Rule-based Fuzzy Inference System Research Articles

Supplier selection for managing supply risks in supply chain: a fuzzy approach

Supplier selection is one of the most important tasks for supply chain decision making, and there are many quantitative and qualitative factors that affect this process. This paper develops a simple and user-friendly supplier selection process for a supply chain which considers various selection criteria for managing supply risks. A rule-based fuzzy inference system (FIS) model is developed using the fuzzy logic toolbox in MATLAB R2012a to select the most excellent supplier by considering both quantitative and qualitative selection criteria. We identify a total of 18 selection criteria, of which four are quantitative and 14 qualitative. Risk factors are also incorporated in the model by developing fuzzy input and output criteria, and the best supplier is selected based on the aggregated supplier ranking index value. Finally, a numerical example presented to explain the usefulness of the developed model.

Microstructure Image Analysis for Estimating Mechanical Properties of Ductile Cast Iron

digital image processing and computer vision technologies have key role to play in the field of material manufacturing and quality control. The microstructure images of materials provide vital information about materials properties. The microstructure visual and mechanical properties are strongly related. The mechanical properties, namely, yield strength, tensile strength and elongation, of ductile iron are directly dependent on ferrite composition and nodularity value of the material. Castings with poor nodularity will exhibit lower tensile elongation and often do not meet minimum tensile strength and finally impact strength requirements. Hence, it is established by experimental results that the composition and nodularity value of the material have paramount importance in material manufacturing. In this paper, a novel automatic method of digital image analysis for estimating important mechanical properties with the help of microstructure visual properties has been proposed. Microstructure image analysis is performed for deriving microstructure properties, namely, nodularity value and percentage of ferrite phase present in material sample. A fuzzy rule based inference system is built using known authentic relationship data published in the research literature (3) to estimate important mechanical properties of the sample material using nodularity value and percentage of ferrite phase. With the inputs, namely, percentage of ferrite phase and nodularity values, to fuzzy inference system, the mechanical properties, namely, yield strength, tensile strength and elongation are predicted. The nodularity of the samples were determined by using image analysis techniques based on ASTM A 247-67(1968) standard. The automatic image analysis minimized the variability of the measurement due to operator bias. The results of the proposed method are compared with results obtained by manual method. The results of proposed method are accurate and close to practical limits. The proposed method is easily repeatable, fast and economical and is expected to be useful in manufacturing of ductile cast iron and quality control practices.

A self-tuning robust observer for marine surface vessels

The current work aims at developing a nonlinear, self-tuning, robust observer to estimate state variables pertinent to the control of under-actuated marine surface vessels. The state estimator combines the advantages of the variable structure systems theory with those of the self-tuning fuzzy logic algorithm. It does not require an exact knowledge of the system dynamics or the construction of a rule-based expert fuzzy inference system. However, the upper bounds of both modeling imprecision and external disturbances must be known. The convergence of the estimation process is guaranteed by forcing the tuning parameters to satisfy inequalities stemming from the sliding conditions. The observer has been implemented herein to provide accurate estimate of the state variables that are needed by an integrated guidance and control system for the autonomous operation of an under-actuated marine surface vessel. The observer along with the integrated guidance and control system have been tested on a six degree-of-freedom ship model that considers numerous uncertainties associated with wave excitation, nonlinear restoring forces, retardation forces, sea-current and wind resistive loads. The theoretical results prove that the proposed self-tuning observer can produce accurate estimates of the state variables in the presence of significant modeling imprecision and environmental disturbances. In addition, they illustrate the use of estimated state variables in the guidance and control system with minimal impact on the close-loop performance of the marine vessel.

A Fuzzy Rule-Based Penalty Function Approach for Constrained Evolutionary Optimization.

This paper proposes a novel fuzzy rule-based penalty function approach for solving single-objective nonlinearly constrained optimization problems. Of all the existing state-of-the-art constraint handling techniques, the conventional method of penalty can be easily implemented because of its simplicity but suffers from the lack of robustness. To mitigate the problem of parameter dependency, several forms of adaptive penalties have been suggested in literature. Instead of identifying a complex mathematical function to compute the penalty for constraint violation, we propose a Mamdani type IF-THEN rule-based fuzzy inference system that incorporates all the required criteria of self-adaptive penalty without formulating an explicit mapping. Effectiveness of the proposed constrained optimization algorithm has been empirically validated on the basis of the standard optimality theorems from the literature on mathematical programming. Simulation results show that fuzzy penalty not only surpasses its existing counterpart i.e., self adaptive penalty, but also remain competitive against several other standard as well as currently developed complex constraint handling strategies.

A Fuzzy Inference System (FIS) and Dimensional Analysis for Predicting Energy Consumption and Mean Residence Time in a Twin-Screw Extruder

Modeling the extrusion process is complex because of the many confounding variables and the dynamic properties of the materials subjected to heat, shear and pressure. Efforts have been made to predict various system and product properties using a flow-modeling phenomenological approach. However, because of the many assumptions and the complexities involved, these models become often impractical for application. In this study, dimensional analysis was used to determine significant dimensionless parameters for the inputs and outputs of a model constrained only by the available experimental data. Thereafter, a rule-based FIS was used, instead of a conventional exponential model, for the prediction of output dimensionless parameters. Optimization or selection of subtractive cluster radii for FIS was achieved using a genetic algorithm. Data were obtained from 4 × 3 × 3 × 2 experimental design (16, 20, 24 and 28% moisture contents; 80, 120 and 160 rpm screw speeds; 3, 4 and 5 mm nozzle diameters and 120 and 140C barrel temperatures) and 3 × 2 (80, 120 and 160 rpm screw speeds; 120 and 140C barrel temperatures for a 4 mm nozzle diameter and 26% moisture content). These factorial design experiments were conducted using a laboratory twin-screw extruder. After training, the FIS captured the process trend based on the experimental data. Correlation coefficient (r2) values were found higher than those obtained from a linear regression model. Practical Applications Extrusion process is widely used to produce human foods, dog foods and polymers. Prediction of extrusion performance and scale-up of the process are very challenging because of complex and dynamic characteristics of biological materials when shear and heat are applied simultaneously. This study presents a novel modeling method to predict dimensionless parameters involving MRT and torque experienced by the extruder. The model was validated with data collected from extrusion of corn starch. This model can be used by producers to predict change in energy consumption and MRT and facilitate scale-up when feed moisture content, die diameter, screw speed and barrel temperature are changed. The modeling methodology can be further expanded to predict other extrusion performance parameters and for other materials by training and validating the model with new data set.

Modelling ambiguity in urban planning

Most data related to urban and regional planning and the assessment of economic, environmental and social sustainability of a city or region have a spatial component. Some of these data are also inherently ambiguous in nature. Traditional Boolean logic in GIS lacks the capability to model the fuzziness, uncertainties and imprecision of data in geographic information and human decision-making processes. While considerable studies have investigated applications of fuzzy system in urban planning, only a few studies have attempted to integrate fuzzy inference within a GIS platform with the Mamdani method. To facilitate the efficient modelling and displaying of the imprecision of geographic data and human judgement, we develop a rule-based fuzzy inference system within ArcGIS environment using the Sugeno method. This article describes the development process of the system and demonstrates the usefulness of fuzzy logic application in urban planning. It concludes with a discussion of implications for urban planning and needs for further research.

Identifying desertification risk areas using fuzzy membership and geospatial technique – A case study, Kota District, Rajasthan

Desertification risk assessment is important in order to take proper measures for its prevention. Present research intends to identify the areas under risk of desertification along with their severity in terms of degradation in natural parameters. An integrated model with fuzzy membership analysis, fuzzy rule-based inference system and geospatial techniques was adopted, including five specific natural parameters namely slope, soil pH, soil depth, soil texture and NDVI. Individual parameters were classified according to their deviation from mean. Membership of each individual values to be in a certain class was derived using the normal probability density function of that class. Thus if a single class of a single parameter is with mean μ and standard deviation σ, the values falling beyond μ + 2σ and μ − 2σ are not representing that class, but a transitional zone between two subsequent classes. These are the most important areas in terms of degradation, as they have the lowest probability to be in a certain class, hence highest probability to be extended or narrowed down in next or previous class respectively. Eventually, these are the values which can be easily altered, under extrogenic influences, hence are identified as risk areas. The overall desertification risk is derived by incorporating the different risk severity of each parameter using fuzzy rule-based interference system in GIS environment. Multicriteria based geo-statistics are applied to locate the areas under different severity of desertification risk. The study revealed that in Kota, various anthropogenic pressures are accelerating land deterioration, coupled with natural erosive forces. Four major sources of desertification in Kota are, namely Gully and Ravine erosion, inappropriate mining practices, growing urbanization and random deforestation.

A Fuzzy-Based Taguchi Method for Multiobjective Design of PM Motors

This paper describes a design optimization based on the fuzzy-based Taguchi method coupled with finite element analysis (FEA). The proposed approach takes advantage of both the Taguchi method and a fuzzy rule based inference system, which forms a robust and practical methodology in tackling multiobjective optimization problems. The proposed methodology is applied to the optimization design of a surface-mounted permanent magnet (SPM) motor. The experimental results confirm the validity of the proposed method.

Environmental Sensor Drift Correction using Wavelet-mFCM-FIS Architecture: An Unsupervised Machine Learning Approach

novel hybrid sensor informatics architecture based on Discrete Wavelet Transform (DWT), Fuzzy logic based clustering (FCM) and Fuzzy Rule based Inference system (FIS) has been investigated and proposed to estimate dynamic generic sensor drift during physical sampling. DWT has been used for sensor pre-processing; data dimension reduction and feature extraction from sensor time series, where as DWT- FCM based approach has been used to estimate the cumulative drift in our sensory system. An intelligent generalized algorithm using multiple FCM maps (m-FCM) has been proposed to implement the drift correction on any future unknown data sets. In the next stage a newly proposed DWT-FCM-FIS architecture has been tested on multisensory environmental data sets covering three consecutive years (2009 - 11) to predict probable month (environmental time of the year) with up to 93% accuracy. This novel hybrid data processing architecture have been implemented and tested upon a real time estuary sensory platform of temperature, conductivity and salinity sensors that have been deployed to monitor the Derwent Estuary in Hobart, Australia. This newly proposed approach could be an adaptive solution to tackle drifts in the sensor networks and improve overall monitoring quality.

21

Introduction: Acute Lung Injury (ALI) is a devastating complication of acute critical illness and one of the leading causes of multiple organ failure and mortality in the intensive care unit (ICU). Early detection of ALI is essential for timely implementation of evidence-based therapies and enrollment into clinical trials. Hypothesis: In this work, we tested a mathematical model utilizing knowledge inferred from clinicians and electronic medical record (EMR) data for the early detection of ALI. Methods: Clinical knowledge sources, including physicians’ experience in critical care medicine, published research and standards, were translated into three complementary mathematical algorithms: rule-based fuzzy inference system, Bayesian network, and finite state machine. Patterns of ALI development expressed in EMR data were also captured by three data-mining algorithms: log-likelihood ratio, Lempel-Ziv complexity, and logistic regression. Finally, a linear discriminant analysis was used to aggregate the output of the aforementioned six algorithms into a single continuous ALI development indicator. The proposed model was trained on EMR data from a population-based sample of 506 (206 ALI, 300 Controls) critically ill patients treated in medical and surgical ICUs at Mayo Clinic, Rochester. Two independent reviewers retrospectively determined the gold standard ALI diagnosis according to the American-European Consensus criteria. The proposed model was tested on an independent validation dataset of 3889 (31 ALI, 3858 Controls) patients from the same ICUs. Model performance was evaluated using sensitivity, specificity, and positive predictive value (PPV). Results: The model achieved 87% sensitivity, 83% specificity and 36% PPV (adjusted to 10% ALI prevalence) in detecting ALI. The ALI model’s detection rate outperforms the current clinical detection rate (87% vs. 30%). In addition, 70% of model-detected ALI cases were identified before the gold standard ALI onset time, a median of 4.9 (IQR: 0.9-31.8) hours early. Conclusions: This mathematical inference model accurately detects early ALI development in critically ill patients and may facilitate early treatment and prevention of ALI and enrollment into time-sensitive clinical trials.

Memristive fuzzy edge detector

Fuzzy inference systems always suffer from the lack of efficient structures or platforms for their hardware implementation. In this paper, we tried to overcome this difficulty by proposing a new method for the implementation of the fuzzy rule-based inference systems. To achieve this goal, we have designed a multi-layer neuro-fuzzy computing system based on the memristor crossbar structure by introducing a new concept called the fuzzy minterm. Although many applications can be realized through the use of our proposed system, in this study we only show how the fuzzy XOR function can be constructed and how it can be used to extract edges from grayscale images. One main advantage of our memristive fuzzy edge detector (implemented in analog form) compared to other commonly used edge detectors is it can be implemented in parallel form, which makes it a powerful device for real-time applications.

Clinical Knowledge-Based Inference Model for Early Detection of Acute Lung Injury

Acute lung injury (ALI) is a devastating complication of acute illness and one of the leading causes of multiple organ failure and mortality in the intensive care unit (ICU). The detection of this syndrome is limited due to the complexity of the disease, insufficient understanding of its development and progression, and the large amount of risk factors and modifiers. In this preliminary study, we present a novel mathematical model for ALI detection. It is constructed based on clinical and research knowledge using three complementary techniques: rule-based fuzzy inference systems, Bayesian networks, and finite state machines. The model is developed in Matlab(®)'s Simulink environment and takes as input pre-ICU and ICU data feeds of critically ill patients. Results of the simulation model were validated against actual patient data from an epidemiologic study. By appropriately combining all three techniques the performance attained is in the range of 71.7-92.6% sensitivity and 60.3-78.4% specificity.

Fuzzy modeling applied to optical and surface properties of a ferrocenylsiloxane polyamide solution

Abstract A fuzzy model was designed to predict changes in surface tension and maximum absorbance due to self-assembly in a DMF solution of poly{1,1′-ferrocene-diamide-[1,3-bis(propylene) tetramethyl-disiloxane} as a function of temperature and concentration. The building of fuzzy rule-based inference systems appears as a grey-box because it allows interpretation of the knowledge contained in the model as well as its improvement with a-priori knowledge. The method provides accurate results and increases the efficiency of utilizing the available information in the model. Small mean squared errors (0.0064 for absorbance and 0.79 for surface tension) and strong correlations between experiment and simulated results (0.93 and 0.97, respectively) were found during model validation. The results showed that it is feasible to apply a Mamdani fuzzy inference system to the estimation of optical and surface properties of a ferrocenylsiloxane polyamide solution.

Rainfall events prediction using rule-based fuzzy inference system

We are interested in rainfall events prediction by applying rule-based reasoning and fuzzy logic. Five parameters: relative humidity, total cloud cover, wind direction, temperature and surface pressure are the input variables for our model, each has three membership functions. The data used is twenty years METAR data for Cairo airport station (HECA) [1972–1992] 30° 3′ 29″ N, 31° 13′ 44″ E. and five years METAR data for Mersa Matruh station (HEMM) 31° 20′ 0″ N, 27° 13′ 0″ E. Different models for each station were constructed depending on the available data sets. Among the overall 243 possibilities we have based our models on one hundred eighteen fuzzy IF–THEN rules and fuzzy reasoning. The output variable which has four membership functions, takes values from zero to one hundred corresponding to the percentage for rainfall events given for every hourly data. We used two skill scores to verify our results, the Brier score and the Friction score. The results are in high agreements with the recorded data for the stations with increasing in output values towards the real time rain events. All implementation are done with MATLAB 7.9.

Probabilistic Fuzzy Control of Mobile Robots for Range Sensor Based Reactive Navigation

In this paper, a probabilistic fuzzy approach is proposed for mobile-robot reactive navigation using range sensors. The primary motivation is an integrated reactive navigation control system with good real-time performance under uncertainty. To accomplish this aim, a probabilistic fuzzy logic system (PFLS) is introduced to range measurement and reactive navigation in local environments. PFLS is first adopted to handle the fuzzy and stochastic uncertainties in range sensors and to provide more precise distance information in unknown environments. Consequently these sensor data are sent to a probabilistic fuzzy rule-based inference system with reactive behaviors for local navigation. The feasibility and effectiveness of the proposed approach are verified by simulation and the experiments on a real mobile robot.

A fuzzy inference system for pump failure diagnosis to improve maintenance process: The case of a petrochemical industry

Pump operating problems may be either hydraulic or mechanical and there is interdependence between the failure diagnoses of these two categories. Consequently, a correct diagnosis of a pump failure needs to consider many symptoms and hydraulic or mechanical causes. But, due to nonlinear, time-varying behavior and imprecise measurement information of the systems it is difficult to deal with pumps failures with precise mathematical equations, while human operators with the aid of their practical experience can handle these complex situations, with only a set of imprecise linguistic if-then rules and imprecise system state, but this procedure is time consuming and needs the knowledge of human experts and experienced maintenance personnel. The purpose of this study is to provide a correct and timely diagnosis mechanism of pump failures by knowledge acquisition through a fuzzy rule-based inference system which could approximate human reasoning. The proposed fuzzy inference system by: (1) reduction of human error, (2) reduction of repair time (3) creation of expert knowledge which could be used for training (4) reduction of unnecessary expenditures for upgrades and finally, (5) reduction of maintenance costs, will improve the maintenance process. The novelty of this work is the knowledge acquisition (the extraction of linguistic rules) through the interactive impact of the critical failure modes on the both hydraulic and mechanical operating parameters including flow rate, discharge pressure, NPSHR (Net Positive Suction Head Required), BHP (Brake Horse Power), efficiency, vibration and temperature. The proposed approach is tested and applied to a petrochemical industry.

A GIS-integrated fuzzy rule-based inference system for land suitability evaluation in agricultural watersheds

Land suitability evaluation in water scarce agricultural watersheds consists of assessment of land potential for various crops as well as surface water potential to identify the scope for supplementary irrigation. A large amount of information related to the crop land suitability can be conveyed through linguistic terms. Capability of fuzzy sets in modeling involving uncertainty and vagueness is made use of in fuzzy rule-based systems, where various decision making criteria in linguistic terms are expressed as fuzzy rules. In the present study, a fuzzy rule-based inference system is developed in Geographic Information System (GIS) environment to assess the land suitability pertaining to the specified crop, considering both land potential and surface water potential. When large numbers of attributes are involved in decision making, representation of the attributes in a common scale, aggregation of the attributes and design of the rule-base becomes difficult tasks. In order to model the heterogeneous land suitability criteria involving large number of attributes, a new approach is proposed in this study in which the attributes are systematically classified into different groups to estimate the intermediate suitability indices. Weighted linear aggregation method and Yager’s aggregation method are used for estimating the aggregated effect of the attributes in each group and the results are compared. Further, the rule-base is developed by using the intermediate land suitability indices. The model has been applied to a subwatershed of Gandheshwari area in West Bengal (India). The input attributes are prepared in raster map format in the GIS environment by using ERDAS IP ver. 9.1 and the output is generated in the form of thematic map showing the suitability of each cell (20 m × 20 m) for the selected crop. For the land suitability evaluation problem in the case study area, Yager’s aggregation method has been found more appropriate than the commonly used weighted linear aggregation method. From the analysis, 23% of the existing paddy fields have been found less suitable/ not suitable for paddy due to the poor surface water potential or unsuitable terrain conditions of the area. The method, integrated with GIS, is found efficient in handling large amount of attribute information, and is useful in the land suitability assessment in agricultural watersheds.

Fog forecasting using rule-based fuzzy inference system

Operational meteorology is perceived as a fuzzy environment in which information is vaguely defined. The mesoscale processes such as fog, stratus and convection are generally dependent on the topography of the place and has always been difficult to forecast for the meteorologists. The main objective of the present study is to introduce the concept of fuzzy inference system (FIS) in the prediction of fog. This approach uses the concept of a pure fuzzy logic system where the fuzzy rule base consists of a collection of fuzzy IF-THEN rules. The fuzzy inference engine uses these fuzzy IF-THEN rules to determine a mapping from fuzzy sets in the input universe of discourse to fuzzy sets in the output universe of discourse based on fuzzy logic principles. Basic weather elements, which affect weather characteristics of fog, are fuzzified. These are then used in fuzzy weather prediction models based on fuzzy inferences. These models are simulated and the crisp results obtained using developed defuzzification strategies are compared with the actual weather data. The basis of methodology is to construct the fuzzy rule base domain from the available daily current weather observations in winter season over New Delhi. The results reveal that dew point spread and rate of change of dew point spread are the most important parameters for the formation of fog. The results further indicate that fog formation over New Delhi are dominant when (i) dew point is greater then 7°C along with dew point spread between 1 and 3°C. (ii) rate of change of dew point spread must be negative and wind speed should be less than 4 knots. This study presents a technique for predicting the probability of fog over New Delhi for 5–6 hours in advance. The skill score indicates that the performance of FIS is appreciably good. The method is found to be promising for operational application.

Use of Fuzzy Logic in Lignite Inventory Estimation

Seam thickness is one of the most important parameters for reserve estimation of a lignite deposit. This paper addresses a case study on fuzzy estimation of lignite seam thickness from spatial coordinates. From the relationships between input (Cartesian coordinates) and output (thickness) parameters, fuzzy clustering and a fuzzy rule-based inference system were designed. Data-driven fuzzy model parameters were derived from numerical values directly. In addition, estimations of the fuzzy model were compared with kriging estimations. It was concluded that the performance of the fuzzy model was more satisfactory. The results indicated that the fuzzy modeling approach is very reliable for the estimation of lignite reserves.

Contribution of fuzzy reasoning method to knowledge integration in a defect recognition system

This article presents the improvement of a defect recognition system for wooden boards by using knowledge integration from two expert fields. These two kinds of knowledge to integrate respectively concern wood expertise and industrial vision expertise. First of all, extraction, modelling and integration of knowledge use the Natural Language Information Analysis method (NIAM) to be formalized from their natural language expression. Then, to improve a classical industrial vision system , we propose to use the resulting symbolic model of knowledge to partially build a numeric model of wood defect recognition. This model is created according to a tree structure where each inference engine is a fuzzy rule based inference system. The expert knowledge model previously obtained is used to configure each node of the resulting hierarchical structure. The practical results we obtained in industrial conditions show the efficiency of such an approach.