Wear Part Detection in Heavy Equipment Using Pixel Subset Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring wear parts in heavy equipment, such as loaders and excavators, are inadequate for detecting worn or detached components, leading to safety risks, equipment damage, and operational inefficiencies due to unscheduled maintenance.
Innovation Solution
A method and apparatus using a convolutional neural network to process images of heavy equipment, identifying wear parts by selecting pixel subsets, determining intensity values, and applying a matching criterion based on labeled training images, allowing for real-time detection and condition assessment of wear parts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If camera based monitoring systems are used to monitor wear parts, then wear part detection capability is improved, but system complexity and processing requirements increase
Solution Approach 1:
The image is divided into multiple pixel subsets that are processed independently through the neural network. This segmentation allows the system to handle large images by breaking them into manageable units, reducing the computational complexity per unit while maintaining comprehensive coverage of the entire wear part surface.
Solution Approach 2:
The patent uses a trained neural network model that has been copied from training data to perform detection. The trained model weights and architecture are replicated to infer wear part conditions from new images, allowing the system to make accurate detections without requiring complex real-time learning computations during actual monitoring operations.
2Loss of time
If real-time image processing is performed to detect wear parts, then detection timeliness is improved, but computational resource consumption increases
Solution Approach 1:
The neural network model is trained in advance using labeled training images before actual monitoring operations. This preliminary training allows the system to perform fast inference during real-time operation, as the complex pattern recognition has already been performed offline, leaving only efficient forward propagation computations for actual wear part detection.
Solution Approach 2:
The system processes images by selecting and analyzing only the necessary pixel subsets that contain potential wear part information, rather than processing every pixel uniformly. This selective processing approach maintains detection accuracy while reducing overall computational resource consumption by focusing calculations on relevant image regions.
Data Source
AI summary
A method and apparatus for locating and/or determining the condition of a wear part in an image of an operating implement associated with heavy equipment is disclosed. The method involves capturing at least one image of the operating implement during operation of the heavy equipment, the image including a plurality of pixels each having an intensity value. The method also involves selecting successive pixel subsets within the plurality of pixels, and processing each pixel subset to determine whether pixel intensity values in the pixel subset meet a matching criterion indicating a likelihood that the pixel subset corresponds to the wear part. The matching criterion is based on processing a labeled set of training images during a training exercise prior to capturing the at least one image of the operating implement.