supports industries to switch production according to needs and the possible adaptions of the available production machines in new requested products. Furthermore, if correctly implemented, AI provides improvements in the production time response and in the machine efficiency of the whole production line, where all the machines of a layout not only work to create a finished product, but also are set for the best efficiency. It is observed that, in an advanced local communication system, the single machine can communicate the identified setting solution to all the other machines involved in the production. By applying AI, it is possible to achieve the optimum of the economic and operating criteria, by setting the production level of all the individual units that work together. The production setting is managed by means of a supervision and coordination system, where the AI system is suitable to adapt the processing to each reconfiguration of the production programs and of the product mixing to meet customer requirements in the best way.
Figure 1.11 Artificial intelligence integrated into the supply chain.
In manufacturing industries, the AI system is integrated in a more complex multilayer structure, as illustrated in Figure 1.12, with the following layers:
Layer 1 (direct control of the single units of the plant). Information about the unit production and about raw materials are executed and transmitted to the highest levels. The first layer is the operational layer enabling production and actuation. The production parameters are optimized by layer 3 related to the AI level.
Layer 2. This layer represents the response to any emergency condition arising in its area of competence of the plant, the optimization and the coordination node keeping communications active with the upper and lower levels of the system. The layer is commanded by layer 3 and provides outputs to layer 1.
Layer 3 (AI level). This level is suitable for verification and optimization of key production processes in real time. The management of this level is assigned to AI algorithms. Improvement solutions can be implemented in all phases of the production process by automatizing the whole supply chain. This layer is the core of the Industry 5.0 system and includes process mining (process decision making by data mining) [53], process optimization, process prediction and process control. IoT data contribute in this level to enrich the dataset processed by the AI algorithms for better control of processes upgrading the production. Graphical dashboards facilitate the decision‐making supported especially by supervised algorithms. The AI allows not only to improve the production process, but also to predict possible failures in a self‐adaptive manner.
Layer 4 (definition of the activities to coordinate the production resources and to achieve the desired final products). This layer is specific for the production area involving RE facilities, production engineering, quality improvement, data processing, and production switching enabled by the AI level. This layer represents principally the production flexibility, the production quality, and the reliability.
Figure 1.12 Multilevel structure of manufacturing industry processes integrating artificial intelligence tools.
The multilevel model of Figure 1.12 is summarized by the block diagram in Figure 1.13, where AI is the feedback of the whole system, layers 1, 2, and 3 represent the single production station, and layer 4 indicates the whole production line processes performing machine diagnostics.
Figure 1.13 Artificial intelligence feedback system in manufacturing processes.
The proposed methodology is adaptable to different industry sectors and represents a valuable tool for the ISO 9001:2015 check control system.
1.3 Intelligent Automatic Systems in Industries
Intelligent systems are implemented by AI algorithms, applied also for the intelligent movements of robotic arms [54]. Motors can control robotic arm movements by commands as coded outputs of the AI algorithms. In this scenario, robotic movements are actuated by image processing and image recognition [55]. In this way, image features classification by AI, and IoT data are fundamental to enable automatic processes. A central workstation [56] can manage the automatic processes by receiving control signals and by activating robotic operations. Robotic manipulation is an important topic in industry automation involving application fields such as self‐adaptive robotic fingers optimized for collaborative robots [57]. The AI engine can optimize the production parameters. The parameter configuration can be performed off‐line [58] or in‐line. The in‐line parameter setting by AI, is an issue for the modern adaptive solutions: auto‐calibration in real time of machine working parameters can be catastrophic if the AI model fails. For this purpose, it is fundamental to construct robust AI models. A more complex industrial environment involves multiple workers, worker tracking, and security aspects [59]. In this scenario the auto‐adaptive solution is applied also to check dangerous positions of workers by stopping machines in the case of alerting conditions, by applying image vision techniques. Image vision is implemented also for robot guidance solutions [11]. Production process simulations improve robotic production. Simulations are performed in static (time independent) or dynamic (time dependent) conditions [60], and are useful to define adaptive conditions. Adaptive solutions are oriented on reconfigurable applications supporting complex positioning tools [61], and robotic capabilities including sensing, production intelligence, and motion. Robots automatically follow instructions by a standard program or generate in real time mechatronic actions by processing sensor data. To optimize the formulation of instructions, image vision techniques are potentially applied together with AR tools, by improving the monitoring of the correct product assembly, by detecting and predicting defects detection, and by adapting actuations. The input data such as historical production data, data sensors and digitized information, are processed for a dynamic parameter setting and for the formulation of new high‐performance programs. Historical production data are typically collected into a big data system able to contain massive data. Digitized information is coded into a dataset to be processed by the AI engine. The PLC is typically interfaced to an electronic board reading a standard program (standard parameter set), or actuating command coming from a protocol, by means the decoding of the AI outputs. The production process control is usually performed by image vision techniques and by IoT sensors placed inside the machines (internal IoT) or outside (external IoT). The architecture describing all the functions in advanced manufacturing processes is illustrated in Figure 1.14.
Figure 1.14 Block diagram of adaptive solutions in advanced manufacturing.
1.4 Technological Approaches to Transform the Production in Auto‐Adaptive Control and Actuation