The fourth industrial revolution is a concept that has disrupted the conventional view of factory automation and digitalization. In fact, the objective of Industry 4.0 is the creation of a Smart-Factory, the keystone of which is CPS in production. In the last section we saw how this technology is able to reproduce the factory in virtual space in order to control and optimize processes based on the autonomy rate of the system. The Internet of Things is considered the basis for the accumulation and transmission of information and knowledge between all parties inside and outside the factory boundaries. Finally, with all the functionalities of Big Data, data storage and processing, CPS in production is able to identify and predict the optimal operating mode of each module or part of the factory. In this section, we will study a CPS embedded intelligent factory in production carried out in the second three parts that we will see during this paragraph. The revolution is that each physical element inside a Smart-Factory can be considered as an autonomous entity, equipped with a capacity for reflection thanks to integrated computing power which allows it to be autonomous in its operation. Therefore, during the working day it is monitored by widespread control operations. Thus, each element of the physical space has autonomous intelligence and moves in the direction of continuous improvement, in order to react quickly to possible uncertainties and disturbances. Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get an original essayWe are going to analyze the architecture of a smart manufacturing factory based on a CPS in production, the pillar is a modular system based on different layers that communicate with each other. From physical modules composed of equipment, AGVs and products, the system creates a cyber display in order to collect information about them in terms of movements, work progress, tasks and skills during operations manufacturing. The possibilities inside cyberspace are endless, but primarily it connects all parts of physical space and allows them to communicate regardless of co-located modules. This functionality allows having a complete and correct view of the production plant mentioned above, in addition to converting it into a flexible system capable of reacting to problems. In this section, we want to focus on the composition of a smart manufacturing factory and the different layers that make it up. These are mainly three layers of material, logic and interaction. All these layers communicate with each other, exchanging a huge amount of information and knowledge. Starting from the first stratum mentioned, it can be considered as the set of elements that drive the production processes and all the movements of resources necessary for the accomplishment of various tasks. It is easy to understand that the material layer is made up of different components, first and foremost the equipment and all the machines that physically produce the product and the product parts during the manufacturing process. Secondly, there are automated robots whose purpose is to manage and carry out the movement of material resources during their acquisition and transportation to the first phase of production and finally to store the finished product in a warehouse. Third, AGV technology which will be studied in depth in the following paragraph, which moves material resources and productssemi-finished products throughout the manufacturing process by making a link between the components mentioned above. Considering an overall overview of the physical layers assembly shop, we can say that the operations (manufacturing, transportation, moving, storage and distribution) are regulated by receiving and sending information and data in real time between entities in order to achieve a responsive system. . In summary, the performances of physical entities are mainly two: the realization of what has been designed and the acquisition of information. The second layer consists of a virtual representation of all the above-mentioned components of the material layer. In fact, in this layer the presence of an LU supervisor is expected for each physical component, LU has different roles but as one can imagine the first role is supervisor with the aim of improving and connecting the different elements of physical space. In this space, we need to consider the logical unit as a single entity with strong computational capability and therefore intrinsic thinking capability that is leveraged through communication and networking between each UL. In fact, they extrapolate information from MCs and use this data to generate control interfaces. For example, LU organizes manufacturing planning for each piece of equipment and transportation planning for all automated vehicles to move parts between machines. Thus, LU composed of integrated thinking and planning capabilities improves and organizes tasks using information and knowledge exchanged through communication links. The interaction layer is created to allow interaction between the other two layers. In fact, it relies on two gates, the first takes and exchanges information in the hardware stratum, while the second gate is operated to connect the logical stratum. The technology is based on WIFI connection and route information to make information accessible from one stratum to another. For example, consider the case where the hardware stratum updates the logical stratum on new manufacturing conditions, in this case it is a CL task to communicate the notice and apply the translation process. After that, the logical unit elaborates the information, realizes a new production model and communicates it via CL to the hardware stratus. Thus, the binding role of CL is essential. In the paragraph above, we have explained the architecture of a smart production factory, composed of physical elements that perform activities vital to the production process. After that, there are logic units with computing power, which are dislocated control interfaces that interact with each other and regulate the behavior of MCs and AGVs. The functionalities mentioned above are the basis for the development of a Smart-Factory, in an unpredictable context. In fact, it must be a flexible system, based on self-regulation and self-adaptation capabilities so as not to suffer from uncertainties and unrest. The final goal is to realize an intelligent production factory, based on autonomy and thinking capabilities, which can be summarized in a production system called NEIMS based on the operation of a biological system. Inspired by the biological system mentioned above, we will propose a production paradigm based on the functioning of the human neurological and hormonal system in order to react to the disorders and uncertainties of the production context. The system based the regulation and productivity of entities inside the plant thanks to implicit commands typical of biological regulation. As explained above, even this system isbased on diffuse control interfaces, integrating thinking capabilities and computing power. Monitoring of physical elements includes disturbances in the context in which the system operates and self-regulates independently. We will now explain how the neurocontrol and hormonal regulation system works inside a production plant, based on the architecture explained above. During the regular course of the production process, the system uses a normal biological monitor. Thus, in the event of an unexpected and critical situation, in order to react to it, the NEIMS uses hormonal regulation providing thinking capabilities to each UL, which communicates, cooperates and makes the decision to react to the disturbances itself. Think about the customer order cycle. Everything starts from an order on the website via a smartphone, this arrives at the production plan and it must be developed. LU analyzes the order and finds all the necessary functions and manufacturing processes to manufacture it. Depending on when the product is to be delivered to the customer, LU organizes with its integrated data processing the plan template for the production of the product. Taking into consideration the case of an order without a critical delivery date. The system lists the order and, through the ordinary biological control paradigm, organizes and establishes the perfect production schedule. Therefore, it may happen that the company is not able to handle the customer's order, and it turns into a rush order, because it has little time to produce and deliver on the set date. In this case, the logical units disrupt the normal order of work and regulate the new way of working through hormonal regulation. In this way, ULs store data in real time and elaborate it, in order to reorganize and reprogram the production model and to be able to deal with urgent orders or any other difficulty. In the following figure, there is shown a possible case of unforeseen challenge and difficulty on the operation of a machine. From this figure, we want to analyze the problems faced by the NEIMS system to maintain a huge level of productivity and efficiency. From the picture above it is easy to understand that there are problems in the operation of machine number three, this data on malfunctions. are transferred to the respective logical unit. In this phase it is essential to reprogram the normal way of working, in order to effectively complete and restore the product in question. The production schedule is rescheduled and the production process is left to machining and therefore the movements of the parts are reprogrammed by the logic unit of AGV number one which passes the task to AGV1 which executes the transportation. In conclusion, the product was created by a single machine, allowing production without loss of time and respecting the delivery date. Through the examples presented previously, we can affirm that systems based on biological control and regulation improve the capabilities of the production plant in terms of reasoning, intelligence and reactivity. Therefore, NEIMS is not limited to handling urgent orders or machine breakdowns, but rather it can be used to explore and develop future production solutions capable of quickly reacting to unexpected challenges and disruptions in the market environment . In this section, we will analyze a practical approach. example of the previously developed production cyber-physical system. The goal is to understand whether the system can be considered feasible and whether it leads to the incredible results mentioned above. The system architecture remains.