Analyzing and marking method and system for engineering machinery fault knowledge

Abstract

The invention discloses an analysis marking method and system for engineering machinery fault knowledge in the technical field of engineering machinery, and the method comprises the steps: constructing a target feature tag library by taking the target feature of the engineering machinery as a principal line; the target features comprise components, working environments, types and working scenes of the engineering machinery; adding a corresponding tag related word to each target feature tag in the target feature tag library; obtaining fault knowledge information of the engineering machinery, and matching the occurrence frequency of each label related word; and performing label marking on the fault knowledge information according to the occurrence frequency of each label related word. According to the method, fault knowledge information can be rapidly analyzed and marked, technical support is provided for subsequent rapid construction of a knowledge base with reasonable classification and rich labels, and the problems that fault knowledge classification is slow, description is not accurate, and the requirement for rapid and accurate application of knowledge in the design process is difficult to support are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering machinery, and in particular to an analysis and marking method and system for engineering machinery fault knowledge. Background Art

[0002] Engineering machinery is usually composed of multiple key assemblies and components, and its extremely complex structure leads to a wide variety of failures. Various problems in the domestic and foreign markets, fault feedback and their solutions are important components of the knowledge base of the R&D design process. They are the source of knowledge for designers to identify potential problems, identify and avoid errors and defects in the design, understand design shortcomings and stimulate innovation and improvement. At present, the amount of information on fault problems is large, and it all depends on technical personnel to make judgments based on experience and classify them into the knowledge base. The workload is large and the efficiency is low, which makes it difficult to meet the consumption demand for fault knowledge in the design process. At the same time, due to manual classification, for the convenience of execution, the classification list is a single level, the number of classification items is small, and the classification granularity is relatively coarse. It is difficult to accurately describe fault knowledge based on the current classification list. The fault knowledge obtained by designers has a large coverage and poor precision guidance. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method and system for analyzing and marking engineering machinery fault knowledge, so as to solve the technical problems that the data import into the knowledge base of the current R&D and design process is time-consuming and labor-intensive, and lacks precise guidance for designers.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for analyzing and marking engineering machinery fault knowledge, comprising: Taking the target features of construction machinery as the main line, a target feature label library is constructed; Adding corresponding tag-related words to each target feature tag in the target feature tag library; Obtain the fault knowledge information of engineering machinery and match the number of occurrences of related words of each tag; The fault knowledge information is labeled according to the number of occurrences of each tag-related word.

[0005] Optionally, the target feature adopts a component, and the building of the target feature label library includes building a multi-level component label library covering the engineering machinery development process with the component as the main line.

[0006] Optionally, labeling the fault knowledge information according to the number of occurrences of each tag-related word includes: Calculate the frequency of occurrence of the label-related words of each component label according to the number of occurrences; Obtain the correlation strength coefficient between each component label and its label-related words; Calculating the weight rate of the label-related words of each component label under the fault knowledge information according to the occurrence frequency and the association strength coefficient; A plurality of component labels with the largest weight ratios are selected as labels of the fault knowledge information.

[0007] Optionally, the target feature adopts an operating environment, and constructing the target feature label library includes constructing an operating environment label library based on the operating environment.

[0008] Optionally, labeling the fault knowledge information according to the number of occurrences of each tag-related word includes: The operating environment labels in which the number of occurrences of label-related words exceeds a preset number are used as labels of the fault knowledge information.

[0009] Optionally, the target feature adopts a category, and the building of the target feature tag library includes building a user operation habit tag library based on the category; The label-related words of the user operation habit labels in the user operation habit label library include action description label-related words, action label-related words, and control component label-related words.

[0010] Optionally, labeling the fault knowledge information according to the number of occurrences of each tag-related word includes: The number of occurrences of the control component label-related words is taken as the number of cycles, and for each of the control component label-related words, its position in the fault knowledge information is determined, and a plurality of words before and after the position are obtained; If there are action-related label words in the multiple words before and after the position, and there are no action-description label words, then the control component label words and the action label words are combined as labels for the fault knowledge information; If there are action-related label words and action-description label related words in multiple words before and after the position, the control component label related words, the action-description label related words and the action label related words are combined as labels for the fault knowledge information.

[0011] Optionally, the target feature adopts a construction scene, and constructing the target feature label library includes constructing a construction scene label library based on the construction scene.

[0012] Optionally, labeling the fault knowledge information according to the number of occurrences of each tag-related word includes: The construction scene labels in which the number of occurrences of label-related words exceeds a preset number are used as labels of the fault knowledge information.

[0013] In a second aspect, the present invention provides an analysis and marking system for engineering machinery fault knowledge, comprising: The label library construction module is configured to construct a target feature label library based on the target features of the construction machinery; A related word adding module is configured to add corresponding tag related words to each target feature tag in the target feature tag library; A related word matching module is matched to obtain fault knowledge information of engineering machinery and matches the number of occurrences of related words of each tag; The label marking module is configured to label the fault knowledge information according to the number of occurrences of each label-related word.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method and system for analyzing and labeling engineering machinery fault knowledge, which can quickly analyze and label fault knowledge information, provide technical support for the subsequent rapid construction of a knowledge base with reasonable classification and rich labels, and solve the problem that fault knowledge classification is slow and the description is inaccurate, which makes it difficult to support the design process's demand for rapid and accurate application of knowledge.

[0015] Multi-level processing is carried out on the components of engineering machinery, which conforms to the product design process of engineering machinery and closely fits the product characteristics of engineering machinery. It can quickly and accurately link the product development process, and the algorithm is simple and easy to implement, reducing the development time of the information system.

[0016] In response to the on-site use needs of construction machinery, three types of label libraries are set up, namely, working environment category, user operation habit category, and construction scene category. These can support the rapid and automatic classification and labeling of fault knowledge, realize the accurate push of knowledge, and improve the design quality and efficiency of designers. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for analyzing and marking engineering machinery fault knowledge provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of a process of labeling fault knowledge information according to user operation habits provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0019] Embodiment 1:

[0020] like Figure 1 As shown, an embodiment of the present invention provides a method for analyzing and marking engineering machinery fault knowledge, comprising the following steps: Step S1: Taking the target features of construction machinery as the main line, construct a target feature label library.

[0021] Step S2: adding corresponding tag-related words to each target feature tag in the target feature tag library.

[0022] Step S3: Acquire fault knowledge information of construction machinery and match the number of occurrences of words related to each tag.

[0023] Step S4: label the fault knowledge information according to the number of occurrences of each tag-related word.

[0024] (1) Taking the target feature of engineering machinery as a component as an example, in order to fully support the use of knowledge in the product design process, a multi-level component label library is established with components as the main line, covering all major design processes of product development, with a ratio of about 90%. As shown in Table 1, this embodiment provides a schematic table of a two-level component label library.

[0025] Table 1: Schematic diagram of a dual-level component tag library

[0026] Components and their label-related words are pre-set according to the development process of construction machinery.

[0027] Labeling fault knowledge information according to the number of occurrences of related words of each label includes: Step S101: Calculate the occurrence frequency of the label-related words of each component label according to the number of occurrences of the label-related words.

[0028] The expression for the frequency of occurrence is: ; In the formula, For the The frequency and number of occurrences of words related to each tag, Fault Knowledge Information The number of occurrences of all words in .

[0029] Step S102: Obtain the correlation strength coefficient between each component label and its label-related words.

[0030] The correlation strength coefficient is preset according to the working experience of the technicians. As shown in Table 2, this embodiment provides a schematic table of correlation strength coefficients.

[0031] Table 2: Schematic table of correlation strength coefficients

[0032] C 11 For example, it means the correlation strength coefficient between the first component label and its first label related word.

[0033] Step S103: Calculate the weight rate of the label-related words of each component label under the fault knowledge information according to the occurrence frequency and the association strength coefficient.

[0034] As shown in Table 3, this embodiment provides a schematic table of occurrence frequency and correlation strength coefficient.

[0035] Table 3: Schematic table of occurrence frequency and correlation strength coefficient

[0036] As shown in Table 4, this embodiment provides a schematic table of weight rates of label-related words of a component label.

[0037] Table 4: Schematic table of weight ratios of label-related words of component labels

[0038] is the weight value Taking the first weight value as an example, .

[0039] Step S104: Select multiple component labels with the largest weight ratio as labels of fault knowledge information.

[0040] In this embodiment, the three largest component labels are selected as labels of the fault knowledge information.

[0041] (2) Taking the target feature of construction machinery as the working environment as an example, the working environment of construction machinery after it is put on the market is usually divided into climate environment and special environment. Based on the characteristics of each type of working environment, its label-related words are decomposed.

[0042] As shown in Table 5, this embodiment provides a schematic table of a working environment label library.

[0043] Table 5: Schematic diagram of the operating environment tag library

[0044] Labeling fault knowledge information according to the number of occurrences of related words of each label includes: The operating environment labels whose label-related words appear more than a preset number of times are used as labels of the fault knowledge information. In this embodiment, the preset number of times is set to 1.

[0045] (3) Taking the target feature of construction machinery as an example, different types of construction machinery have different user operation habits, so a user operation habit label library is constructed.

[0046] The label-related words of the user operation habit label in the user operation habit label library include action description label-related words, action label-related words, and control component label-related words. As shown in Table 6, this embodiment provides a schematic table of a user operation habit label library.

[0047] Table 6: Schematic diagram of user operation habit tag library

[0048] Labeling fault knowledge information according to the number of occurrences of related words of each label includes: The number of occurrences of the control component label-related words is taken as the number of cycles, and for each control component label-related word, its position in the fault knowledge information is determined, and multiple words before and after the position are obtained; If there are action-related label words in multiple words before and after the position, and there are no action-description label words, then the control component label words and the action label words are combined as the label of the fault knowledge information; If there are action-related label words in multiple words before and after the position, and there are action-description label related words, then the control component label related words, action-description label related words and action label related words are combined as labels for the fault knowledge information.

[0049] like Figure 2 As shown, the specific process of labeling the user operation habit of the fault knowledge information is as follows: first search for the control component label-related words in the fault knowledge information, and if found, search for the action label-related words; if found, continue to search for whether there are action description label-related words, if so, the label content can be: the found control component label-related words + action description label-related words + action label-related words; if not, the label content can be the control component label-related words + action label-related words.

[0050] (4) Taking the construction scene as an example, the target feature of engineering machinery is mainly divided into 16 types: petrochemical, wind power, transportation, urban construction, earthwork, crushing, mining, etc. Construction scene related word elements are established for the construction objects and typical working conditions of each construction scene. As shown in Table 7, this embodiment provides a schematic table of construction scene labels.

[0051] Table 7: Schematic table of construction scene labels

[0052] Labeling fault knowledge information according to the number of occurrences of related words of each label includes: The construction scene labels whose label-related words appear more than a preset number of times are used as labels of the fault knowledge information. In this embodiment, the preset number of times is set to 1.

[0053] Embodiment 2:

[0054] The embodiment of the present invention provides an analysis and marking system for engineering machinery fault knowledge. The analysis and marking system is configured to execute the analysis and marking method provided in the first embodiment, and its structure specifically includes: The label library construction module is configured to construct a target feature label library based on the target features of the construction machinery; A related word adding module is configured to add corresponding tag related words to each target feature tag in the target feature tag library; A related word matching module is matched to obtain fault knowledge information of engineering machinery and matches the number of occurrences of related words of each tag; The label marking module is configured to label the fault knowledge information according to the number of occurrences of each label-related word.

[0055] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0059] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for analyzing and marking engineering machinery fault knowledge, characterized in that: include: Taking the target features of construction machinery as the main line, a target feature label library is constructed; Adding corresponding tag-related words to each target feature tag in the target feature tag library; Obtain the fault knowledge information of engineering machinery and match the number of occurrences of related words of each tag; The fault knowledge information is labeled according to the number of occurrences of each tag-related word.

2. The analysis and marking method of engineering machinery fault knowledge according to claim 1 is characterized in that: The target feature adopts a component, and the construction of the target feature label library includes taking the component as the main line to construct a multi-level component label library covering the engineering machinery development process.

3. The method for analyzing and marking engineering machinery fault knowledge according to claim 2 is characterized in that: The labeling of the fault knowledge information according to the number of occurrences of each label-related word includes: Calculate the frequency of occurrence of the label-related words of each component label according to the number of occurrences; Obtain the correlation strength coefficient between each component label and its label-related words; Calculating the weight rate of the label-related words of each component label under the fault knowledge information according to the occurrence frequency and the association strength coefficient; A plurality of component labels with the largest weight ratios are selected as labels of the fault knowledge information.

4. The analysis and marking method of engineering machinery fault knowledge according to claim 1 is characterized in that: The target feature adopts the operating environment, and the construction of the target feature label library includes taking the operating environment as the main line to construct an operating environment label library.

5. The analysis and marking method of engineering machinery fault knowledge according to claim 4 is characterized in that: The labeling of the fault knowledge information according to the number of occurrences of each label-related word includes: The operating environment labels in which the number of occurrences of label-related words exceeds a preset number are used as labels of the fault knowledge information.

6. The analysis and marking method of engineering machinery fault knowledge according to claim 1 is characterized in that: The target feature adopts a category, and the building of the target feature tag library includes building a user operation habit tag library based on the category; The label-related words of the user operation habit labels in the user operation habit label library include action description label-related words, action label-related words, and control component label-related words.

7. The analysis and marking method of engineering machinery fault knowledge according to claim 6 is characterized in that: The labeling of the fault knowledge information according to the number of occurrences of each label-related word includes: The number of occurrences of the control component label-related words is taken as the number of cycles, and for each of the control component label-related words, its position in the fault knowledge information is determined, and a plurality of words before and after the position are obtained; If there are action-related label words in the multiple words before and after the position, and there are no action-description label words, then the control component label words and the action label words are combined as labels for the fault knowledge information; If there are action-related label words and action-description label related words in multiple words before and after the position, the control component label related words, the action-description label related words and the action label related words are combined as labels for the fault knowledge information.

8. The analysis and marking method of engineering machinery fault knowledge according to claim 1 is characterized in that: The target feature adopts a construction scene, and constructing a target feature label library includes constructing a construction scene label library based on the construction scene.

9. The analysis and marking method of engineering machinery fault knowledge according to claim 8 is characterized in that: The labeling of the fault knowledge information according to the number of occurrences of each label-related word includes: The construction scene labels in which the number of occurrences of label-related words exceeds a preset number are used as labels of the fault knowledge information.

10. An analysis and marking system for engineering machinery fault knowledge, characterized in that: include: The label library construction module is configured to construct a target feature label library based on the target features of the construction machinery; A related word adding module is configured to add corresponding tag related words to each target feature tag in the target feature tag library; A related word matching module is matched to obtain fault knowledge information of engineering machinery and matches the number of occurrences of related words of each tag; The label marking module is configured to label the fault knowledge information according to the number of occurrences of each label-related word.

Images