The integration of internet of things (IoT) technologies has been a key aspect in the advancement of modern smart factories, separating them from traditional automated factories. Smart factories use IoT to control automated manufacturing equipment and defect detection tools, leading to improved production efficiency and quality. In this study, the authors propose a concept of a smart factory that integrates deep learning algorithms into a defect detection system and outlines the network architecture for the proposed smart factory. The proposed smart factory system employs equipment for manufacturing, functional testing and problem detection while utilizing checkpoints to identify faulty goods. Defect detection technology is widely used throughout the production, packaging, and functional testing processes, resulting in reduced costs and increased yield of final products. This leads to a more efficient production process, with less waste and higher quality products. Moreover, the proposed smart factory concept utilizes deep learning techniques in internet technology for defect detection.
Top1. Introduction
In this research article, we propose a method for recognizing cyber physical systems in a smart manufacturing system using wireless connectivity and deep learning techniques in industrial processes. Cyber physical systems (CPS) are a combination of physical and cyber systems that interact with each other in real time, and are becoming increasingly important in the field of manufacturing. The integration of CPS in smart manufacturing systems can improve efficiency and flexibility, but it also poses new challenges in terms of communication and data management. Our proposed method utilizes wireless connectivity and deep learning techniques to overcome these challenges and improve the recognition of CPS in smart manufacturing systems. The results of this research have the potential to enhance the efficiency and flexibility of industrial processes and contribute to the advancement of smart manufacturing technology (Galambos et al. 2018; Liu et al. 2021).
In recent years, the integration of cyber physical systems (CPS) in smart manufacturing systems has gained significant attention due to the potential improvements in efficiency and flexibility. CPS are a combination of physical and cyber systems that interact with each other in real time, and they have the ability to improve the monitoring, control, and decision-making capabilities of manufacturing systems (Cui 2021; Martinez et al. 2022).
One of the main challenges in integrating CPS in smart manufacturing systems is the communication and data management between the physical and cyber systems. Wireless connectivity has been proposed as a solution to this challenge, as it allows for real-time communication and data transfer between the CPS and the smart manufacturing system.
Several researchers have proposed the use of wireless technologies, such as WiFi and Zigbee, for the communication between CPS and smart manufacturing systems. In a study by (Xie et al. 2021), the authors proposed a wireless communication system based on WiFi for the monitoring and control of industrial robots in a smart manufacturing system. The system was able to achieve a high data transfer rate and low latency, demonstrating its potential for use in industrial environments.
Another study (Schneider et al. 2019) proposed the use of Zigbee technology for the communication between CPS and smart manufacturing systems. The authors developed a wireless sensor network based on Zigbee for the monitoring and control of a machining process. The system was able to improve the efficiency and flexibility of the machining process by providing real-time data on the machining conditions. Deep learning techniques have also been proposed as a solution to the challenges of CPS recognition in smart manufacturing systems. Deep learning is a type of machine learning that is able to learn from data and make decisions based on that data. It has been shown to be effective in image and speech recognition, and has been proposed for use in industrial processes as well.
In a study by (Streitz 2019), the authors proposed the use of deep learning for the recognition of CPS in a smart manufacturing system. The authors developed a deep neural network for the recognition of industrial robots in a manufacturing system. The system was able to achieve a high recognition rate and low computational complexity, demonstrating its potential for use in industrial environments.
Another study (Liu et al. 2020) proposed the use of deep learning for the recognition of CPS in a smart manufacturing system. The authors developed a deep convolutional neural network for the recognition of machines and equipment in a manufacturing system. The system was able to achieve a high recognition rate and low computational complexity, demonstrating its potential for use in industrial environments.