[40]
HTTP, Hypertext Transfer Protocol; KNX, Konnex; LoRa, long range; SSL, secure sockets layer;, Transmission Control Protocol;, transport layer security;, User Datagram Protocol; XML, eXtensible Markup Language.
Particularly interesting is the LoRaWAN protocol suitable for long range wide area network (WAN) wireless technology tailored for IoT interconnection, and for bidirectional communication systems. The main features of this protocol are the low power consumption, and the possibility to improve scalable wireless networks.
1.2 State of the Art of Scientific Approaches Oriented on Process Control and Automatisms
Technologies and architectures are fundamental for the upgrade of the company production. Different examples are provided to comprehend how innovative tools, including AI, can be applied in a new production scenario.
1.2.1 Architectures Integrating AI
The software and the hardware, in a modern information system oriented on Industry 5.0, must be integrated into a flexible information system infrastructure structured as illustrated in the model of Figure 1.4, where the first layer is represented by the hardware layer constituted by sensors and in general by IoT devices. The firmware layer is programmed in an operating system (OS) framework to provide a defined application including control and actuation processes. The AI interface is the intelligent core of the system, able to update machine setting, by considering prediction of failure conditions, and by automatically adjusting machine and robot working conditions. This automatism is a fundamental aspect of Industry 5.0 systems, where processing functions are managed in auto‐adaptive modality. The AI algorithms can be executed directly in the application layer by executing a code (python, java, visual basic, etc.), or by using objects of GUIs. In the architecture model of Figure 1.4, the processor, operates in multitasking and multiuser modality, where the central processing unit (CPU) time is divided for all the programs that work simultaneously. The AI engine and the OS manage the database management system (DBMS) able to collect digital information of the whole supply chain. Furthermore, AI is suitable to exchange data and digital commands to electronic boards, interfacing machines or robots as for intelligent actuators.
Figure 1.4 Hierarchical scheme of the software in Industry 5.0.
Another important element for Industry 4.0 and Industry 5.0 implementations are the PLC systems enabling the actuation. The block scheme of Figure 1.5 represents a variation of the classic Von Neumann microprocessor scheme including the AI capability in the PLC system. The PLC system is constituted by:
A random access memory (RAM).
A microprocessor.
Input and output (I/O) ports.
An AI engine interfaced with a Programming Unit interface.
Figure 1.5 Advanced PLC architecture in Industry 5.0: central processing unit (CPU), memory, I/O ports, Program Unit module, and AI upgrading industrial processes.
1.2.2 AI Supervised and Unsupersived Algorithms
Different technologies can be integrated to improve Industry 4.0 production processes and in general digitalization. In industrial cases, supervised and unsupervised AI image vision tools detecting defects can be adopted. In this way, image vision and 3D image reconstruction methods play an important role as for assembling processes in the tire industry [41]. The image processing of raw images requires usually a high computational cost and is applied in post‐processing modality. Concerning real‐time processing, image segmentation techniques detect most relevant defects but more information about probable defects is hidden and is not easily visible in standard industrial environments. The hidden defects are “extracted” by more accurate inspections and by the application of specific intelligent image processing algorithms enhancing anomalous features. Intelligent algorithms are usually named machine learning (ML). In Table 1.6 the main ML unsupervised and supervised algorithms are classified [42]. The supervised learning algorithm processes a known input dataset and data outputs to learn the regression/classification model. In supervised learning approaches, the training is performed by “labelled” data, selecting specific variables to focus the analysis: some data are already tagged with the requested answer, and the labeled data are adopted for the self‐learning of the algorithms predicting outcomes of the labeled variables. Unsupervised learning is the training modality of the algorithm which processes a dataset that is not classified/labeled. In the unsupervised learning approaches the model does not need to be supervised: the models discover information and common features of the variables (attributes) and find all kinds of unknown patterns in the data. The learning phase is structured in the following sequential steps:
Training dataset construction.
Features vector extraction.
Algorithm application setting data processing parameters.
Training model construction.
Table 1.6 Classification of machine learning algorithms.
| Machine learning algorithm class | Unsupervised | Supervised |
|---|---|---|
| Continuous | Clustering:K‐meansMean shift clusteringDensity‐based spatial clustering of applications with noiseExpectation maximization Clustering using gaussian mixture modelsAgglomerative hierarchical clusteringDimensionality reduction:Principal component analysisSingular value decomposition | Linear regressionPolynomial regressionArtificial neural networkRandom forestsDecision trees |
| Categorical | Association analysis:AprioriFP‐growthHidden Markov model | Classification:k‐nearest neighborsDecision treesLogistic regressionNaïve BayesArtificial neural networkSupport vector machine |
Both classes of supervised and unsupervised algorithms are typically applied for data processing applications of image processing for feature classification.
A typical class of unsupervised algorithms are the clustering ones. Clustering methods are able to group objects
