sustainability Review Monitoring and Control in Underground Coal Gasification: Current Research Status and Future Perspective Yuteng Xiao 1, Jihang Yin 1, Yifan Hu 1, Junzhe Wang 2, Hongsheng Yin 1,* and Honggang Qi 3 1 School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China; [email protected] (Y.X.); [email protected] (J.Y.); [email protected] (Y.H.) 2 Bell Honors School, Nanjing University of Posts and Telecommunications, Nanjing 210023, China; [email protected] 3 School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 101408, China; [email protected] * Correspondence: [email protected]; Tel.: +86-137-7589-2769 Received: 23 October 2018; Accepted: 29 December 2018; Published: 4 January 2019 Abstract: By igniting in the coal seam and injecting gas agent, underground coal gasification (UCG) causes coal to undergo thermochemical reactions in situ and, thus, to be gasified into syngas for power generation, hydrogen production, and storage. Compared with traditional mining technology, UCG has the potential sustainable advantages in energy, environment, and the economy. The paper reviewed the development of UCG projects around the world and points out that UCG faces difficulties in the field of monitoring and control in UCG. It is expounded for the current research status of monitoring and control in UCG, and clarified that monitoring and control in UCG is not perfect, remaining in the stage of exploration. To improve the problem of low coal gasification rate and gas production, and then to make full use of the potential sustainable advantages, the paper offers a perception platform of a UCG monitoring system based on the Internet-of-Things (IoT) and an optimal control model for UCG based on deep learning, and has an outlook on breakthrough directions of the key technologies related to the package structure design for moisture-proof and thermal insulation, antenna design, the strategy for energy management optimization, feature extraction and classification design for the network model, network structure design, network learning augmentation, and the control of the network model, respectively. Keywords: underground coal gasification; monitoring and control; Internet of Things; deep learning 1. Introduction Coal is one of the most important fossil fuels in the world, playing a vital role in human production, especially in industrial heating, urban gas production, power generation, and other fields. However, the use of coal, especially the emission of sulfides and nitrogen oxides during coal combustion, causing a series of environmental problems, has seriously affected the physical and psychological health and living quality of human beings all over the world [1]. One way to solve these problems is UCG. It converts coal into gas, followed by the operation of removing sulfides and nitrogen oxides, bypassing the traditional coal-burning process, and has the characteristics of low pollution emission [2]. In addition, UCG is also characterized by a high resource utilization rate [3] (it can exploit the unmineable coal compared with the traditional mining technology, such as coal that is too deep, of low grade, and in thin seams) and low cost [4] (water and coal in situ can be used directly during Sustainability 2019, 11, 217; doi:10.3390/su11010217 www.mdpi.com/journal/sustainability Sustainability 2019, 11, 217 2 of 14 Sustainability 2019, 11, x FOR PEER REVIEW 2 of 14 UCG process, reducing operating costs). Therefore, UCG is one of the most promising sustainable sustainable technologies in energy, environment, and the economy, having broad application technologies in energy, environment, and the economy, having broad application prospects [5]. prospects [5]. Figure1 illustrates the schematic diagram for UCG. With the compressor injecting a gas agent Figure 1 illustrates the schematic diagram for UCG. With the compressor injecting a gas agent (air, oxygen, oxygen enrichment with different concentration, carbon dioxide, or steam) through an (air, oxygen, oxygen enrichment with different concentration, carbon dioxide, or steam) through an injection well, the coal in the coal seam, deeply buried under overburden, is gasified into syngas by injection well, the coal in the coal seam, deeply buried under overburden, is gasified into syngas by igniting in the active cavity. Then the harmful gases, such as sulfides and nitrogen oxides, in syngas are igniting in the active cavity. Then the harmful gases, such as sulfides and nitrogen oxides, in syngas in the operation of gas cleaning and the residue is left underground. Finally, the syngas with H2, CO, are in the operation of gas cleaning and the residue is left underground. Finally, the syngas with H2, and CH4, which is output through the production well, becomes a clean feed gas for power generation, CO, and CH4, which is output through the production well, becomes a clean feed gas for power hydrogen production, and storage [6,7]. generation, hydrogen production, and storage [6,7]. Figure 1. Schematic diagram for UCG. Figure 1. Schematic diagram for UCG. InIn thethe nearly nearly 100 100 years years of research of research and practice and inpractice the world, in the many world, experiences many andexperiences achievements and haveachievements been accumulated have been in accumulated the methods in and the technologies methods and of technologies UCG. However, of UCG. in practice However, the gasification in practice processthe gasification needs to beprocess monitored needs and to controlledbe monitored to ensure and thatcontrolled the underground to ensure gasificationthat the underground has a stable combustiblegasification has gas a composition stable combustible and calorific gas composition value, as well and as calorific a higher value, gas yield as well and as gasification a higher gas rate yield [1]. UCGand gasification is a very complex rate [1]. physical UCG is and a very chemical complex process, physical and manyand chemical factors affectprocess, the and composition many factors and qualityaffect the of syngas.composition Considering and quality high of temperature syngas. Considering humidity high and closedtemperature environment, humidity it and is difficult closed toenvironment, effectively monitor it is difficult and controlto effectively the UCG monito processr and to control improve the the UCG quality process of theto improve syngas. the Therefore, quality scholarsof the syngas. in various Therefore, countries scholars have in carried various out countries a series have of meaningful carried out research a series onof meaningful the monitoring research and controlon the inmonitoring UCG, such and as control the GPR in (Ground UCG, such Penetrating as the GPR Radar) (Ground technique Penetratin for theg monitoringRadar) technique [8,9], and for studythe monitoring on controlling [8,9], theand combustion study on controlling state in the the gasification combustion process state in [10 the–14 gasification]. There are process few related [10– studies,14]. There technical are few means related remaining studies, on technical paper, or means at the experimentalremaining on teaching paper, level,or at andthe basicexperimental research isteaching almost level, blank. and Therefore, basic research there are is almost still some blank. obstacles Therefore, standing there inare the still way some to actualobstacles application standing atin present.the way to In actual recent application years, with at present. the rapid In developmentrecent years, with of the the Internet-of-Things rapid development (IoT) of the and Internet- deep learningof-Things research (IoT) and [15– 19deep], great learning success research has been [15–19], achieved great in solving success complex has been monitoring achieved and in controlsolving problemscomplex monitoring [20–25]. This and undoubtedly control problems provides [20–25]. a new This idea undoubtedly for the monitoring provides and a new control idea of for UCG. the monitoring and control of UCG. Based on this, the paper puts forward a new idea about monitoring and control of UCG based on IoT and deep learning to improve the problem of the low coal gasification rate and gas production, and then makes full use of the potential sustainable advantages. Sustainability 2019, 11, 217 3 of 14 Based on this, the paper puts forward a new idea about monitoring and control of UCG based on IoT and deep learning to improve the problem of the low coal gasification rate and gas production, and then makes full use of the potential sustainable advantages. This paper reviews the development of UCG projects worldwide and the research progress related to monitoring and control for UCG. Taking the development of IoT and deep learning as an opportunity, it is a new idea of applying the IoT and deep learning into monitoring and control in UCG to be put forward, and the key technical breakthrough directions related to them are also discussed. 2. The Development of UCG Projects Worldwide In 1868, William Siemens creatively proposed the technical idea of coal gasification in the underground, and then the Russian chemist Dimitri I. Mendeleev proposed the process conception of UCG in 1888 [26]. By the beginning of the 20th century, as many cities were covered with smoke from the side effects of the Industrial Revolution, William Ramsay opened the first UCG test in Durham, England to try to solve the problem [27]. Since then, the world’s major coal powers have been competing for