Development of a real-time machine learning system for MGS At SHJ Medical Gas Specialists, based in Chesham, UK, we have developed a real- time machine learning system for the optimal operation of MGS, utilising a set of emerging IT technologies including 4G/5G , artificial intelligence (AI), the IoT, blockchain and cloud and edge computing. It uses real-time big data analytics to enhance productivity and efficiency and to optimise decision making and performance, creating an opportunity to apply real-time AI techniques for advanced control, management and maintenance by collecting data from sources on the IoT networks. Qualitative and quantitative data

analysis builds a next-generation decision support system that can also action changes to optimise the efficient operation of MGS. This is a new data-driven model that is dramatically changing the landscape of the healthcare sector by providing digital solutions with innovative measures. Experimental results have demonstrated that up to 30 per cent of energy costs can be saved through real- time AI optimisation. Optimum performance of system

operations is achieved by leveraging the trained deep neural network (DNN) with edge computing and distributed cloud over the IoT communication networks, where the sensing capabilities and the computational power are provided by the designed controller, transmitter and distributed cloud to track everything that is relevant to operations. Through such deep learning and big data analysis, we can develop a knowledge base from which to correct errors and perform focused maintenance procedures without unnecessary interruptions, thus improving efficiency and maximising profitability. It has been shown that the real-time machine learning system can be used to provide fault detection and isolation capabilities and can be integrated within an optimal control framework (trained by AI) to respond to the changing conditions of medical air plants. This optimal controller is enabled to provide its own monitoring capabilities which can be used to identify faults within the process and also within the controller itself. As discussed previously, compressed

air currently costs many times the price of electricity and MGS are often operated inefficiently. IoT and blockchain technologies can be used to modernise medical gas alarms, improve reliability and security and reduce networking costs. Remote monitoring, fault detection and isolation tasks can be performed to achieve the maximum life and efficiency from MGS using fibre-optic/industrial bus or wireless (or both for redundancy), designed and built for real-time data collecting and analysis.


The fibre-optic communication thus has been developed to increase data rates without electromagnetic or radio frequency interference (EMI/RFI), and to provide a cost-effective way to transmit more information with guaranteed safety. The wireless communication network based on self-developed protocol by an ultra-high frequency (UHF) radio frequency (RF) can achieve up to a two kilometre wireless link. With the IoT communication network built, real-time monitoring and intelligent control of MGS can be achieved, so that we can have an eagle-eye view of every event while it is happening. The IoT networks developed will require

greater capacity to support sensors that monitor and control a wide range of industrial processes and equipment, reporting back into a central console. Not only is the IoT driving more bandwidth, it is also driving a consolidation of IT systems to better process valuable production data and enable faster decision making based on this information. Coupled with emerging technologies such as 4G/5G and blockchain resistant to modification of the data to connect people and business processes, the IoT allows objects to be sensed or controlled remotely across the network. This creates opportunities for more direct integration of the physical world into computer-based systems, and results in improved efficiency, accuracy and economic benefit as well as reduced human intervention. It also creates an opportunity to

improve the efficiency of intelligent MGS by applying machine learning and AI techniques for advanced control, management and maintenance. This allows the upgrade of current systems by

collecting data from all sources on the IoT networks for real-time big data analytics. Such next-generation decision support systems will optimise the efficient use and operations of MGS. With the development and implementation of remote monitoring and intelligent control of MGS through the integration of advanced data communication technologies for industrial IoT networks with combined edge computing and distributed cloud for machine learning, a new optimal, energy- efficient operation of medical compressed air plant has been developed. Massive data, such as from vibration and acoustic measurements, is remotely collected through the newly-built supervisory control and data acquisition (SCADA) and IoT networks. The complex processes are modelled

and trained by a DNN using multilayer perceptron (MLP) with adaptive learning rate and wavelet activation function. This rapidly identifies network coefficients for minimising energy consumption by Bayesian optimisation with Gaussian processes, and allows higher accuracy of fault detection and prediction (such as leakage), and condition monitoring-based predictive maintenance (using AI algorithms to predict the next failure of a component/machine/system). This leads to a highly efficient and reliable operation of MGS.

System Implementation SHJ has developed and implemented a real-time machine learning system from product design to customised production, through feasibility studies, innovative technologies development and system prototype testing. Using printed circuit boards (PCBs) as machine controllers, signal collectors and transmitters and developing IoT communication networks for real-time monitoring, control and AI optimisation, we have constructed an intelligent plant control and predictive maintenance system for the highly efficient operation of MGS. It enables remote monitoring and

control, risk reduction and shorter response times and provides essential management data for predictive maintenance purposes. This has been achieved through changing the current way of designing, installing and running MGS. The next-generation SCADA and IoT networks and the products and intelligent energy-saving systems developed use a three-level process and data specification framework:

SHJ’s Empower plant control system provides real-time diagnostics, alerts and fault detection on their medical gas plant.

SCADA and IoT networks with data communication assured by blockchain 1 UHF (RF Wireless, product deliverable) to on-site remote monitoring station/tablet PC screen.

2 Hardwired (RS485/Optical Fibre, 41

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  |  Page 98  |  Page 99  |  Page 100  |  Page 101  |  Page 102  |  Page 103  |  Page 104  |  Page 105  |  Page 106  |  Page 107  |  Page 108  |  Page 109  |  Page 110  |  Page 111  |  Page 112  |  Page 113  |  Page 114  |  Page 115  |  Page 116