At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a tire inspection system for the tire industry. We provide methods for processing tire sidewall data obtained from a camera and a laser sensor. The captured data comprise visual and geometric data characterizing the tire surface, providing a real representation of the captured tire sidewall. We use an unfolding process, that is, a polar transform, to further process the camera-obtained data. The principles and automation of the designed polar transform, based on polynomial regression (i.e., supervised learning), are presented. Based on the data from the laser sensor, the detection of abnormalities is performed using an unsupervised clustering method, followed by the classification of defects using the VGG-16 neural network. The inspection system aims to detect trained and untrained abnormalities, namely defects, as opposed to using only supervised learning methods.

The article deals with methods of Artificial Intelligence and their utilisation in technical diagnostics. Special meaning will be given on methods such as Deep learning. The deep learning method seems to be a very good candidate for defect detection and pattern recognition. The method was applied for technical diagnostic in automotive factory and the problem will be described in the paper.

One of the rationalization areas is the material supply process. New tasks of material supply are: integration of supply with the operation of the entire system, especially at the product design stage, effective use of material resources, reduction of the level of supply costs from the point of view of production costs. in the conditions of unit and small batch production the materials requirement needs to be carefully planned and optimized due to the use of many different kinds, types and sizes of materials and dynamic changes of demand over time. In this situation there are needed tools enabling the measurement of production costs for particular tasks on the basis of currently realized processes. One of these tools is activity based costing which is a groundwork for decision making process in the material supply area. Basing on activity based costing, a model of materials requirements planning was developed, which considers minimizing the number of different kinds and sizes of materials by using alternative materials and, consequently, lowering production costs.

On the stage of product design there is a problem concerning production cost estimation in the moment when elements are not yet definitely designed. Depending on the amount of the available information, more or less precise cost estimation methods are applied, i.e.: variant methods, generation methods, hybrid methods. The proposed method of cost estimation is based on a formalized description of information related to construction, manufacturing and organizational characteristics concerning the designed element, the automation method of technological processes design using methods of group technology and a model of determining production costs of machine elements based on Activity Based Costing.