Predictive maintenance is a critical element of the Industry 4.0 initiative for smart factories. By using ML-enabled sensors to monitor the current health and conditions of industrial equipment, with enough data, factories can predict when and where issues will occur in the future.
- Sensor modules can be retrofitted onto existing machinery, greatly reducing the cost and disruption to add machine learning to existing infrastructure.
- With an intuitive UI, Qeexo AutoML is the only tool needed for collecting data, building models, and deploying solutions to edge systems.
- The build and deployment of machine learning models can be entirely automated with Qeexo AutoML so that daily/weekly upgrade based on new data is feasible.
Minor differences in the hardware setup and environment can affect the accuracy of machine learning models. For best performance, each individual machine needs to be equipped with a unique model and periodically updated for improvement.
via Qeexo AutoML Vision
Qeexo AutoML Vision is an image-focused machine learning platform based on Qeexo AutoML for use cases such as quality inspection. It automatically builds machine learning models for edge devices using image data and is currently available by inquiry.
- Qeexo AutoML Vision does not require expensive infrastructure or equipment and can be integrated with a small fraction of the cost and effort compared to alternatives.
- Qeexo AutoML Vision can be used by existing employees, without complicated training and ramp-up time to operate.
- Machine learning models generated by Qeexo AutoML Vision run locally and do not require internet connectivity, so data never leaves premise.
KwangSung Corporation is an automotive parts manufacturer and Tier 1 supplier for Hyundai and Kia, with operations in Korea, America, China, and India. Before Qeexo AutoML, KwangSung employed workers to visually inspect parts with their bare eyes. They needed a better way to detect defects in its “quarter garnish” parts, including scratches, gas marks, short shots, and black spots.