operation and maintenance knowledge base construction and management method provided by an embodiment of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for building and managing a knowledge base for multi-process equipment operation and maintenance, characterized in that: include: According to the actual situation of the factory, a multi-process equipment operation and maintenance knowledge base architecture is established with the equipment name as the entity and the fault phenomenon and treatment method as the attribute; Obtain attribute value information of the fault phenomenon and the treatment method accumulated in a free state over a period of time through a repair processing and acceptance work order system; Obtaining the occurrence frequency attribute values of the fault phenomenon of the device name entity and sorting them in descending order, summing the occurrence frequency attribute values from high to low, defining the fault whose sum accounts for a preset proportion of the total number of faults of the device name entity as a common fault, and pre-processing the attribute values of each fault phenomenon and corresponding treatment method within the common fault range under the knowledge base architecture to achieve knowledge fusion; Based on the knowledge base after knowledge fusion and the actual maintenance history and skills experience of the factory, several maintenance treatment methods and tutorials for the common faults are organized into treatment method attribute value information according to the knowledge fusion method, and scored according to a certain evaluation method and ranked from best to worst, and pushed and guided in the repair processing and acceptance work order system.

2. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 1, characterized in that: The knowledge base architecture also includes: process number and component number; The process number-equipment name classification-equipment number, the equipment number-component name classification-the component number constitute entity-relationship-entity triples, and the entity corresponding to the fault phenomenon-the fault phenomenon-fault phenomenon attribute value constitutes entity-attribute-attribute value triples.

3. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 2, characterized in that: The entity-relationship-entity triples and the entity-attribute-attribute value triples are expanded and optimized according to the actual situation of the factory.

4. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 1, characterized in that: In addition to the attributes under the equipment number entity, it also includes a fault cause attribute, a standard working time attribute, a safety matter attribute, and a maintenance type attribute.

5. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 1, characterized in that: The knowledge base architecture includes a triple of fault phenomenon-fault cause-handling method, and the triple adopts a production rule knowledge representation method to forward reason from the fault phenomenon to the fault cause.

6. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 1, characterized in that: The evaluation method of the attribute value of the processing method attribute is a membership function matrix evaluation method.

7. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 6, characterized in that: The index set of the membership function matrix evaluation method includes effect index, efficiency index, and cost index, which is recorded as W=[w1w2w3]. The membership function matrix of the processing method attribute value under a certain fault phenomenon attribute value classification is r ij represents the membership degree of the i-th indicator of the j-th attribute value of the treatment method, c j Represents the membership of the j-th processing method attribute value, and is sorted in descending order according to the membership.

8. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 1, characterized in that: The repair processing and acceptance work order system includes three links: fault reporting, repair processing, and completion acceptance, and each link is operated by three types of role personnel with different permissions.

9. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 8, characterized in that: The maintenance processing link records the maintenance start time and maintenance end time, and based on this, collects the time-consuming data of the corresponding processing methods in the knowledge base architecture, sorts them from low to high, and takes several multiples of the time consumed by the maintenance personnel to complete the processing methods at a preset ratio, rounds them up as the attribute value of the standard working time attribute of the processing method, and adds them to the knowledge base.

10. A method for building and managing a multi-process equipment operation and maintenance knowledge base according to claim 1, characterized in that: The method further comprises: A matching mechanism is added to the repair processing and acceptance work order system, unmatched items are summarized regularly, the occurrence frequency attribute values of the fault phenomena of the equipment name entity are obtained and sorted in descending order, the occurrence frequency attribute values are summed from high to low, and the faults whose sum accounts for a preset proportion of the total number of faults of the equipment name entity are defined as common faults, and the attribute values of each fault phenomenon and the corresponding processing method within the range of common faults are pre-processed under the knowledge base architecture to realize iterative upgrading of the knowledge fusion step.

Images