(195f) Stepping Towards the Industrial Sixth Sense

Industry 4.0 is transforming chemical processes into complex, smart cyber-physical systems, by the addition of elements such as smart sensors, Internet of Things, big data analytics or cloud computing. Modern engineering systems and manufacturing processes are operating in highly dynamic environments, and exhibiting scale, structure and behaviour complexity. Under these conditions, plant operators find it extremely difficult to manage all the information available, infer the desired conditions of the plant and take timely decisions to handle abnormal operation¹. Human beings acquire information from the surroundings through sensory receptors for vision, sound, smell, touch, and taste, the Five Senses. The sensory stimulus is converted to electrical signals as nerve impulse data communicated with the brain. When one or more senses fail, the humans are able to re-establish communication and improve the other senses to protect from incoming dangers. Furthermore, a mechanism of ‘reasoning’ has been developed during evolution, which enable analysis of present data and generation of a vision of the future, which might be called the Sixth Sense. As industrial processes are already equipped with five senses: ‘hearing’ from acoustic sensors, ‘smelling’ from gas and liquid sensors, ‘seeing’ from camera, ‘touching’ from vibration sensors and ‘tasting’ from composition monitors, the Sixth Sense could be achieved by forming a sensing network which is self-adaptive and self-repairing, carrying out deep-thinking analysis with even limited data, and predicting the sequence of events via integrated system modelling.

This contribution introduces the development of an intelligent monitoring and control framework for chemical process, integrating the advantages of Industry 4.0 technologies, cooperative control and fault detection via wireless sensor networks. The framework consists of four main components. The first one is a wireless sensors network, transmitting over a 5G communication network, that facilitates data management for improved fault detection. The second component is an efficient fault detection algorithm that can analyse the data and classify it in faulty or normal. The third component is a knowledge-based and a model-based fault detection monitoring system. For the fault-detection, a two-stage method based on a hybrid learning approach is applied, which utilises supervised and unsupervised learning. Finally, the fourth component is a cooperative model predictive control system that takes the required measures to ensure stable process information. Under the cooperative framework, the distributed controllers share information about their state with other controllers, thus interaction between processing units is not lost. Using information on the process’ structure and behaviour, equipment information, and expert knowledge, the system is able to detect faults. The integration with the monitoring system facilitates the detection and optimises the controller’s actions. The chemical process is a mini-plant that produces sodium ion solution as sodium chloride for the fine chemical, the pharmaceutical and the food industry. The dataset used for simulations consists of over 10 million samples, with each sample having 43 variable measurements, including temperature, flows, pressures and levels, collected by deployed wireless sensors set up on the process units. The results indicate that the proposed approach achieve high fault detection accuracy based on plant measurements, while the cooperative controllers improve the control of the process.

1. Natarajan, S., & Srinivasan, R., 2014, Computers and Chemical Engineering 60, pp. 182-196