CN114357185A - Manufacturing equipment fault monitoring model training method based on knowledge graph - Google Patents
Manufacturing equipment fault monitoring model training method based on knowledge graph Download PDFInfo
- Publication number
- CN114357185A CN114357185A CN202111588468.3A CN202111588468A CN114357185A CN 114357185 A CN114357185 A CN 114357185A CN 202111588468 A CN202111588468 A CN 202111588468A CN 114357185 A CN114357185 A CN 114357185A
- Authority
- CN
- China
- Prior art keywords
- equipment
- fault monitoring
- monitoring model
- knowledge
- graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention belongs to the technical field of computer application, and particularly discloses a manufacturing equipment fault monitoring model training method based on a knowledge graph, which comprises the following steps: acquiring historical operating state data of the equipment, and carrying out standardization processing on the acquired historical operating state data of the equipment; acquiring equipment parts and manual operation text data, and preprocessing the acquired equipment parts and manual operation text data; labeling the preprocessed equipment parts and the manually operated text data to construct an equipment knowledge graph; and monitoring the equipment fault in real time based on the constructed equipment knowledge graph, the standardized equipment historical operating state data and the equipment fault monitoring model. According to the method and the device, labeling management is carried out on the data of parts of the device and the data of manual operation of the device except the operation data of the device, and interpretable knowledge is coded into the fault monitoring model in a knowledge driving mode, so that the model is optimized to provide an accurate fault monitoring result.
Description
Technical Field
The invention belongs to the technical field of computer application, and particularly relates to a manufacturing equipment fault monitoring model training method based on a knowledge graph.
Background
With the development of computer technology, more and more technologies are applied to the field of manufacturing industry, and equipment operation conditions are monitored, so that corresponding managers can be helped to more clearly recognize the equipment operation state, and the equipment damage is avoided to cause loss. And through effective fault monitoring, detailed data and data support can be provided for specific fault prevention, and stable operation of equipment is guaranteed, so that the healthy development of the manufacturing industry is guaranteed. In the prior art, historical operating state data of manufacturing equipment is mainly collected on site, a fault monitoring model of the manufacturing equipment is constructed and model training is carried out, the accuracy of the monitoring model is improved by increasing training times and modifying model parameters, and finally the trained fault monitoring model can acquire data of the manufacturing equipment from a database in real time and carry out fault screening.
However, the operation state of the equipment is influenced by various factors, the fault monitoring model is one-sidedness only from historical operation data, and once the equipment is influenced by force-ineligible factors, the method only using the historical operation state data fails, so that the method in the prior art faces great challenges, and how to improve the accuracy of the equipment fault monitoring model becomes an urgent problem to be solved.
Accordingly, further developments and improvements are still needed in the art.
Disclosure of Invention
In order to solve the above problems, a knowledge graph-based manufacturing equipment fault monitoring model training method is proposed. The invention provides the following technical scheme:
a manufacturing equipment fault monitoring model training method based on knowledge graph includes:
acquiring historical operating state data of the equipment, and carrying out standardization processing on the acquired historical operating state data of the equipment;
acquiring equipment parts and manual operation text data, and preprocessing the acquired equipment parts and manual operation text data;
labeling the preprocessed equipment parts and the manually operated text data to construct an equipment knowledge graph;
and monitoring the equipment fault in real time based on the constructed equipment knowledge graph, the standardized equipment historical operating state data and the equipment fault monitoring model.
Further, the normalization process includes: and screening the historical data of normal operation to obtain a normal state data set.
Further, the preprocessing comprises operations of cleaning and removing abnormal and missing sample data.
Further, the labeling process includes: and extracting related entities and relations from the equipment part text data and the manual operation text data.
Further, the method for constructing the equipment knowledge graph comprises the following steps: and integrating the extracted entities and relations, and obtaining the equipment knowledge graph based on the entities and relations.
Further, the method for obtaining the equipment knowledge graph based on the entity and the relation comprises the following steps: and constructing event triples of the equipment, namely an entity 1, a relation and an entity 2, and connecting the event triples to obtain the equipment knowledge graph.
Further, the method for monitoring the equipment in real time comprises the following steps: and inputting the constructed equipment knowledge graph and the normal state data set into an equipment fault monitoring model, and optimizing and training the equipment fault monitoring model.
Further, the method for integrating the equipment knowledge graph and the equipment fault monitoring model comprises the following steps: and vectorizing the relevant information acquired from the equipment knowledge graph, and inputting the historical operating state data of the equipment into the equipment fault monitoring model together.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for knowledge-graph based fault monitoring model training of manufacturing equipment.
An electronic terminal, comprising: a processor and a memory;
the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory so as to enable the terminal to execute a manufacturing equipment fault monitoring model training method based on knowledge graphs.
Has the advantages that:
1. the method for training the fault monitoring model of the manufacturing equipment by combining the knowledge map and the historical data is provided, so that the fault monitoring model can accurately monitor the equipment;
2. label management is carried out on the data of parts and manual operation of the equipment except the equipment operation data, and interpretable knowledge is coded into a fault monitoring model in a knowledge-driven mode, so that the model is optimized to provide an accurate fault monitoring result;
3. by cleaning and removing the defect data, the operation speed and accuracy of the model can be increased, and the accuracy of the fault monitoring model training of the manufacturing equipment can be ensured;
4. the model is optimized more pertinently by periodically acquiring historical data and performing auxiliary management through a knowledge graph;
5. and a fault monitoring model is built by extracting the triples, so that the user can quickly find the source.
Drawings
FIG. 1 is a schematic flow chart of a method for training a fault monitoring model of manufacturing equipment based on a knowledge-graph in an embodiment of the present invention;
FIG. 2 is a schematic diagram of an equipment knowledge graph building process in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the embodiments of the present application, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of additional like elements in the article or system in which the element is included.
As shown in fig. 1, a method for training a fault monitoring model of manufacturing equipment based on a knowledge graph includes:
s101, acquiring historical equipment running state data, and carrying out standardization processing on the acquired historical equipment running state data; namely collecting equipment operation data for standardization processing;
s102, acquiring equipment parts and manual operation text data, and preprocessing the acquired equipment parts and manual operation text data; collecting equipment parts and manually operated text data, and preprocessing;
s103, labeling the preprocessed equipment parts and the manually operated text data to construct an equipment knowledge graph; labeling equipment parts and manual operation texts to construct an equipment knowledge graph;
s104, monitoring equipment faults in real time based on the established equipment knowledge graph, the standardized equipment historical operation state data and the equipment fault monitoring model; namely combining an equipment knowledge map and an equipment fault monitoring model.
Further, the normalization process includes: and screening the historical data of normal operation to obtain a normal state data set. The abnormal historical data can not help to train the equipment fault monitoring model, meanwhile, the accuracy of the equipment fault monitoring model can be influenced, the calculation complexity is increased, the normal data set is screened out, and the calculation speed and the accuracy of the model are accelerated.
Further, the preprocessing comprises operations of cleaning and removing abnormal and missing sample data. Abnormal and missing sample data can not help to train the equipment fault monitoring model, and meanwhile, the accuracy of the equipment fault monitoring model can be influenced, the calculation complexity is increased, a normal data set is screened out, and the calculation speed and accuracy of the model can be accelerated.
Further, the labeling process includes: and extracting related entities and relations from the equipment part text data and the manual operation text data.
Further, the method for constructing the equipment knowledge graph comprises the following steps: and integrating the extracted entities and relations, and obtaining the equipment knowledge graph based on the entities and relations.
Further, the method for obtaining the equipment knowledge graph based on the entity and the relation comprises the following steps: and constructing event triples of the equipment, namely an entity 1, a relation and an entity 2, and connecting the event triples to obtain the equipment knowledge graph.
Further, the method for monitoring the equipment in real time comprises the following steps: and inputting the constructed equipment knowledge graph and the normal state data set into an equipment fault monitoring model, and optimizing and training the equipment fault monitoring model.
Further, the method for integrating the equipment knowledge graph and the equipment fault monitoring model comprises the following steps: and vectorizing the relevant information acquired from the equipment knowledge graph, and inputting the historical operating state data of the equipment into the equipment fault monitoring model together. The vectorized knowledge graph and the normal state data set are input into the equipment fault monitoring model together for repeated training, and the equipment fault monitoring model is optimized.
The training method of the equipment fault monitoring model comprises the following steps:
constructing a characteristic sample data set according to an original sample data set at a periodic sampling time point, wherein the original sample data set is used for representing the historical working condition of the equipment, the original sample data set needs to be complete, and the influence of defects on the representation of the whole equipment is avoided, wherein the periodic sampling time point is used for the sample data collected by each target measuring point in a plurality of target measuring points;
performing unsupervised learning on the original sample data set through a preset target number of abnormal detection models respectively to obtain a target number of detection result lists;
when the original fault tag set is judged to need to be expanded according to the target number of detection result lists, adjusting the target number of abnormal detection models according to the actually expanded incremental fault tags, carrying out unsupervised learning on the original sample data set through the adjusted abnormal detection models, obtaining the target number of detection result lists again, and circulating the steps until the original fault tag set is judged not to need to be expanded according to the new target number of detection result lists, taking the new target number of detection result lists as a target detection result list set, and taking the expanded original fault tag set as a target fault tag set;
and training the classification model based on the original sample data set, the characteristic sample data set, the target detection result list set and the target fault label set to obtain a fault monitoring model.
As shown in fig. 2, the equipment knowledge graph construction process is as follows:
collecting equipment parts and manually operated text data and preprocessing the equipment parts and the manually operated text data, wherein the preprocessing comprises operations such as cleaning, removing and the like;
labeling the equipment text data, including equipment part text data and manual operation text data;
extracting related entities and relations from the labeled equipment text data;
integrating the entities and the relations, and constructing event triples (entity 1, relation and entity 2) of the equipment;
and linking the event triples to obtain an equipment knowledge graph, applying an equipment fault monitoring model, applying the optimized equipment fault monitoring model to equipment, and monitoring the running state of the equipment in real time to provide accurate fault information.
The second embodiment of the invention provides equipment which comprises a memory and a processor, wherein the memory is used for storing programs, and the memory can be connected with the processor through a bus. The memory may be a non-volatile memory such as a hard disk drive and a flash memory, in which a software program and a device driver are stored. The software program is capable of performing various functions of the above-described methods provided by embodiments of the present invention; the device drivers may be network and interface drivers. The processor is used for executing a software program, and the software program can realize the method provided by the first embodiment of the invention when being executed.
A third embodiment of the present invention provides a computer program product including instructions, which, when the computer program product runs on a computer, causes the computer to execute the method provided in the first embodiment of the present invention.
The fourth embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method provided in the first embodiment of the present invention is implemented.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A manufacturing equipment fault monitoring model training method based on knowledge graph is characterized by comprising the following steps:
acquiring historical operating state data of the equipment, and carrying out standardization processing on the acquired historical operating state data of the equipment;
acquiring equipment parts and manual operation text data, and preprocessing the acquired equipment parts and manual operation text data;
labeling the preprocessed equipment parts and the manually operated text data to construct an equipment knowledge graph;
and monitoring the equipment fault in real time based on the constructed equipment knowledge graph, the standardized equipment historical operating state data and the equipment fault monitoring model.
2. The knowledge-graph-based manufacturing equipment fault monitoring model training method of claim 1, wherein the normalization process comprises: and screening the historical data of normal operation to obtain a normal state data set.
3. The knowledge-graph-based manufacturing equipment fault monitoring model training method of claim 1, wherein the preprocessing comprises cleaning and rejecting abnormal and missing sample data operations.
4. The knowledge-graph-based manufacturing equipment fault monitoring model training method of claim 1, wherein the labeling process comprises: and extracting related entities and relations from the equipment part text data and the manual operation text data.
5. The knowledge-graph-based manufacturing equipment fault monitoring model training method of claim 1, wherein the method for constructing the equipment knowledge graph comprises the following steps: and integrating the extracted entities and relations, and obtaining the equipment knowledge graph based on the entities and relations.
6. The knowledge-graph-based manufacturing equipment fault monitoring model training method of claim 5, wherein the method for obtaining the equipment knowledge graph based on the entities and the relations comprises the following steps: and constructing event triples of the equipment, namely an entity 1, a relation and an entity 2, and connecting the event triples to obtain the equipment knowledge graph.
7. The knowledge-graph-based manufacturing equipment fault monitoring model training method according to claim 1, wherein the method for monitoring the equipment in real time comprises the following steps: and inputting the constructed equipment knowledge graph and the normal state data set into an equipment fault monitoring model, and optimizing and training the equipment fault monitoring model.
8. The knowledge-graph-based manufacturing equipment fault monitoring model training method of claim 7, wherein the method for integrating the equipment knowledge graph with the equipment fault monitoring model comprises the following steps: and vectorizing the relevant information acquired from the equipment knowledge graph, and inputting the historical operating state data of the equipment into the equipment fault monitoring model together.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the program when executed by a processor implements the method of any one of claims 1 to 8.
10. An electronic terminal, comprising: a processor and a memory;
the memory is for storing a computer program and the processor is for executing the computer program stored by the memory to cause the terminal to perform the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111588468.3A CN114357185A (en) | 2021-12-23 | 2021-12-23 | Manufacturing equipment fault monitoring model training method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111588468.3A CN114357185A (en) | 2021-12-23 | 2021-12-23 | Manufacturing equipment fault monitoring model training method based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114357185A true CN114357185A (en) | 2022-04-15 |
Family
ID=81101386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111588468.3A Pending CN114357185A (en) | 2021-12-23 | 2021-12-23 | Manufacturing equipment fault monitoring model training method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114357185A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115293379A (en) * | 2022-09-26 | 2022-11-04 | 北京理工大学 | Knowledge graph-based on-orbit spacecraft equipment anomaly detection method |
-
2021
- 2021-12-23 CN CN202111588468.3A patent/CN114357185A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115293379A (en) * | 2022-09-26 | 2022-11-04 | 北京理工大学 | Knowledge graph-based on-orbit spacecraft equipment anomaly detection method |
| CN115293379B (en) * | 2022-09-26 | 2023-01-24 | 北京理工大学 | Knowledge graph-based on-orbit spacecraft equipment anomaly detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN113282461B (en) | Alarm identification method and device for transmission network | |
| US20220414539A1 (en) | Machine learning performance monitoring and analytics | |
| JP6141235B2 (en) | How to detect anomalies in time series data | |
| CN112364133B (en) | Post image generation method, device, equipment and storage medium | |
| US20110307743A1 (en) | False alarm mitigation | |
| CN111897695B (en) | Method and device for acquiring KPI abnormal data sample and computer equipment | |
| CN109992484B (en) | Network alarm correlation analysis method, device and medium | |
| US20210319636A1 (en) | System and method of using mechanical systems prognostic indicators for aircraft maintenance | |
| US12007745B2 (en) | Apparatus for predicting equipment damage | |
| CN112183906B (en) | Machine room environment prediction method and system based on multi-model combined model | |
| CN114595113A (en) | Anomaly detection method and device in application system and anomaly detection function setting method | |
| CN113919540A (en) | Method for monitoring running state of production process and related equipment | |
| CN114357185A (en) | Manufacturing equipment fault monitoring model training method based on knowledge graph | |
| US20230297095A1 (en) | Monitoring device and method for detecting anomalies | |
| KR102024829B1 (en) | System and Method for Fault Isolation in Industrial Processes using CART based variable ranking | |
| CN113947076A (en) | Policy data detection method and device, computer equipment and storage medium | |
| Packianather et al. | Development of soft computing tools and IoT for improving the performance assessment of analysers in a clinical laboratory | |
| CN110458383B (en) | Method and device for realizing demand processing servitization, computer equipment and storage medium | |
| CN114510994A (en) | Training method and device for urban underground gas leakage recognition model | |
| JP2020086786A (en) | Detection device and machine learning method | |
| CN114530163A (en) | Method and system for recognizing life cycle of equipment by adopting voice based on density clustering | |
| US20200082281A1 (en) | Verification device | |
| KR102612280B1 (en) | Virtual Sensing Apparatus and Method Using Artificial Intelligence | |
| CN117395176A (en) | Network fault identification method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |