Current Issue

20 September 2019, Volume 1 Issue 3

Previous Issue    Next Issue

Comprehensive Reviews

Parallel rail transportation system

Bin NING

2019, 1(3):  215-218.  doi:10.11959/j.issn.2096-6652.201931

Asbtract ( 442 )   HTML ( 40)   PDF (414KB) ( 621 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the development of new perception, big data, artificial intelligence, and cloud computing techniques, the innovation of railway transportation systems is completely promoted. The parallel rail transportation systems are presented, in which the artificial rail transportation systems are the digitalization, modelling, and software definition of real rail transportation systems. The artificial rail transportation systems are the virtual reconstruction of real rail transportation systems in the cyberspace. The artificial rail transportation systems and real rail transportation systems are coexisting, parallel running, and interacting, which enables data-and-intelligence-driven decisions to lead to a new paradigm of intelligent management, operation, and services of rail transportation systems.

General game AI with statistical forward planning algorithms

LUCAS Simon, Tianyu SHEN, Xiao WANG, Jie ZHANG

2019, 1(3):  219-227.  doi:10.11959/j.issn.2096-6652.201935

Asbtract ( 584 )   HTML ( 172)   PDF (1413KB) ( 1197 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Statistical forward planning (SFP) algorithms use a simulation model (also called forward model) to adaptively search for effective sequences of actions.They offer a simple and general way to provide rapidly adaptive AI controllers for a variety of games.The two powerful SFP example algorithms:Monte Carlo tree search and rolling horizon evolution were introduced in this paper and key insights into their working principles were provided.It is demonstrated that the algorithms are able to play a variety of video games surprisingly well without the need for any prior training.

Regular Papers

End-to-end parallel autonomous mining systems and key technologies

Chao YANG,Yu GAO,Yunfeng AI,Bin TIAN,Long CHEN,Jian WANG,Fei-Yue WANG

2019, 1(3):  228-240.  doi:10.11959/j.issn.2096-6652.201929

Asbtract ( 476 )   HTML ( 37)   PDF (1003KB) ( 552 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In view of the current research situation and the urgent demand for unmanned mines,the end-to-end parallel autonomous mining solution was proposed based on the ACP method in this paper.The research status of unmanned mining transportation system was analyzed.The basic framework of parallel autonomous mining was designed.The parallel autonomous mining are mainly composed of four parts:the management and control center for autonomous mining,the autonomous transportation platform of truck,the autonomous mining/shovel platform and the remote take-over platform.The 7 key technologies for realizing parallel autonomous mining system were discussed,namely,the virtual parallel mine construction,environment perception and localization,unmanned control for single equipment,collaborative work between multi-equipment,management and control for all the equipment,decision for parallel taking over,and mine network communication.The implementation and deployment of parallel autonomous mining systems will effectively improve the operational efficiency and the level of safe production of mining enterprises,and will promote the construction of green mines,which is of great significance for achieving sustainable development.

Research on architecture and system deployment of intelligent power plant based on digital twin

Haidong FAN

2019, 1(3):  241-248.  doi:10.11959/j.issn.2096-6652.201930

Asbtract ( 497 )   HTML ( 46)   PDF (4584KB) ( 1893 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Under the call of structural reform of energy supply and clean,efficient and intelligent coal-fired power production in China,based on the analysis of the research and practice status of intelligent power plant,combined with digital twin theory and methods,production and operation activities and elements of power plants were virtualized and digitized with the industrial big data platform and management cloud platform as the core,the intelligent power plant architecture were constructed including decision-making,intelligent supervision,intelligent control and intelligent equipment,which covered all aspects of production and operation of power plant equipment,so that the power plant had the characteristics of comprehensive perception,collaborative optimization,prediction and early warning and scientific decision-making.

Research and implementation of industrial Internet of things communication system based on MQTT

Fan JIA,Gang XIONG,Fenghua ZHU,Bin TIAN,Shuangshuang HAN,Shichao CHEN

2019, 1(3):  249-259.  doi:10.11959/j.issn.2096-6652.201928

Asbtract ( 341 )   HTML ( 44)   PDF (5204KB) ( 466 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The industrial Internet of things makes full use of sensors,computer networks,big data process and other technologies to solve the problem of “information island” caused by the closed operation of traditional industrial systems,enabling the rapid and convenient data exchange between systems.How to establish high quality and low bandwidth data exchange mode in industrial field and cloud is a big challenge to realize intelligent manufacturing.MQTT protocol is widely used in the Internet of things system because of its lightweight and flexible configuration.MQTT-based industrial Internet of things communication system was built to realize multi-source and heterogeneous data exchange between cloud and industrial field,remote monitoring of device status,user service subscription and other functions,so that the performance and related applications of MQTT protocol in industrial Internet of things communication system could be studied.

Research on hip joint stress distribution algorithms based on deep learning

Yuanping LIU,Yukai SONG,Xiaoyan ZHANG,Xianqiang LIU

2019, 1(3):  260-268.  doi:10.11959/j.issn.2096-6652.201934

Asbtract ( 334 )   HTML ( 16)   PDF (4440KB) ( 340 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem of the stress distribution algorithm of hip cartilage,a deep learning model to replace the finite element analysis (FEA) was proposed.This deep learning model was divided into unsupervised learning module and supervised learning module.Firstly,an unsupervised learning module was adopted to encode the shape of hip cartilage and femur.Then the coding and decoding of stress distribution implement was implemented so that stress data can be combined with the neural network.Next a supervised learning module supervised by the stress data was used,and the model uses neural networks to learn a mapping relationship from the shape code of the hip cartilage and femur to the stress code of the stress distribution.Finally,a fitted deep learning model was obtained.This deep learning model can simulate the FEA method to a certain extent.But the mean absolute error and the normalized mean absolute error are still larger than that of the FEA method,so the FEA method cannot be completely replaced by our deep learning model.Meanwhile,the limitations of the deep learning model in the use of input features were studied,and a direction to improve the performance of the model was proposed.

ACP based parallel power generation control system

Guolian HOU,Linjuan GONG,Ye SU,Yaohua TANG

2019, 1(3):  269-279.  doi:10.11959/j.issn.2096-6652.201927

Asbtract ( 239 )   HTML ( 10)   PDF (2813KB) ( 445 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The power generation side control is the foundation of stable operation of power grid.However,the existing control methods cannot meet the growing demands of energy,environment,and human society to the power generation process.Therefore,the theory of ACP based parallel power generation control system was presented for the safety,high efficiency as well as environmental friendliness of power generation process.At first,the artificial power generation control system which is equivalent to the physical power generation control system was constructed.Secondly,the optimal model of power plant and its corresponding control strategy were chosen through the computational experiments of artificial control system to guide the operation of physical control system.Meanwhile,the behaviors of physical system were assessed for the approaching of artificial system.Then,the stable operation,maximum efficiency,and minimum energy consumption were achieved with the parallel execution of artificial control system and physical control system.Finally,the parallel control of gas turbine system in combined cycle power plant was taken as an example to demonstrate the feasibility and remarkable advantages of the adopted method.

Research and validation of human-in-the-loop hybrid-augmented intelligence in Sawyer

Haijun FU,Shichao CHEN,Yilun LIN,Gang XIONG,Bin HU

2019, 1(3):  280-286.  doi:10.11959/j.issn.2096-6652.201933

Asbtract ( 675 )   HTML ( 58)   PDF (5435KB) ( 482 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Machine learning predicts the future through the patterns of past data,and has gained a lot of research and application in recent years.However,it’s far away from human in dynamic,non-complete,and unstructured information processes.Therefore human decision-making,combined with machine learning,knowledge base were introduced in this paper and a human-in-the-loop hybrid-augmented intelligence closed-loop system was built.Based on Sawyer collaborative robot,a human-machine collaboration experiment platform was built,and a grasping experiment was designed.It turns out that the Sawyer,which is introduced human intelligence,performs better in dealing with unstructured environments than that only machine learning is used.

Research on sustainable intelligent model for online catering take-out trashes

Yuanxin ZHANG,Ming ZHOU,Shenyan WANG,Zhenzhen LIANG,Wenwen DING,Xiao WANG

2019, 1(3):  287-304.  doi:10.11959/j.issn.2096-6652.201921

Asbtract ( 372 )   HTML ( 43)   PDF (1135KB) ( 529 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

While the integration of Internet and catering industry has brought great economic benefits to the society,it has also led to the explosive growth of take-out garbage.The governance of online catering takeaway is a complex system engineering that greatly relates to the multi-agencies and multi-factors at various levels,and it needs efforts of supporters from all aspects of the society to positively participate.However,relevant theoretical research on processing takeaway trash is still rarely reported,as well as the policy and regulations,and implementations of corresponding measures.The theories and techniques that exist in system ecology and sustainable system engineering were introduced,and the AHP method was adopted to propose the impact indicators of the governance body participation.By incorporat ing the blockchain technology,the parallel traceability governance system based on the ACP theory and knowledge automation for online catering takeaway garbage could provide a platform of decentralized green credit.This green credit system can arouse the initiative of relevant participating bodies for effective coordination,and can also solve the problem of no experience and making decisions difficultly.

Developing trend and key technical analysis of intelligent acupuncture robot

Tiancheng XU,Xuejun WANG,Dongdong LU,Mengye LU,Qi LIN,Xiaoqiang ZHANG,Yi CHENG

2019, 1(3):  305-310.  doi:10.11959/j.issn.2096-6652.201918

Asbtract ( 1231 )   HTML ( 188)   PDF (1138KB) ( 889 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Acupuncture therapy has been adopted in more than 183 countries and regions around the world.With the rapid development of robot technology,research and development of intelligent acupuncture robot become possible,based on its core technology related research,that the point of automatic positioning and intelligent distribution point is the key technology and difficulty in research and development of intelligent acupuncture robot was pointed out in this paper,and thus,the concept of communion robot potential application value to the development of medical robot was also discussed.The latest research results of intelligent acupoint matching were also provided.

Parallel cities:framework,methodology,and application

Yisheng LYU,Fei-Yue WANG,Yu ZHANG,Xiaodong ZHANG

2019, 1(3):  311-317.  doi:10.11959/j.issn.2096-6652.201932

Asbtract ( 475 )   HTML ( 35)   PDF (25137KB) ( 433 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The concept,basic framework,methodology and applications of parallel city were presented in this paper.The parallel city is an application of ACP-based parallel intelligence in city fields.The real city is running with its equivalent,and the artificial city is in virtual space,in a parallel and interactive way.The artificial city has the descriptive,predictive,and prescriptive functions on the real city.There is a closed-loop workflow between the real city and the artificial city,which iteratively optimizes the urban systems,leading to a new paradigm of intelligent urban management.