Fuzzy Online Research Articles

Temperature-Controlled Laser Cutting of an Electrical Steel Sheet Using a Novel Fuzzy Logic Controller

A novel PID-type fuzzy logic controller (FLC) with an online fuzzy tuner was created to maintain stable in situ control of the cutting front temperature, aiming to enhance the laser process for thin non-oriented electrical steel sheets. In the developed controller, the output scaling factors and the universe of discourse were initially optimized using a hybrid of the particle swarm optimization and grey wolf optimization methods. The optimal parameters obtained were utilized in experiments involving the laser cutting of thin non-oriented electrical steel sheets, compared to an open-loop control system maintaining a constant cutting speed. The PID-type FLC with an online fuzzy tuner demonstrated a superior cutting quality, generating a smaller roundness and a reduced heat-affected zone (HAZ) through the in situ tuning of control parameters. Particularly, the HAZ width was significantly smaller than that reported in a previous study which used fuzzy gain scheduling for temperature control. Moreover, the cutting time was diminished by optimally adjusting the cutting speed using PID-type FLC with an online fuzzy tuner. Therefore, the accumulated heat in the steel sheet, particularly under high laser pulse frequencies, was effectively reduced, making it suitable for industrial applications.

Mountain-Expressway Slope Safety Based on the Online Monitoring System and Fuzzy Comprehensive Evaluation

Abstract Mountainous highway slopes are characterized by their point-like distribution, large number, relatively small scale, and susceptibility to human activities and environmental changes. Overall monitoring and assessment of slopes are necessary to detect hazards in a timely manner and prepare disaster prevention measures in advance. There is a lack of integration and utilization of monitoring data, and the slope safety evaluation system is not mature. In response to these problems, this study uses real-time monitoring data of highway slopes as the research object. Real-time monitoring data of multisource monitoring indicators are used to evaluate and provide early warning on the degree of safety of the highway slopes. The main research includes the following: (1) Construction of an online monitoring system for highway slopes. This study analyzes the sensitivity of the slope’s influencing factors and the deformation characteristics of slopes along mountainous highway slopes. The application principles of monitoring indicators, points, and monitoring networks are created. (2) Highway slope stability evaluation hierarchical models are generated from monitoring the index layer to the judgment criterion layer based on multisource monitoring indexes. According to the analytic hierarchy process–fuzzy comprehensive evaluation methods, the real-time stability level of the slopes is determined on the basis of the stability assessment data set. (3) A real-time evaluation model was applied to the stability evaluation of slopes. The established model is suitable for stability evaluation and security classification of highway slopes in mountain areas. From the evaluation results, heavy rainfall is the main reason for the safety level reduction of slopes in mountain areas. According to monitoring items, the system can evaluate the safety level of slopes and monitor the subsidence of mountain highway subgrades and geological disasters, such as landslides and collapses, along mountain highways in real time.

Online one pass clustering of data streams based on growing neural gas and fuzzy inference systems

AbstractThe clustering of big data streams has become a challenging task due to time and space constraints of the hardware and decreasing accuracy when the dimensionality of input data grows in time. In this paper, fuzzy growing neural gas is introduced, an online fuzzy approach for clustering data streams based on the growing neural gas algorithm, by adopting more restrictive criteria for selecting the winner nodes in the topological graph constructed at each iteration of the algorithm. The algorithm is tested on public datasets, and the results show improvements over existing clustering methods.

Optimized fuzzy rule-based energy management for a battery-less PV/wind-BWRO desalination system

Coupling water desalination processes with Renewable Energy Sources (RESs) can be a sustainable and ecological approach to the global water/energy supply crisis. In this regard, small-scale standalone battery-less Brackish Water Reverse Osmosis (BWRO) desalination system powered by a hybrid PV/Wind RES is expected to meet freshwater demand of a small isolated community. One particularity of the proposed architecture deals with the absence of electrochemical storage; only taking benefit of hydraulic storage in water tanks when RE is available. This study puts forward the prime importance of Water/Power flows management optimization. For this purpose, an online Fuzzy Logic-based Energy Management Strategy (FLEMS) is proposed. Firstly, a Hand-Made Fuzzy Inference System (HMFIS) was designed to identify the instantaneous power sharing between the system hydro-mechanical processes (well pumping, water storage and desalination processes). Secondly, an offline genetic algorithm optimization was applied on the HMFIS design in order to optimize the power sharing factor and maximize freshwater production. Then, when applying unknown power profile, the optimized FLEMS demonstrated its performance to improve the system energy efficiency and enhance the brackish water (from 16.7% in autumn to 63% in summer) and freshwater production (to 3.3% during autumn for instance) compared with the HMFIS-based EMS.

Experimental investigation on the online fuzzy energy management of hybrid fuel cell/battery power system for UAVs

The hybrid powerplant combining a fuel cell and a battery has become one of the most promising alternative power systems for electric unmanned aerial vehicles (UAVs). To enhance the fuel efficiency and battery service life, highly effective and robust online energy management strategies are needed in real applications.In this work, an energy management system is designed to control the hybrid fuel cell and battery power system for electric UAVs. To reduce the weight, only one programmable direct-current to direct-current (dcdc) converter is used as the critical power split component to implement the power management strategy. The output voltage and current of the dcdc is controlled by an independent energy management controller. An executable process of online fuzzy energy management strategy is proposed and established. According to the demand power and battery state of charge, the online fuzzy energy management strategy produces the current command for the dcdc to directly control the output current of the fuel cell and to indirectly control the charge/discharge current of the battery based on the power balance principle.Another two online strategies, the passive control strategy and the state machine strategy, are also employed to compare with the proposed online fuzzy strategy in terms of the battery management and fuel efficiency. To evaluate and compare the feasibility of the online energy management strategies in application, experiments with three types of missions are carried out using the hybrid power system test-bench, which consists of a commercial fuel cell EOS600, a Lipo battery, a programmable dcdc converter, an energy management controller, and an electric load. The experimental investigation shows that the proposed online fuzzy strategy prefers to use the most power from the battery and consumes the least amount of hydrogen fuel compared with the other two online energy management strategies.

Antlion Algorithm Optimized Fuzzy PID Supervised On-line Recurrent Fuzzy Neural Network Based Controller for Brushless DC Motor

In this paper, Antlion algorithm optimized Fuzzy PID supervised on-line Recurrent Fuzzy Neural Network based controller is proposed for the speed control of Brushless DC motor. Learning parameters of the supervised on-line recurrent fuzzy neural network controller, i.e., learning rate (η), dynamic factor (α), and number nodes (Ni) are optimized using Genetic algorithm, Particle Swarm optimization, Ant colony optimization, Bat algorithm, and Antlion algorithm. The proposed controller is tested with different operating conditions of the Brushless DC motor, such as varying load conditions and varying set speed conditions. The time domain specifications such as rise time, overshoot, undershoot, settling time, recovery time, and steady state error and also integral performance indices such as root mean square error, integral of absolute error, integral of squared error, and integral of time multiplied absolute error are measured and compared for above optimized controller. Simulation results show Antlion algorithm optimized Fuzzy PID supervised on-line recurrent fuzzy neural network based controller has proved to be superior than other considered controllers in all aspects. In addition, the experimental verification of proposed control system is presented to test the effectiveness of the proposed controller with different operating conditions of the Brushless DC motor.

Evolving Fuzzy Model (eFuMo) Method for On-line Fuzzy Model Learning with Application to Monitoring System

Evolving Fuzzy Model (eFuMo) Method for On-line Fuzzy Model Learning with Application to Monitoring System

Change points detection in crime-related time series: An on-line fuzzy approach based on a shape space representation

The extension of traditional data mining methods to time series has been effectively applied to a wide range of domains such as finance, econometrics, biology, security, and medicine. Many existing mining methods deal with the task of change points detection, but very few provide a flexible approach. Querying specific change points with linguistic variables is particularly useful in crime analysis, where intuitive, understandable, and appropriate detection of changes can significantly improve the allocation of resources for timely and concise operations. In this paper, we propose an on-line method for detecting and querying change points in crime-related time series with the use of a meaningful representation and a fuzzy inference system. Change points detection is based on a shape space representation, and linguistic terms describing geometric properties of the change points are used to express queries, offering the advantage of intuitiveness and flexibility. An empirical evaluation is first conducted on a crime data set to confirm the validity of the proposed method and then on a financial data set to test its general applicability. A comparison to a similar change-point detection algorithm and a sensitivity analysis are also conducted. Results show that the method is able to accurately detect change points at very low computational costs. More broadly, the detection of specific change points within time series of virtually any domain is made more intuitive and more understandable, even for experts not related to data mining.

A new intelligent online fuzzy tuning approach for multi-area load frequency control: Self Adaptive Modified Bat Algorithm

The primary aim of the Automatic Generation Control (AGC) is to maintain system frequency and tie-line interchanges in a predestine limits by regulating the power generation of electrical generators, in case of fluctuations in the system frequency and tie-line loadings. This paper proposes a new online intelligent strategy to realize the control of multi-area load frequency systems. The proposed intelligent strategy is based on a combination of a novel heuristic algorithm named Self-Adaptive Modified Bat Algorithm (SAMBA) and the Fuzzy Logic (FL) which is used to optimally tune parameters of Proportional–Integral (PI) controllers which are the most popular methods in this context. The proposed controller guaranties stability and robustness against uncertainties caused by external disturbances and impermanent dynamics that power systems face. To achieve an optimal performance, the SAMBA simultaneously optimizes the parameters of the proposed controller as well as the input and output membership functions. The control design methodology is applied on four-area interconnected power system, which represents a large-scale power system. To evaluate the efficiency of the proposed controller, the obtained results are compared with those of Proportional Integral Derivative (PID) controller and Optimal Fuzzy PID (OFPID) controller, which are the most recent researches applied to the present problem. Simulation results demonstrate the successfulness and effectiveness of the Online-SAMBA Fuzzy PI (MBFPI) controller and its superiority over conventional approaches.

Online fuzzy based decision support system for human resource performance appraisal

The evaluation of employees’ performance is geared towards assessing individual’s contribution to the attainment of organizational goals. Performance appraisal (PA) is a key tool in an organization due to its potency to either make or mar such organization. Irregular standards for human resource PA, tribal sentiment, emotional status of assessors, and delay in appraisal processes among others are the key problems of the conventional methods of appraising employees’ performances in an organization. This research therefore proposes an online fuzzy based decision support system for human resource PA. The proposed system incorporates an efficient computational technique which handles the delays and bias associated with the orthodox performance appraisal system in organizations. The fuzzy inference system developed in this research uses Mamdani technique, Center of Gravity Defuzzification approach and takes as input the key attributes considered when appraising the performance of an employee. An experimental study of the proposed system was conducted using the dataset of academic staff. Standard statistical technique was used to measure the accuracy level of the System and the result shows that the proposed system has 0.78 probability (78%) of predicting accurately the appraisal status of an academic staff.

Transfer learning using the online Fuzzy Min–Max neural network

In this paper, we present an empirical analysis on transfer learning using the Fuzzy Min---Max (FMM) neural network with an online learning strategy. Three transfer learning benchmark data sets, i.e., 20 Newsgroups, WiFi Time, and Botswana, are used for evaluation. In addition, the data samples are corrupted with white Gaussian noise up to 50 %, in order to assess the robustness of the online FMM network in handling noisy transfer learning tasks. The results are analyzed and compared with those from other methods. The outcomes indicate that the online FMM network is effective for undertaking transfer learning tasks in noisy environments.

A bio-inspired kinematic controller for obstacle avoidance during reaching tasks with real robots

This paper describes a redundant robot arm that is capable of learning to reach for targets in space in a self-organized fashion while avoiding obstacles. Self-generated movement commands that activate correlated visual, spatial and motor information are used to learn forward and inverse kinematic control models while moving in obstacle-free space using the Direction-to-Rotation Transform (DIRECT). Unlike prior DIRECT models, the learning process in this work was realized using an online Fuzzy ARTMAP learning algorithm. The DIRECT-based kinematic controller is fault tolerant and can handle a wide range of perturbations such as joint locking and the use of tools despite not having experienced them during learning. The DIRECT model was extended based on a novel reactive obstacle avoidance direction (DIRECT-ROAD) model to enable redundant robots to avoid obstacles in environments with simple obstacle configurations. However, certain configurations of obstacles in the environment prevented the robot from reaching the target with purely reactive obstacle avoidance. To address this complexity, a self-organized process of mental rehearsals of movements was modeled, inspired by human and animal experiments on reaching, to generate plans for movement execution using DIRECT-ROAD in complex environments. These mental rehearsals or plans are self-generated by using the Fuzzy ARTMAP algorithm to retrieve multiple solutions for reaching each target while accounting for all the obstacles in its environment. The key aspects of the proposed novel controller were illustrated first using simple examples. Experiments were then performed on real robot platforms to demonstrate successful obstacle avoidance during reaching tasks in real-world environments.

On-Line Fuzzy Monitoring of Micro-Hole Drilling Based on Genetic Algorithm

In automated micro-hole drilling system, in order to improve the drilling performance and reduce of production costs by maximizing the use of drill life and preventing drill failures, the drill bit wear state monitoring is more important. However, drill bit wear is difficult to measure in drilling process. By observation, wear failure of the drill bit could cause related changes of the spindle current signal, so construct fuzzy control mathematical models with the relationship between drill bit wear and spindle current, genetic algorithm and fuzzy control theory are applied to micro-drilling system in this paper .The membership functions of fuzzy control model are optimized by genetic algorithms. Through calculation, we can get drill bit wear value which used as monitoring threshold value in micro-hole drilling on-line monitoring system to avoid the drill breakage and improve the monitoring reliability.

Convergence of the Single-Pass and Online Fuzzy C-Means Algorithms

Scalable versions of the widely used fuzzy c-means clustering algorithm called single-pass fuzzy c-means and online fuzzy c-means have been recently introduced. Both algorithms facilitate scaling to very large numbers of examples while providing partitions that very closely approximate those one would obtain using fuzzy c-means. Both algorithms have been successfully applied to a number of datasets, most notably, magnetic resonance image volumes of the human brain. In this letter, we show that weighting examples in the fuzzy c-means algorithm does not cause a violation in its convergence proof, and we provide a separate proof of convergence that holds for any dataset.

A methodology for designing of intelligent services in ubiquitous communications

Mobile ad hoc networks (MANETs) are recognised as one of the key infrastructures in ambient intelligence (AmI) due to their promising ubiquitous connectivity. Key factors for reliable performance of service protocols in MANETs are the manner in which they adapt to route changes caused by mobility and communicating traffic patterns. Our main idea to support AmI ubiquitous communications is to use fuzzy C-mean clustering as data mining technique to extract knowledge and dependencies from high-level information of the application scenario. We use the resulting knowledge to predict the upcoming context and make MANETs services context-aware. Thus, a mobile node builds dynamic models determined by IF-THEN rules for its various environments and adapts its service protocols. We propose a methodology for storing and processing MANETs context, online fuzzy reasoning about it and improving the performance of underlying service protocols based on simple distributed, unobtrusive and handling different scenarios intelligent algorithm.

COMPETITIVE ANALYSIS FOR THE MOST RELIABLE PATH PROBLEM WITH ONLINE AND FUZZY UNCERTAINTIES

Based on some results of the fuzzy network computation and competitive analysis, the Online Fuzzy Most Reliable Path Problem (OFRP), which is one of the most important problems in network optimization with uncertainty, has been originally proposed by our team. In this paper, the preliminaries about fuzzy and the most reliable path and competitive analysis are given first. Following that, the mathematical model of OFRP, in which two kinds of uncertainties, namely online and fuzzy, are combined to be considered at the same time, is established. Then some online fuzzy algorithms are developed to address the OFRP and the rigorous proofs of the competitive analysis are given in detail. Finally, some possible research directions of the OFRP are discussed and the conclusions are drawn.

Real-time process mining system for supply chain network: OLAP-based fuzzy approach

Currently, companies active in the development of high-tech products have become more and more complex in the age of mass customisation. Not only do they have to focus on improving product quality, but rather on gaining experience to modify the current processes in order to streamline the integrated workflow. A Real-time Process Mining System (R-PMS) is developed to analyse the proposed XML-based process data for discovering the hidden relationships among processes. The new feature of this system is the incorporation of the process mining engine, which is characterised by the combined capabilities of the Online Analytical Processing (OLAP) and Fuzzy Logic (FL), to form a robust framework for highlighting the undesirable process setting and parameters for further improvement in a real-time manner. The simulation results indicated that the OLAP-based fuzzy approach was generally superior to those of conventional methods which offer higher flexibility on production process management with decision support ability. In this paper, the detailed architecture and a case study have been included to demonstrate the feasibility of the proposed system.

Accurate and Fast Off and Online Fuzzy ARTMAP-Based Image Classification With Application to Genetic Abnormality Diagnosis

We propose and investigate the fuzzy ARTMAP neural network in off and online classification of fluorescence in situ hybridization image signals enabling clinical diagnosis of numerical genetic abnormalities. We evaluate the classification task (detecting a several abnormalities separately or simultaneously), classifier paradigm (monolithic or hierarchical), ordering strategy for the training patterns (averaging or voting), training mode (for one epoch, with validation or until completion) and model sensitivity to parameters. We find the fuzzy ARTMAP accurate in accomplishing both tasks requiring only very few training epochs. Also, selecting a training ordering by voting is more precise than if averaging over orderings. If trained for only one epoch, the fuzzy ARTMAP provides fast, yet stable and accurate learning as well as insensitivity to model complexity. Early stop of training using a validation set reduces the fuzzy ARTMAP complexity as for other machine learning models but cannot improve accuracy beyond that achieved when training is completed. Compared to other machine learning models, the fuzzy ARTMAP does not loose but gain accuracy when overtrained, although increasing its number of categories. Learned incrementally, the fuzzy ARTMAP reaches its ultimate accuracy very fast obtaining most of its data representation capability and accuracy by using only a few examples. Finally, the fuzzy ARTMAP accuracy for this domain is comparable with those of the multilayer perceptron and support vector machine and superior to those of the naive Bayesian and linear classifiers.

A decoupled fuzzy indirect adaptive sliding mode controller with application to robot manipulator

This paper presents a decoupled adaptive fuzzy Sliding Mode Control (SMC) for robotic manipulators. This controller is proposed for a class of Multiple-Input Multiple-Output (MIMO) systems with unknown non-linear dynamics. Indeed, an online fuzzy adaptation scheme is suggested to approximate unknown non-linear functions to design SMC. Moreover, the proposed controller is replaced by a local decoupled controller for each arm. The stability of the proposed control scheme is proved. As an illustration, the trajectory control of a two-degrees-of-freedom robotic manipulator is considered.

Learning and adaptation of an intelligent mobile robot navigator operating in unstructured environment based on a novel online Fuzzy–Genetic system

In this paper we present our novel Fuzzy–Genetic techniques for the online learning and adaptation of an intelligent robotic navigator system. Such a system could be used by autonomous mobile vehicles navigating in unstructured and changing environments. In this work we focus on the online learning of the obstacle avoidance behaviour, which is an example of a behaviour that receives delayed reinforcement. We show how this behaviour can be co-ordinated with other behaviours that receive immediate reinforcement (such as goal seeking and edge following) learnt during our previous work to generate an intelligent reactive navigator that can deal with unstructured and changing outdoor environments. The system described uses a life long learning paradigm whereby it is able to dynamically adapt to new environments and update its knowledge base.