A novel control approach based on hybrid Fuzzy Logic and Seeker Optimization for optimal energy management between micro-sources and supercapacitor in an islanded Microgrid
یک روش کنترل جدید مبتنی بر منطق فازی ترکیبی و بهینه سازی جستجوگر برای مدیریت بهینه انرژی بین منابع کوچک و ابر رسانا در یک میکروگرید جزیره ای-2020
This work presents a novel control technique for proportional power sharing among parallel VSCs connected to an islanded Microgrid in a distributed generation system consisting of Photovoltaic (PV) and Solid Oxide Fuel Cell (SOFC) as two micro-sources. For tracking the maximum solar energy, a Seeker Optimized Fuzzy based Dynamic PI (FSOA-DPI) controller is implemented for the Modified Perturb and Observe MPPT method. Again, for the optimum cost management of the Microgrid system, DPI controller based decentralized Virtual Impedance Drooping (VID) technique is implemented for suitable load sharing between the two hybrid micro-sources. An Energy Storage System (ESS) regulated by FSOA-DPI controller is also proposed for this Microgrid system to ensure the better transient and sub-transient stability during fault occurrence. The dynamic response and stability of the system with proposed method is compared and contrasted with conventional PI controller based method during load sharing for ensuring the robust control under conditions of nonlinear load and faults. The harmonic analysis has been carried out by Fast Fourier Transform (FFT) and the values indicate that the Total Harmonic Distortion (THD) is well within the prescribed IEEE standard limits. Validation and justification of the improvements achieved by the proposed controller are realized using Matlab/Simulink environment.
Keywords: Microgrid | Distributed generation (DG) | Hybrid micro-source | Photovoltaic (PV) | Solid Oxide Fuel Cell (SOFC) | Virtual Impedance Drooping | Seeker Optimization Approach (SOA)
Comfort evaluation of seasonally and daily used residential load insmart buildings for hottest areas via predictive mean vote method
ارزیابی راحتی ساختمانهای بار مسکونی فصلی و روزانه برای گرمترین مناطق با استفاده از روش پیش بینی میانگین رای گیری-2020
tIn this paper, two energy management controllers: Binary Particle Swarm Optimization Fuzzy Mam-dani (BPSOFMAM) and BPSOF Sugeno (BPSOFSUG) are proposed and implemented. Daily and seasonallyused appliances are considered for the analysis of the efficient energy management through these con-trollers. Energy management is performed using the two Demand Side Management (DSM) strategies:load scheduling and load curtailment. In addition, these DSM strategies are evaluated using the meta-heuristic and artificially intelligent algorithms as BPSO and fuzzy logic. BPSO is used for scheduling of thedaily used appliances, whereas fuzzy logic is applied for load curtailment of seasonally used appliances,i.e., Heating, Ventilation and Air Conditioning (HVAC) systems. Two fuzzy inference systems are appliedin this work: fuzzy Mamdani and fuzzy Sugeno. This work is proposed for the energy management of thehottest areas of the world. The input parameters are: indoor temperature, outdoor temperature, occu-pancy, price, decision control variables, priority and length of operation times of the appliances, whereasthe output parameters are: energy consumption, cost and thermal and appliance usage comfort. More-over, the comfort level of the consumers regarding the usage of the appliances is computed using Fanger’spredictive mean vote method. The comfort is further investigated by incorporating the renewable energysources, i.e., photovoltaic systems. Simulation results show the effectiveness of the proposed controllersas compared to the unscheduled case. BPSOFSUG outperforms to the BPSOFMAM in terms of energyconsumption and cost of the proposed scenario.
Keywords:Energy management | Thermal comfort | Appliance usage comfort | Fuzzy logic | Fuzzy inference systems
Application of a fuzzy-logic based model for risk assessment in additive manufacturing r&d projects
استفاده از یک مدل مبتنی بر منطق فازی برای ارزیابی ریسک در پروژه های تحقیق و توسعه افزودنی-2020
Experts from industry and academics have highlighted Additive Manufacturing (AM) as a technology that is revolutionizing manufacturing. AM is a process that consists of creating a three-dimensional object by incorporating layers of a material such as metal or polymer. This research studies risks associated with AM R&D Project Management. A significant set of risks with a potential negative impact on project objectives in terms of scope, schedule, cost and quality are identified through an extensive literature review. These risks are assessed through a survey answered by ninety academics and professionals with noteworthy sector expertise. This process is made by the measurement of two parameters: likelihood of occurrence and impact on project objectives. According to the responses of the experts, the level of relevance of each risk is calculated, innovatively, through a fuzzy logic-based model, specifically developed for this study, implemented in MATLAB Fuzzy Logic Toolbox. The results of this study show that the risks “Defects occurring during the manufacturing process”, “Defective design”, “Poor communication in the project team” and “Insufficient financing” are determined as the most critical in AM R&D Project Management. The proposed model is presented as a powerful new tool for organizations and academics, to prioritize the risks that are more critical to develop appropriate response strategies to achieve the success of their projects.
Keywords: Additive Manufacturing | 3D printing | Risk Assessment | Project Management | Fuzzy Logic
A Type-2 Fuzzy Logic Approach to Explainable AI for regulatory compliance, fair customer outcomes and market stability in the Global Financial Sector
رویکرد منطق فازی نوع 2 به هوش مصنوعی قابل توضیح برای انطباق با مقررات ، نتایج عادلانه مشتری و ثبات بازار در بخش مالی جهانی-2020
The field of Artificial Intelligence (AI) is enjoying unprecedented success and is dramatically transforming the landscape of the financial services industry. However, there is a strong need to develop an accountability and explainability framework for AI in financial services, based on a risk-based assessment of appropriate explainability levels and techniques by use case and domain. This paper proposes a risk management framework for the implementation of AI in banking with consideration of explainability and outlines the implementation requirements to enable AI to achieve positive outcomes for financial institutions and the customers, markets and societies they serve. The work presents the evaluation of three algorithmic approaches (Neural Networks, Logistic Regression and Type 2 Fuzzy Logic with evolutionary optimisation) for nine banking use cases. We review the emerging regulatory and industry guidance on ethical and safe adoption of AI from key markets worldwide and compare leading AI explainability techniques. We will show that the Type-2 Fuzzy Logic models deliver very good performance which is comparable to or lagging marginally behind the Neural Network models in terms of accuracy, but outperform all models for explainability, thus they are recommended as a suitable machine learning approach for use cases in financial services from an explainability perspective. This research is important for several reasons: (i) there is limited knowledge and understanding of the potential for Type-2 Fuzzy Logic as a highly adaptable, high performing, explainable AI technique; (ii) there is limited cross discipline understanding between financial services and AI expertise and this work aims to bridge that gap; (iii) regulatory thinking is evolving with limited guidance worldwide and this work aims to support that thinking; (iv) it is important that banks retain customer trust and maintain market stability as adoption of AI increases.
Keywords: Regulatory Compliance | Accountability and Explainability | Type-2 Fuzzy Logic | Neural Networks
Hybrid Deep Learning Type-2 Fuzzy Logic Systems For Explainable AI
سیستم های منطق فازی نوع 2 یادگیری عمیق ترکیبی برای هوش مصنوعی قابل توضیح-2020
The recent years have witnessed a rapid rise in the use of Artificial Intelligence (AI) systems, in particular Machine Learning (ML) models. The vast majority of AI systems employ black box models that lack transparency in operation and decision making. This lack of transparency curtails the use of these AI systems in regulated applications (such as medical, financial applications, etc.) where it is important to understand the reasoning behind the predictions of the AI system. In these situations, interpretable models need to be used. However, interpretable models can turn into black-box models for high dimensional inputs. There are a variety of approaches that have been proposed to solve this problem. In this paper, we present a novel hybrid deep learning type-2 fuzzy logic system for explainable AI which addresses these challenges to provide a highly interpretable model that has reasonable performance when compared to the other black box models.
Keywords: Explainable Artificial Intelligence | Interval Type-2 Fuzzy Logic System | Deep Learning
Prediction of greenhouse gas emissions from Ontario’s solid waste landfills using fuzzy logic based model
پیش بینی انتشار گازهای گلخانه ای از محل های دفع زباله جامد انتاریو با استفاده از مدل مبتنی بر منطق فازی-2020
In this study, multi-criteria assessment technique is used to predict the methane generation from large municipal solid waste landfills in Ontario, Canada. Although a number of properties determine the gas generation from landfills, these parameters are linked with empirical relationships making it difficult to generate precise information concerning gas production. Moreover, available landfill data involve sources of uncertainty and are mostly insufficient. To fully characterize the chemistry of reaction and predict gas generation volumes from landfills, a fuzzy-based model is proposed having seven input parameters. Parameters were identified in a linguistic form and linked by 19 IF-THEN statements. When compared to measured values, results of the fuzzy based model showed good prediction of landfill gas generation rates. Also, when compared to other first order decay and second order decay models like LandGEM, the fuzzy based model showed better results. When plotting the LandGEM and Fuzzy model values to the actual measured data, the fuzzy model resulted in a better fit to actual data than the LandGEM model with a coefficient of determination R2 of 0.951 for fuzzy model versus 0.804 for LandGEM model. The results show how multi-criteria assessment technique can be used in modelling of complicated processes that take place within the landfills and somehow accurately predicting the landfill gas generation rate under different operating conditions
Keywords: Municipal solid waste | Landfill gas | Life-cycle assessment | Waste to energy | Greenhouse gas emissions | Fuzzy model
Fuzzy logic interpretation of quadratic networks
تفسیر منطق فازی از شبکه های درجه دوم-2020
Over past several years, deep learning has achieved huge successes in various applications. However, such a data-driven approach is often criticized for lack of interpretability. Recently, we proposed arti- ficial quadratic neural networks consisting of quadratic neurons in potentially many layers. In cellular level, a quadratic function is used to replace the inner product in a traditional neuron, and then under- goes a nonlinear activation. With a single quadratic neuron, any fuzzy logic operation, such as XOR, can be implemented. In this sense, any deep network constructed with quadratic neurons can be interpreted as a deep fuzzy logic system. Since traditional neural networks and quadratic counterparts can represent each other and fuzzy logic operations are naturally implemented in quadratic neural networks, it is plau- sible to explain how a deep neural network works with a quadratic network as the system model. In this paper, we generalize and categorize fuzzy logic operations implementable with individual quadratic neu- rons, and then perform statistical/information-theoretic analyses of exemplary quadratic neural networks.
Keywords: Machine learning | Artificial neural network (ANN) | Quadratic network | Fuzzy logic
Simplifie d optimized control using reinforcement learning algorithm for a class of stochastic nonlinear systems
کنترل بهینه شده ساده با استفاده از الگوریتم یادگیری تقویت کننده برای دسته ای از سیستم های غیرخطی تصادفی-2020
In this work, a reinforcement learning (RL) based optimized control approach is developed by implementing tracking control for a class of stochastic nonlinear systems with unknown dynamic. The RL is constructed in identifier-actor-critic architecture, where the identifier aims for determining the stochastic system in mean square, the actor aims for executing the control action and the critic aims for evaluating the control performance. In almost all of the published RL-based optimal control, since both actor and critic updating laws are yielded on the basis of implementing gradient descent method to the square of Bellman residual error, these methods are very complex and are performed difficultly. By contrast, the proposed optimized control is obviously simple because the RL algorithm is derived based on the negative gradient of a simple positive function. Furthermore, the proposed approach can remove the assumption of persistence excitation, which is required for most RL based adaptive optimal control. Finally, based on the adaptive identifier, the system stability is proven by using the quadratic Lyapunov function rather than quartic Lyapunov function, which is usually required for most stochastic systems. Simulation further demon- strates that the optimized stochastic approach can achieve the desired control objective
Keywords: Optimal control | Tracking control | Adaptive identifier | Fuzzy logic systems
Motion control of a space manipulator using fuzzy sliding mode control with reinforcement learning
کنترل حرکت یک مکانیزم فضا با استفاده از کنترل حالت کشویی فازی با یادگیری تقویتی-2020
The free-flying space manipulators present challenges in controlling the motions of both the spacecraft bus and the manipulator, because of the highly-coupling system dynamics and the unknown space environment disturbances. Although the sliding mode controllers are robust to the unknown disturbances and system uncertainties, the chattering effect could affect the pointing accuracy and the lifetime of the actuators. This paper first introduces the dynamics of a CuBot, which is a 3-rigid-link manipulator based on the CubeSat platform. To maintain the robustness while decreasing the chattering effect, an innovative reinforcement learning based fuzzy adaptive sliding mode controller is proposed. To maintain the robustness while reducing the chattering effect, an innovative reinforcement learning based fuzzy adaptive sliding mode controller is proposed. The switching gain is updated to estimate the lumped upper bound of the system uncertainties and the unknown disturbances, and then a new fuzzy logic adaptive law is applied on the switching gain to decrease the chattering effects. On top of that, the fuzzy logic rules are tuned by an innovative modified reinforcement learning mechanism to achieve the better tracking performance. The uniformly ultimately bounded tracking errors are guaranteed by the proposed control scheme, and the effectiveness is validated by the simulation results.
Keywords: CubeSat | Fuzzy logic inference | Reinforcement learning | Sliding mode control | Space manipulator
Variable structure battery-based fuel cell hybrid power system and its incremental fuzzy logic energy management strategy
سیستم قدرت هیبریدی سلول سوختی مبتنی بر باتری ساختار متغیر و استراتژی مدیریت انرژی منطق فازی افزایشی آن-2020
A hybrid power system consists of a fuel cell and an energy storage device like a battery and/or a supercapacitor possessing high energy and power density that beneficially drives electric vehicle motor. The structures of the fuel cell-based power system are complicated and costly, and in energy management strategies (EMSs), the fuel cell’s characteristics are usually neglected. In this study, a variable structure battery (VSB) scheme is proposed to enhance the hybrid power system, and an incremental fuzzy logic method is developed by considering the efficiency and power change rate of fuel cell to balance the power system load. The principle of VSB is firstly introduced and validated by discharge and charge experiments. Subsequently, parameters matching of the fuel cell hybrid power system according to the proposed VSB are designed and modeled. To protect the fuel cell as well as ensure the efficiency, a fuzzy logic EMS is formulated via setting the fuel cell operating in a high efficiency and generating an incremental power output within the affordable power slope. The comparison between a traditional deterministic rules-based EMS and the designed fuzzy logic was implemented by numerical simulation in three different operation conditions: NEDC, UDDS, and user-defined driving cycle. The results indicated that the incremental fuzzy logic EMS smoothed the fuel cell power and kept the high efficiency. The proposed VSB and incremental fuzzy logic EMS may have a potential application in fuel cell vehicles.
Keywords: Fuel cell vehicles | Hybrid fuel cell/battery power | system | Variable structure battery (VSB) | Incremental fuzzy logic energy | management | Maintain efficiency and lifespan