fischertechnik Qualitätssicherung mit KI Simulation model Assembled 9 V
Artificial intelligence in research, education and industryThe use of artificial intelligence in industry, education and research is becoming increasingly important. In order to visualize this complex topic hands-on, the Quality Assurance model with AI system from fischertechnik is excellently suited. A sustainable learning experience is created thanks to the combination of theory and practice.Visualization of quality assurance by AI with fischertechnikThe use of artificial intelligence in quality control brings many advantages, which are already used in the automotive industry, for example. Processes can be shortened, error rates and costs minimized, and error evaluation can be standardized. The fischertechnik sorting system is supplied with workpieces in three different colors. These workpieces are equipped with three processing features and various error screens. The workpieces are scanned by the camera and classified with the help of the trained AI. Depending on the color, characteristic and fault pattern, the workpieces are then sorted by artificial intelligence based on their quality characteristics. The used AI is realized with machine learning in tensorflow, in which an artificial neural network with image data was trained. The taught-in KI is executed on the fischertechnik TXT 4.0 controller. The sequential control of the model is implemented in the programming environment ROBO Pro Coding and in Python.Generate your own AI applicationsIf you want to go one step further, you have the possibility to generate your own AI-applications. The training is carried out in Python, for which an appropriate example project is provided for explanation.Model structure of the sorting route with AISorting system for workpieces in 3 different colors (white, red, blue), with 3 different processing characteristics (drilling, cut-outs, bore+cut-outs) as well as various error patterns (drill-out and round hole, hole missing, cut-outs missing in whole or in part, cracks in the workpiece. These processing and error characteristics are simulated with the corresponding adhesive labels on the workpieces. The workpieces are scanned by the camera and classified with the help of the trained AI. Depending on the color, characteristic and error pattern, the workpieces are then sorted into 4 different shafts. The KI is implemented with Tensorflow and is executed on the TXT 4.0 controller. Own AI models can also be generated. Training is done on a computer in Python. A corresponding sample project is provided. The sequence control for the sorting system is implemented in the ROBO Pro Coding programming environment and in Python.