A Method for Automatic Identification of Process Failure Modes
A technology for process failure and automatic identification, applied in office automation, data processing applications, instruments, etc., can solve the problems of high implementation cost, poor consistency, and low efficiency, achieve large information memory capacity, stable and reliable operation, and avoid common disadvantages Effect
Inactive Publication Date: 2019-05-07
NANCHANG HANGKONG UNIVERSITY
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the traditional identification method of process failure mode relies entirely on manual operation, which has the common disadvantages of manual operation such as low efficiency, poor consistency, restricted by the professional level and responsibility of PFMEA members, and high implementation cost.
It is worth mentioning that due to the limitation of human memory, the limitation of manual search, and the uncertainty of association and analogy thinking, it often leads to the omission of process failure modes.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0042] Example: A preferred implementation example is listed below to show the operation process of the process failure mode automatic identification system. The specific steps are as follows:
[0043] 1) Enter the process instruction information described in natural language: "Check whether the tooling is within the qualified period";
[0044] 2) Utilize the cloud language technology platform of Harbin Institute of Technology to transform process instruction information into structured information, such as figure 2 As shown, the structured information includes four levels of language feature information of part of speech, dependency syntax, semantic role, and semantic dependency, and is stored as an XML format file. The file information in XML format is as follows:
[0045]
[0046] 3) When the special word "check" appears and is at the beginning of the sentence, the following negative word insertion algorithm is implemented:
[0047]
[0048]
[0049] Among them, k is the correspo...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for automatic identification of process failure modes, the steps of which are: taking the process instruction information listed in the process instruction book as the input of the system, and using natural language processing technology to convert it into a structure that can be stored in a relational database information. Then, starting from the six factors that affect the quality of the process: people, machines, materials, methods, environment, and testing, and according to the language characteristics of the six factors at the four levels of morphology, syntax, semantics, and context, the negative word insertion algorithm And the typical failure mode library, automatically output several corresponding process failure modes. The system effectively avoids the common disadvantages unique to manual operation, such as high implementation cost, low execution efficiency, recognition effect depends on the professional level and sense of responsibility of the participants, and so on. In addition, under a specific and clear failure judgment mechanism, all possible potential process failure modes are exhausted, and the comprehensiveness and stability that machine recognition can achieve exceeds manual recognition.
Description
Technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method for automatically identifying process failure modes. Background technique [0002] Process failure mode and impact analysis (PFMEA) is an important basic work to improve the reliability of the product manufacturing process. It is to analyze each process of the product manufacturing process on the premise that the product meets the design requirements, find out all potential process failure modes in the process as much as possible, analyze the causes and consequences, and then analyze the process. An analytical method that takes appropriate preventive or remedial measures. This technology originated in the US aviation industry, and has been widely used in aviation, aerospace, machinery, automobiles and other fields, and has achieved remarkable results. It has played a huge role in ensuring the reliability of products in these fields. [0003] Process failur...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/27
CPCG06Q10/10
Inventor 聂文滨刘卫东胡坤曾天陈虎
Owner NANCHANG HANGKONG UNIVERSITY