Spinning Mill Fault Source Estimation From Sparse Machine Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current spinning mills face challenges in detecting faults and estimating their sources quickly and precisely, often requiring experienced staff or external consultation due to insufficient sensor coverage and complex fault propagation across multiple processing steps.
Innovation Solution
An electronic device and method that receive parameter information from textile machines and materials, detect faults by identifying deviations from reference information, access configuration and knowledge-based information, and apply this data to machine-learning algorithms to estimate the sources of faults accurately and efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are installed at every textile machine to capture all parameters, then measurement precision and fault detection capability are improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent introduces an electronic device as an intermediary that receives parameter information from sensors at selected locations and uses machine learning algorithms to infer fault sources. This intermediary processing layer enables accurate fault detection without requiring sensors at every machine, thus resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The system creates a virtual model of the spinning mill's production process and fault propagation patterns through machine learning. This digital copy allows the system to predict fault sources at upstream machines based on parameters measured at downstream machines, eliminating the need for physical sensors at every location
2Measurement precision
If manual inspection by experienced staff is used to identify fault sources, then measurement precision is improved, but loss of time increases due to delayed detection and correction
Solution Approach 1:
The system enables self-service fault diagnosis by automatically analyzing parameter deviations and identifying fault sources using machine learning algorithms. This eliminates the need for manual inspection by experienced staff, simultaneously achieving high accuracy in fault source identification and rapid response time
Solution Approach 2:
The system continuously monitors parameter information and provides real-time feedback when deviations are detected. The machine learning model immediately processes this feedback to identify fault sources, enabling rapid automatic response without waiting for manual inspection
3Reliability
If comprehensive sensor coverage is implemented across all machines, then reliability of fault detection is improved, but loss of energy and cost increase
Solution Approach 1:
The system implements partial sensing by installing sensors only at strategically selected locations where parameter measurement provides maximum information for fault detection. The machine learning model compensates for the incomplete data coverage, maintaining high detection reliability while minimizing sensor quantity and associated costs
Data Source
AI summary
An electronic device and associated method are used to detect a fault in a spinning mill and to estimate one or more sources of the fault, the spinning mill including a plurality of textile machines that sequentially process textile materials. With the electronic device, the method receives parameter information of one or more of the textile machines and of one or more of the textile materials. The electronic device detects faults and location of the faults by identifying parameter information of the textile materials deviating from reference information. The electronic device is used to access configuration information of the textile machines and knowledge-based information related to possible sources of faults in the spinning mill. The method incudes using the electronic device to apply parameter information, configuration information, and knowledge-based information to one or more machine-learning algorithms to estimate the sources of the faults.