Optimal carbon storage reservoir management through deep reinforcement learning
مدیریت بهینه ذخیره مخزن کربن از طریق یادگیری تقویتی عمیق-2020
Model-based optimization plays a central role in energy system design and management. The complexity and high-dimensionality of many process-level models, especially those used for geosystem energy exploration and utilization, often lead to formidable computational costs when the dimension of decision space is also large. This work adopts elements of recently advanced deep learning techniques to solve a sequential decisionmaking problem in applied geosystem management. Specifically, a deep reinforcement learning framework was formed for optimal multiperiod planning, in which a deep Q-learning network (DQN) agent was trained to maximize rewards by learning from high-dimensional inputs and from exploitation of its past experiences. To expedite computation, deep multitask learning was used to approximate high-dimensional, multistate transition functions. Both DQN and deep multitask learning are pattern based. As a demonstration, the framework was applied to optimal carbon sequestration reservoir planning using two different types of management strategies: monitoring only and brine extraction. Both strategies are designed to mitigate potential risks due to pressure buildup. Results show that the DQN agent can identify the optimal policies to maximize the reward for given risk and cost constraints. Experiments also show that knowledge the agent gained from interacting with one environment is largely preserved when deploying the same agent in other similar environments.
Keywords: Reinforcement learning | Multistage decision-making | Deep autoregressive model | Deep Q network | Surrogate modeling | Markov decision process | Geological carbon sequestration
Industrial smart and micro grid systems e A systematic mapping study
سیستم های هوشمند و ریز شبکه صنعتی و یک مطالعه نقشه برداری منظم-2020
Energy efficiency and management is a fundamental aspect of industrial performance. Current research presents smart and micro grid systems as a next step for industrial facilities to operate and control their energy use. To gain a better understanding of these systems, a systematic mapping study was conducted to assess research trends, knowledge gaps and provide a comprehensive evaluation of the topic. Using carefully formulated research questions the primary advantages and barriers to implementation of these systems, where the majority of research is being conducted with analysis as to why and the relative maturity of this topic are all thoroughly evaluated and discussed. The literature shows that this topic is at an early stage but already the benefits are outweighing the barriers. Further incorporation of renewables and storage, securing a reliable energy supply and financial gains are presented as some of the major factors driving the implementation and success of this topic.
Keywords: Industrial smart grid | Industrial micro grid | Systematic mapping study | Strategic energy management | Industrial facility optimization | Renewable energy resources
Knowledge Diffusion and economic Growth based on Fourier’s law
انتشار دانش و رشد اقتصادی براساس قانون فوریه-2020
Learning is the basic thing for a person’s growth, whenever in school or on the work. Also the economic growth of a country depends its technology and science. The knowledge diffusion in a firm dynamic system is important. Some former models have been given by Fernando E. Alvarez, Francisco J. Buera and Robert E. Lucas, Jr’s paper: “Models of Idea Flows” (Alvarez et al., 2008). Our model based on the earlier work but extend the definition of spread direction based on Fourier’s law, in which case can also explain the asymptotic equilibrium state. Solving the partial differential equation helps us to learn the solution well. A simulation is given using finite difference method to sketch the curve moving, also comparing with the realistic economic curves and they are fit. It can well explain the economic stable in the closed system of a single country and a “huge” change under some special outside “source” power.
Keywords: Knowledge diffusion | Economic growth | Fourier’s law | Finite difference method | Partial differential equation
Differential shedding: A study of the fiber transfer mechanisms of blended cotton and polyester textiles
ریختن دیفرانسیل: مطالعه مکانیسم های انتقال فیبر پارچه های مخلوط پنبه و پلی استر-2020
One of the primary interests of forensic sciences is the study of traces, better conceived as silent witnesses to criminal activity whose existence is attributable to Locard’s principle. Thus, textile fibers are commonly exploited as they are easily transferred during contact which can vary in intensity depending upon the type of activity that occurred. Regardless, current knowledge pertaining to fiber transfer mechanisms, particularly in regards to blended textiles, is limited. It is recognized that the intensity of the contact, the type of textile as well as the size and type of fibers composing it have a significant influence on the amount of fibers transferred. However, when the donor textile is blended (eg. 50% cotton, 50% polyester), it often happens that one of the two types of fibers is transferred in greater proportion to the receiving surface (eg. 80% cotton and 20% polyester). The percentages indicated on the manufactured label are however not representative of the respective proportions (based on the number of fibers) of each type of fiber composing the fabric, but rather the weight of each respective type of fiber used to fabricate the garment. Therefore, the amount of collected fibers (traces) cannot be easily correlated to the proportions indicated on the manufactured label used to describe the textile. The objective of this study was to test the transfer capacities of blended textiles of different cotton and polyester proportions by performing several simulations under controlled conditions (i.e. contact between two textiles with a constant force and speed). The results were then correlated to the fiber type, morphology, and size. Overall, the project contributes to improving the comprehension of fiber transfer mechanisms, and provides insight on the quantity and the proportions of fibers capable of being transferred between the donor and the recipient textiles following a specific type of action and contact (legitimate or otherwise).
Keywords: Blended textiles | Textile characteristics | Shedding capacity | Primary transfer simulation | Fiber proportions
چارچوب حاکمیتی هوش تجاری در دانشگاه: مطالعه موردی دانشگاه دو لا کاستا
سال انتشار: 2020 - تعداد صفحات فایل pdf انگلیسی: 8 - تعداد صفحات فایل doc فارسی: 25
دانشگاه ها و شرکت ها دارای فرآیندهای تصمیم گیری هستند که به آنها اجازه می دهد تا به اهداف سازمانی دست پیدا کنند. در حال حاضر، تحلیل داده ها نقش مهمی در ایجاد دانش، بدست آوردن الگوهای مهم و پیش بینی استراتژی ها ایفا می کنند.این مقاله طراحی چارچوب نظارت هوش تجاری را برای دانشگاه دو لا کاستا ارائه کرده است که به آسانی برای سازمان های دیگر هم قابل استفاده است. برای این منظور، تشخیص انجام شده به منظور شناسایی میزان بلوغ تحلیلی انجام شده است. با استفاده از این چشم انداز، مدلی برای تقویت فرهنگ سازمانی ، زیر ساختارها، مدیریت داده، تحلیل داده و نظارت ارائه شده است.این مدل در بر گیرنده تعریف چارچوب نظارتی، اصول هدایت کننده، استراتژی ها، نهادهای تصمیم گیرنده و نقش ها می باشد. بنابراین، این چارچوب برای استفاده از کنترل های موثر جهت اطمینان از موفقیت پروژه های هوش تجاری و دست یابی به اهداف برنامه توسعه همراه با چسم انداز تحلیلی سازمان ارائه شده است.
کلمات کلیدی: هوش تجاری | نظارت | دانشگاه | تحلیل | تصمیم گیری
|مقاله ترجمه شده|
Rule-interposing deep reinforcement learning based energy management strategy for power-split hybrid electric vehicle
استراتژی مدیریت انرژی مبتنی بر یادگیری تقویتی عمیق قانون برای خودروی الکتریکی هیبریدی تقسیم برق-2020
The optimization and training processes of deep reinforcement learning (DRL) based energy management strategy (EMS) can be very slow and resource-intensive. In this paper, an improved energy management framework that embeds expert knowledge into deep deterministic policy gradient (DDPG) is proposed. Incorporated with the battery characteristics and the optimal brake specific fuel consumption (BSFC) curve of hybrid electric vehicles (HEVs), we are committed to solving the optimization problem of multi-objective energy management with a large space of control variables. By incorporating this prior knowledge, the proposed framework not only accelerates the learning process, but also gets a better fuel economy, thus making the energy management system relatively stable. The experimental results show that the proposed EMS outperforms the one without prior knowledge and the other state-of-art deep reinforcement learning approaches. In addition, the proposed approach can be easily generalized to other types of HEV EMSs.
Keywords: Energy management strategy | Hybrid electric vehicle | Expert knowledge | Deep deterministic policy gradient | Continuous action space
Establishment and application of intelligent city building information model based on BP neural network model
ایجاد و کاربرد مدل اطلاعات هوشمند شهرسازی براساس مدل شبکه عصبی BP-2020
The construction of smart cities in our country has received extensive attention. Under the situation that smart cities are vigorously promoted nowadays, compared with traditional construction and operation and maintenance methods, building information model (BIM) technology is more suitable to serve as an important foundation for intelligent management in the whole process of construction projects. BIM is an abbreviation for building information model. BIM relies on a variety of digital technologies, which can be used to realize information modeling of urban buildings and infrastructure. The efficiency of information exchange in the process of intelligence construction ensures the integrity and accuracy of information data exchange and maintains the consistency of information data exchange. Data and information have objectivity, applicability, transferability, and sharing. Geographic data is a digital representation of various geographical features and phenomena and their relationships. BIM is a digital representation of physical and functional characteristics of a facility. It can It is used as a shared knowledge resource for facility information. It becomes a reliable basis for facility life-cycle decision-making. Input BP neural network, and then learn and train by BP neural network.
Keywords: BP neural network | Smart city | Building information model
Drivers, barriers and social considerations for AI adoption in business and management: A tertiary study
رانندگان ، موانع و ملاحظات اجتماعی برای پذیرش هوش مصنوعی در مشاغل و مدیریت: یک مطالعه عالی-2020
The number of academic papers in the area of Artificial Intelligence (AI) and its applications across business and management domains has risen significantly in the last decade, and that rise has been followed by an increase in the number of systematic literature reviews. The aim of this study is to provide an overview of existing systematic reviews in this growing area of research and to synthesise their findings related to enablers, barriers and social implications of the AI adoption in business and management. The methodology used for this tertiary study is based on Kitchenham and Charter’s guidelines , resulting in a selection of 30 reviews published between 2005 and 2019 which are reporting results of 2,021 primary studies. These reviews cover the AI adoption across various business sectors (healthcare, information technology, energy, agriculture, apparel industry, engineering, smart cities, tourism and transport), management and business functions (HR, customer services, supply chain, health and safety, project management, decisionsupport, systems management and technology acceptance). While the drivers for the AI adoption in these areas are mainly economic, the barriers are related to the technical aspects (e.g. availability of data, reusability of models) as well as the social considerations such as, increased dependence on non-humans, job security, lack of knowledge, safety, trust and lack of multiple stakeholders’ perspectives. Very few reviews outside of the healthcare management domain consider human, organisational and wider societal factors and implications of the AI adoption. Most of the selected reviews are recommending an increased focus on social aspects of AI, in addition to more rigorous evaluation, use of hybrid approaches (AI and non-AI) and multidisciplinary approaches to AI design and evaluation. Furthermore, this study found that there is a lack of systematic reviews in some of the AI early adopter sectors such as financial industry and retail and that the existing systematic reviews are not focusing enough on human, organisational or societal implications of the AI adoption in their research objectives.
Keywords: artificial intelligence | business | machine learning | management | systematic literature review | tertiary study
Qualitative and quantitative project risk assessment using a hybrid PMBOK model developed under uncertainty conditions
ارزیابی ریسک کمی و کیفی پروژه با استفاده از یک مدل توسعه یافته PMBOK تحت شرایط غیر قطعی-2020
This study presented a qualitative and quantitative project risk assessment using a hybrid PMBOK model developed under uncertainty conditions. Accordingly, an exploratory and applied research design was employed in this study. The research sample included 15 experienced staff working in main and related positions in Neyr Perse Company. After reviewing the literature and the Project Management Body of Knowledge (PMBOK), 32 risk factors were identified and their number reduced to 17 risks using the expert opinions via the fuzzy Delphi technique run through three stages. The results of the confirmatory factor analysis showed that all risks were confirmed by the members of the research sample. Then the identified risks were structured and ranked using fuzzy DEMATEL and fuzzy ANP techniques. The final results of the study showed that the political and economic sanctions had the highest weight followed by foreign investors’ attraction and the lack of regional infrastructure.
Keywords: Project risks | Project management body of knowledge (PMBOK) | Uncertainty | Mixed qualitative and quantitative risk assessment approach | Mathematics | Probability theory | Engineering | Industrial engineering | Business
Uncertainty in information system development: Causes, effects, and coping mechanisms
عدم اطمینان در توسعه سیستم اطلاعات: علل ، اثرات و مکانیسم های مقابله-2020
Information system development (ISD) projects are an ever-growing field of project management (PM) with their unique features, and project failures in ISD are relatively common. In the broader context of PM, uncertainty is a studied, yet mercurial phenomenon. By contrast, uncertainty in ISD projects has received relatively little attention from scholars, and PM literature has not systematically focused on uncertainty in ISD from a viewpoint other than that of project managers. In order to understand uncertainties in ISD projects, we need to first understand the causes behind them, their effects on everyday ISD work, and share coping mechanisms utilized among industry professionals. In the context of ISD projects, we set out to explore what causes uncertainty, what are the effects of uncertainty, and how software industry professionals cope with uncertainty. We conducted eleven semi-structured interviews with a diverse range of ISD professionals, and analyzed the interviews using conventional content analysis. Our results extend and complement current knowledge on the causes, effects, and coping mechanisms of uncertainty, especially in the context of ISD. Additionally, we present practical considerations on how to implement our findings into ISD industry and education.
Keywords: Uncertainty | Risk | Information system development | Cause | Effect | Coping mechanism