Spinning quality fluctuation-oriented key factor extraction method

Abstract

The invention discloses a spinning quality fluctuation-oriented key factor extraction method. The method is characterized by comprising the following steps: S1, constructing a multi-Agent-based production process uncertainty prediction model by means of a multi-Agent technology, wherein the uncertainty prediction model comprises a system management Agent, an object management Agent, an execution Agent, a human-computer interface Agent, a data interface Agent, a source data Agent, an initialization Agent, a target data Agent, a query Agent, a statistic Agent and an analysis Agent; S2, completing the design of acceptance functions and influence functions; S3, completing the standardized processing of data; S4, completing the calculation of correlation coefficients; S5, carrying out dependency evaluation on the basis of DEA; and S6, extracting key factors. According to the method disclosed in the invention, the fluctuation extraction in the spinning process is solved, so that the product efficiency is improved and the uncontrollable factors are reduced to minimum.

Description

Technical field [0001] The invention relates to the field of spinning quality fluctuation monitoring, in particular to a method for extracting key factors facing spinning quality fluctuations. Background technique [0002] Under normal circumstances, there are many uncertain factors that affect the textile production process, such as the machine itself, man-made anomalies, production plan changes, the arrival of emergency tasks, environmental impacts, and other situations. According to the theory of man-machine environmental systems engineering, it can be Divided into machine factors, human factors, system factors, planned task factors, environmental factors and other factors, and each category can also be divided into multiple sub-categories according to specific circumstances. For example, machine factors can be divided into mechanical failures, electrical failures, and control system failures; human factors can be divided into misoperation failures, abnormal personnel changes,...

AI Technical Summary

Problems solved by technology

But the result is often unsatisfactory, which leads to the low growth point of the enterprise economic index

The crux of the problem lies in: the root cause of the error in the production and quality data during the weaving process has not been scientifically analyzed and judged from the root, but it is just blindly "artificially" determined, and never pays attention to how to ensure various data in the weaving process. The basic theoretical research of correctness, of course, there is no relevant theory as a guiding basis

Images