GAOYONG LUO – RESEARCH AND DEVELOPMENT LEAD, SHJ MEDICAL GAS SPECIALISTS, UK MEDICAL GAS SYSTEMS


Real-time AI control of medical gas systems


Gaoyong Luo of SHJ Medical Gas Specialists explains how real-time AI systems can achieve optimum performance of medical air plants with power efficiency optimised by predictive control.


Increasing pressure on the National Health Service (NHS) as a result of the pandemic has increased the demands for oxygen supply from medical gas systems (MGSs), thus causing higher energy consumption and greater impact on the environment. NHS hospitals have made considerable advances to reducing carbon footprints and emissions by building resilience and adaptation into the heart of carbon net zero strategies. This response to the immediate pressure has reinforced the need to build smart hospitals as net zero carbon buildings, with more sustainable and energy-efficient operation of structures by accelerating the adoption of digital technologies in healthcare. However, due to the complexity of adoption of different types of innovation in different NHS contexts, it still remains a challenge to identify a route to net zero emissions and to digitise the NHS for such as complex MGSs, where the combinations of reliability, energy inefficiency, air quality, and plant downtime are considered as the key risks. To realise the potential benefits of


technological innovations, an AI-based data-driven system over IoT (Internet of things) networks has been researched and developed by implementing Industry 4.0, known as the fourth industrial revolution and the digital transformation for smart industry, where the objective is to make production processes and decision- making more efficient, autonomous, and


AI-based data-driven systems can now be delivered to help digitise the healthcare industry


adaptive using AI, cyber-physical systems, big data IoT.1


These processes, resource


utilisation, and productivity can then be improved and maximised through qualitative and quantitative data analysis that provides descriptive, predictive, and prescriptive inputs and feedback loops. This explains why technology enabling big data capture (sensing), analysis (cloud computing), connectivity (IoT), and intelligent monitoring and control (AI algorithm) is becoming the new baseline for building smart hospitals. By using mathematical algorithms and input- output models to enhance productivity and efficiency, and enhance decision- making and performance, AI and machine learning can create insights that provide visibility, predictability, and automation of operations, and can be applied to produce technology innovations to power products and services that benefit from the digital transformation of Industry 4.0.2


Due to


the availability of vast data sets over IoT networks, AI-based data-driven systems


Gaoyong Luo Gaoyong Luo is a Chair Professor of Electronics Information and


Communication Engineering and leads Research and Development at SHJ Medical Gas Specialists. Prof. Luo is a renowned expert in the field of wavelets, artificial intelligence, multicarrier spread spectrum communications, angular momentum modulation,


remote sensing, and audio coding, with expertise in control and modulation theory and applications to automation and communication systems. Prof. Luo has published over 100


referred journal/conference papers and 20 patents and is the author of Wavelets in Engineering Applications. He has taught thousands of students and supervised the work of PhD students, conducting research to serve both academia and industry.


36


and products can now be delivered to help digitise the healthcare industry and to better serve this sector. Facing the burden of coronavirus, and


to maintain a stable supply of all medical gases and keep their systems operating with the best efficiency to create the safest possible environment and support remote working environments, it has become increasingly important to remotely monitor MGSs and intelligently control medical air plants, where sensing, data processing, communication technology, and AI can be integrated to enable the systems to make confident decisions, as well as optimising the operations and maintenance of processes of prediction and prevention. Remotely monitoring MGSs in real-time over IoT networks where all devices are connected also allows a global vision and the reporting of any parameter/anomaly so that hospitals can enhance usage of medical gases and reduce risk of failure. Also, using data collected from IoT networks for real-time inference can help create predictive maintenance programs based on machine condition monitoring, resulting in more uptime and higher efficiency. This would allow the hospital equipment maintenance provider to constantly verify that the system is operating safely and make reasonable adjustments to optimal performance. At the facility and system level, to meet the emerging challenge of the energy-efficient and optimal operation of medical air plants, a real-time AI enabled system is designed to perform intelligent plant control with respect to energy savings and reduced costs and carbon emissions,3


and


to implement predictive maintenance. By building IoT networks to remotely collect data and deriving tight frame Mexican hat wavelet with sparse representation4


as


activation functions to construct novel deep wavelet neural networks (DWNNs) to process streaming data for predictive control, faults prediction and machines condition monitoring, real-time AI can now be applied to improve control strategy and optimise system performance.


IFHE DIGEST 2023


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92  |  Page 93  |  Page 94  |  Page 95  |  Page 96  |  Page 97