Article by: Asst.Prof. Yod Sukamongkol
Faculty of Engineering, Ramkhamheang University
Industrial 4.0 need the alternative technologies which are Internet of Things (IoT) and Artificial Intelligence (AI). AI is a general term used to describe various forms of advanced computational and control techniques associated with the analysis of large data sets. These techniques mimic the natural reasoning process of the human brain. At present, AI is initially used to serve the human’s needs, for example, in the self-driving car, user assistance in smart phone, waitress robot, etc.
AI’s characteristics consist of
Acting Humanly: AI can act like a human as communicate with natural language, or it can sense the surrounding condition and it can learn and respond as a machine learning.
Thinking Humanly: AI can think like a human cause its analyzed processes use the mathematical models as the basis of which is the artificial neural network imitating a nervous system in the human brain.
Thinking rationally: AI can use the data mining as the base case and analyze them logically, reasonably and wisely.
Acting rationally: After rationally thinking, AI can respond and action efficiently due to the real-time surrounding condition
How does AI work?
AI makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. Due to these technologies, computers can be trained to accomplish specific tasks by processing large amounts of data and recognizing patterns in the data, therefore, AI works by combining large amounts of data with fast, iterative processing and intelligent algorithms, allowing the software to learn automatically from patterns or features in the data.
In fact, first, AI need lots of set of data or parameters and use data mining techniques to search historical data and identify process, opportunities, process bottlenecks and process variability issues. As neural networks analyze data with genetic algorithms more wisely than conventional techniques, AI can minimize processes by selecting the best operational set point and working condition. Then, its self-learning will develop artificial expert systems that contain the knowledge discovered during the data mining exercise along with that of domain experts to control the high efficiency machine’s operation with optimal conditions.
How does AI use for Energy Conservation in Factory?
According to lots of parameter data sets are needs for training AI, the accuracy and precise sensors and smart meters are necessary to implement for measuring those parameters which effect the energy used in the factory. IoT technologies and internet network system are also required to sent data and communicate with AI. The net result of utilizing artificial intelligent techniques in industrial environments will be an improvement in the factors that influence complex industrial processes and, finally, lead to the energy used efficiently.
At present, Department of Industrial Works, Ministry of Industry, lunches a policy to promote the use of smart boiler system which composes of sensors, IoT and AI. The necessary parameters and analyzed the energy conservation of operating boiler are shown in the following table.
By using artificial intelligent techniques, it is, therefore, possible to discover for example patterns in a steam production system of the boiler that may cause production bottleneck, or an increase in process variability resulting in reduced product quality or increase energy usage and cost. In addition, AI’s responds that control the operation of boiler, such as water level, steam’s pressure and steam’s temperature at real-time, this result in the decrement of risk of accident occurred, on another hand, AI increases the safety of boiler operation. Moreover, AI can also control the quality and quantity of emission followed the environment friendly regulation.
Although, AI has lots of benefits, for example, energy conservation, energy efficient, safety and environment friendly, as described above, the feasibility study of implement AI system in the factory must be considered because, presently, its installation cost still high due to Intelligent sensors, advanced control, monitoring device, software process modelling and simulation, data storage and AI management systems. In addition, the human resources like operators, workers and owners must be educated in this AI Technologies to prepare and can use this tech efficiently when it is implemented.
