Fuzzy Logic Research Articles

Probabilistic modeling of hydrogen pipeline failure utilizing limited statistical data

The estimation of failure probability is vital for managing pipeline integrity during hydrogen transportation. However, due to the lack of dedicated failure statistics for hydrogen pipelines, accurate probability assessments remain challenging despite numerous national pipeline incident databases. In this work, a quantitative method was developed for assessing hydrogen pipeline failure probabilities, even with extremely limited statistical data. Critical influencing factors and base failure probabilities of hydrogen pipelines were identified with the Pipeline and Hazardous Materials Safety Administration (PHMSA) database. A modified parameter system was proposed to explore the multi-level failure mechanisms associated with structural degradation through statistical analysis tailored to hydrogen pipelines. With integrating Bayesian inference and fuzzy logic analysis, a novel virtual expert system model was developed to employ random sampling analysis for correcting failure probabilities, thereby deriving a correction coefficient. The use of numerical cases illustrates the proposed method's effectiveness and interpretability. This work aims to support decision-making to ensure the safe remaining lifespan of hydrogen pipelines.

Expert System for Autoclave Damage Detection Using the Fuzzy Logic Method

As a resource supporting public health services, management of electromedical equipment must be carried out quickly, accurately and integratedly so that function, safety, security and benefits can be optimized. The management of electromedical equipment is regulated in the Republic of Indonesia Minister of Health Regulation Number 65 of 2016 concerning Electromedical Service Standards. The expected result of this research is an expert system that can accurately detect damage to sterile electromedical equipment, especially autoclaves. This expert system can then assist electromedical technicians in finding damage and as an assessment in making decisions for appropriate and validated actions to be taken. From the results of testing and analysis of the expert system for detecting damage to Autoclaves using the fuzzy logic method, the following conclusions were obtained. The damage detection expert system application in the Autoclave has been proven to be able to provide 100% diagnosis results. This system can assess the degree of damage of 11.6235981%. based on the input symptoms provided, thus providing decisions that are close to the actual conditions. The expert system built is able to speed up the damage detection process compared to manual methods. This helps in taking quicker action to prevent further damage to the autoclave.

Prediction of seam strength of cotton canvas fabric using fuzzy logic

This study investigates the application of fuzzy logic in predicting seam strength in cotton plain canvas fabric, focusing on both warp and weft directions. The precise prediction of seam strength is crucial for manufacturers to uphold quality standards, enhance production efficiency, and minimize waste. The fuzzy logic model in this study uses thread linear density and stitch per inch as input parameters and warp and weft seam strength as output variables. The modeling was conducted using MATLAB, specifically utilizing the Mamdani fuzzy inference system with triangle membership functions. The fuzzy logic model was found to be very accurate, as shown by coefficients of determination (R2) of 0.9841 for the warp way and 0.9888 for the weft way, along with correlation coefficients (R) of 0.992 and 0.9944. The mean absolute percentage error (MAPE) was calculated to be 4.8719 % for the warp way and 4.7561 % for the weft way, each below 5 %, underscoring the model's reliability and robustness in seam strength prediction. This research provides findings with substantial implications for the textile industry, where the application of predictive models is on the rise to enhance production efficiency and product quality. Manufacturers can improve their ability to forecast regarding fabric properties and adjust production processes through the implementation of fuzzy logic models. This approach is consistent with current industry trends emphasizing automation and digitalization, wherein predictive models are essential for facilitating smart manufacturing and quality control.

Enhancing Multi-Machine Power System Stability with STATCOM-SMES: A Soft Computing Approach

The increasing complexity and increasing mismatch between supply and demand within modern power systems necessitate advanced methods for ensuring system stability and reliable operation. This article investigates the enhancement of transient stability in a multi-machine power system through the integration of Flexible AC Transmission Systems (FACTS) devices, specifically a Static Synchronous Compensator (STATCOM) combined with energy storage. Leveraging soft computing techniques such as Fuzzy Logic Controllers (FLC) and Artificial Neural Networks (ANN), this study evaluates the performance improvements in transient stability. The methodology involves modeling a multi-machine power system, implementing STATCOM-SMES configurations, and designing FLC and ANN controllers to dynamically support system stability. Simulations are conducted using MATLAB/Simulink, applying a three-phase to ground fault to assess the system's transient response. Performance metrics such as peak overshoot, settling time, and damping ratio are analyzed to compare the effectiveness of the proposed techniques. The results demonstrate significant improvements in transient stability with the application of FLC and ANN controlled STATCOM-SMES systems. This study underscores the potential of integrating soft computing techniques with FACTS devices to enhance the dynamic performance and resilience of power systems, contributing valuable insights for future research and practical applications in power system stability.

Adaptive fuzzy inverse optimal output feedback decentralised prescribed performance control for interconnected nonlinear systems

This paper investigates an adaptive fuzzy inverse optimal output feedback decentralised prescribed performance control problem for interconnected systems. Firstly, the fuzzy logic systems (FLSs) are utilised to model unknown nonlinear functions in each subsystem and then an auxiliary system is constructed. Based on the auxiliary system, a fuzzy decentralised state observer is formulated to estimate unmeasurable states. Secondly, by applying the adaptive backstepping design technique and the inverse optimal control theory, an adaptive fuzzy inverse optimal output feedback decentralised controller is ultimately designed. It is proved that the proposed adaptive fuzzy inverse optimal decentralised controller not only minimises the cost function but also ensures that all variables of the control systems are semi-globally ultimately bounded and that the tracking errors converge to a small residual set with the prescribed performance bound. Finally, the effectiveness of the proposed control approach is verified by a nonlinear inverted pendulum large-scale system.

Robust Control Strategy of Acoustic Micro Robots Based on Fuzzy System.

This study presents a robust control strategy for acoustic micro robots utilizing a novel interval type-three fuzzy system. Micro robots driven by acoustic forces face significant challenges in fluid environments due to complex nonlinearities, uncertainties, and disturbances. To address these issues, we propose a control framework that combines fuzzy logic and sliding mode control to enhance the stability and trajectory tracking performance of micro robots under varying fluid conditions. The interval type-3 fuzzy logic system provides increased robustness by better handling external disturbances and uncertainties compared to the robustness of the traditional methods. The experimental results from one-dimensional, two-dimensional, and three-dimensional fluid cavities demonstrate that the proposed control method significantly improves tracking accuracy, reducing the errors in complex environments. This control framework offers promising potential for the precise manipulation of micro robots in biomedical applications and other microfluidic systems. The minimum trajectory tracking control mean square error is 12.82 μm.

A Q‐Learning and Fuzzy Logic Control of Hybrid Energy Storage System Using Two Stage Low‐Pass Filter to Smooth Power Fluctuations in Microgrid

ABSTRACTThe intermittent and fluctuating nature of wind turbine output power is increasingly being recognized as a significant issue adversely impacting the power quality and stability of electrical grids. With the increasing integration of wind power, this challenge cannot be underestimated. However, a potential solution for mitigating the adverse effects of such fluctuations lies in the Hybrid Energy Storage System (HESS), which encompasses battery energy storage systems (BESS) and supercapacitors (SC). The HESS is equipped with flexible operational modes for charging and discharging, thus enabling grid‐connected microgrids to possess the ability to counteract these oscillations. In this article, a control strategy based on the combination of Q‐learning and fuzzy logic control approaches is presented for tuning the parameters of a utilized two‐stage variable time constant low‐pass filter (LPF) in a grid‐connected microgrid. The proposed strategy adaptively tunes the time constants of LPFs to mitigate wind power fluctuations. Furthermore, practical constraints for the energy storage systems and their interfaced converters, such as preventing overcharge/discharge, ramp rate requirements, and certain maximum power conversion ranges, have been taken into account. Numerical simulation results verify the effectiveness of the proposed two‐stage variable time constant LPF for output wind power fluctuation reduction considering practical constraints of HESS.

Adaptive fixed-time fuzzy control for delayed recycling continuous stirred tank reactor with asymmetric time-varying full-state constraints

Recently, there are some results concerning stability and finite-time stability control for continuous stirred tank reactors (CSTR). However, when considering the control of time-delay CSTR systems or fixed-time stability of CSTR systems, there are relatively few articles involved. In this paper, we first consider the CSTR system that includes both of the above factors simultaneously, that is, the adaptive fixed-time fuzzy control design problem for a CSTR with a delayed recycle stream and asymmetric time-varying full-state constraints. Firstly, based on existing works, we present an improved practical fixed-time stability criterion, which can be applied to more complex nonlinear systems. Then, we construct time-varying asymmetric integral barrier Lyapunov functions to handle asymmetric time-varying full-state constraints. Next, fuzzy logic systems are used to approximate the unknown functions of the system, and a sliding mode differentiator is introduced to avoid the “explosion of complexity” of the time derivative of the virtual controller. Furthermore, using the improved practical fixed-time stability criterion, we present the adaptive fixed-time fuzzy controller design processes that can ensure tracking performance in a fixed-time, and states of the system never violate their constraint bounds. Finally, a simulation example is provided to verify the effectiveness of the proposed control strategy.

Optimal data-driven strategy for in-house and outsourced technological innovations by open banking APIs

AbstractOpen banking is a customer consent-driven data-sharing framework to maintain interoperability among financial and non-financial institutions through secure application programming interfaces. Traditional retail banks are losing their competitive edge against digital banks, FinTech, and BigTech firms due to a higher outflow of customer account data than inflow. These firms capitalize on open banking data to launch innovative products and introduce “ready-to-deploy” Banking-as-a-Service platforms for end-to-end banking operations without the need to build full-scale infrastructures. Therefore, banks must reshape data-driven strategies to stay competitive. This research proposes a decision-support tool to select optimal digital strategies using the Strategic Value Index (SVI), a metric derived from analyzing multiple strategic objectives of bank stakeholders. The SVI minimizes implementation time and costs while maximizing operational action importance to a balanced digital strategy that combines both in-house and outsourced technological developments. The importance of operational action is quantified using evidential reasoning with fuzzy logic to address the challenge of aggregating incomplete and ambiguous banking data and assessments from multiple stakeholders. The theoretical approach is validated through a real application in a Latin American bank, and its findings are globally transferable. Cost and time data were sourced from public repositories, as made available accessible through government-mandated disclosures. The sensitivity analysis revealed that hybrid in-house and outsourced development is more flexible in meeting tight timelines and budget constraints. The combined approach is more cost-effective, time-efficient, and aligned with the internal needs of banks compared to either entirely in-house or fully outsourced models.

High-Order Disturbance Observer-Based Fuzzy Fixed-Time Safe Tracking Control for Uncertain Unmanned Helicopter with Partial State Constraints and Multisource Disturbances

In the real-world operation of unmanned helicopters, various state constraints, system uncertainties and multisource disturbances pose considerable risks to their safe fight. This paper focuses on anti-disturbance adaptive safety fixed-time control design for the uncertain unmanned helicopter subject to partial state constraints and multiple disturbances. Firstly, a developed safety protection algorithm is integrated with the fixed-time stability theory, which assures the tracking performance and guarantees that the partial states are always constrained within the time-varying safe range. Then, the compensation mechanism is developed to weaken the adverse impact induced by the filter errors. Simultaneously, the influence of the multisource disturbances on the system stability are weakened through the Ito^ differential equation and high-order disturbance observer. Further, the fuzzy logic system is constructed to approximate the system uncertainties caused by the sensor measurement errors and complex aerodynamic characteristics. Stability analysis proves that the controlled unmanned helicopter is semi-globally fixed-time stable in probability, and the state errors converge to a desired region of the origin. Finally, simulations are provided to illustrate the performance of the proposed scheme.

Solving Fuzzy Delay Differential Equations using Fuzzy Elzaki Transform and Fuzzy Elzaki Decomposition Method

Objective: In this work, the fuzzy Elzaki transform and fuzzy Elzaki decomposition method are used to solve fuzzy delay differential equations. The fuzzy Elzaki decomposition method is a combination of the fuzzy Elzaki transform and Adomian decomposition method in a fuzzy environment. The use of transforms in solving differential equations makes the solution process simpler. Methodology: The fuzzy Elzaki transform is applied in the fuzzy delay differential equation. The nonlinear terms are decomposed using Adomian polynomials in a nonlinear fuzzy delay differential equation. In the transformed domain, the resulting algebraic equation is solved. The solution in the original time domain is obtained by applying the inverse Elzaki transform. Findings: The fuzzy Elzaki transform and fuzzy Elzaki decomposition method are useful for handling the complexities associated with fuzzy functions and delays in differential equations. The technique used to solve the fuzzy delay differential equation gives results with better accuracy compared to the exact solution. The applicability of the method is illustrated with numerical examples. Novelty: The Elzaki transform is a helpful tool for solving delay differential equations with discontinuities. For the resilient solution of complicated differential equations, especially those including nonlinearity and fuzzy logic, the fuzzy Elzaki decomposition approach is useful. It gives an organized way to find the solution to fuzzy delay differential equation by utilizing the advantages of both the Elzaki transform and the Adomian decomposition method in a fuzzy situation. Keywords: Triangular Fuzzy Number, Fuzzy Elzaki Transform, Adomian decomposition method, Fuzzy Elzaki decomposition method, Fuzzy Delay Differential Equations (FDDE)

FMCNet: A Fuzzy Multiscale Convolution Network for Remote Sensing Image Segmentation

Due to being affected by factors such as imaging distance, lighting, ground features, and environment, objects in the same class may have certain differences, and different classes of objects often produce similar visual features in remote sensing images. This phenomenon leads to an uncertainty problem in segmentation of remote sensing images, i.e., intra-class heterogeneity and inter-class blurring. To alleviate this problem, a fuzzy multiscale convolution neural network (FMCNet) is proposed in this paper. By extracting receptive fields of different scales, sizes and aspect ratios, the detailed information in remote sensing objects is fully represented. The relationship between their adjacent pixels is effectively expressed by fuzzy logic learning to alleviate the uncertain segmentation. The proposed method achieves overall accuracies of 85.33%, 86.31%, and 85.39% on the Vaihingen, Potsdam, and Gaofen Image datasets respectively. It demonstrates superior performance compared to existing popular methods.

Fuzzy Neural Logic Reasoning for Robust Classification

The efficacy of neural networks is widely recognized across a multitude of machine learning tasks, yet their black-box nature impedes the understanding of their decision-making processes. Such lack of explainability limits their use in high-stake fields such as medicine and finance, where transparent decision-making is essential. In contrast, traditional rule-based models offer clear input-output mappings, but often lag in performance when compared to their neural network counterparts. To address this challenge, this study introduces Fuzzy Neural Logic Reasoning (FNLR), a novel architecture that combines the best of both rule-based and deep learning models to achieve performance, interpretability, and noise robustness simultaneously. At its core, FNLR employs a “Symbolic Pre-training + Neural Fine-tuning” paradigm. Initially, the model adapts a pre-fitted binary decision tree. It then performs a “neuralization” process, replacing each node of the tree with a corresponding neural network equivalent. This transformation is facilitated through three shallow MLP modules, which are trained to emulate the relational operators intrinsic to decision trees. The model architecture is also extensible, allowing it to further boost expressiveness. Furthermore, FNLR incorporates fuzzy logic by proposing novel fuzzy relational operators, accounting for satisfaction degrees of propositions and thus eliminating rigid decision boundaries. This approach enhances model flexibility, enabling all paths of the decision tree to contribute to the target prediction in a weighted manner. Empirical evaluations on tabular datasets from various domains demonstrate that FNLR performs comparably to, or better than, state-of-the-art deep learning models designed for tabular data, while also exhibiting strong robustness to noise.

Type-2 fuzzy adaptive robust fault-tolerant control for manipulators with disturbance observer

A configuration of interval type-2 (IT2) fuzzy adaptive fault-tolerant control strategy is designed for the position trajectory tracking of cooperated robot manipulators carrying a common object. First, a non-zero time-varying parameter is installed in IT2 FLS, then a property of universal approximation of IT2 fuzzy logic system (FLS) is proposed, where the non-zero time-varying parameter has the relation with the approximation precision of IT2 FLS. Second, for the unknown compounded disturbance, a disturbance observer is designed to estimate it and is integrated into the IT2 adaptive control. To improve the approximation accuracies, the novel IT2 FLSs with non-zero parameter are utilized to compensate for the uncertain nonlinear terms with including the uncertainties and fault components in the system, the fault-tolerant control with some adaptive laws are established using the stability theory of barrier Lyapunov function (BLF), where the approximation accuracies can be modified online using the provided adaptive laws with neglecting the number of fuzzy rules, the computation burden of the proposed control is greatly reduced because of a small number of updated laws. Finally, the simulation results are compared with those of several existing control methods, which confirms the validity of the designed control approach.

Geotechnological multicriteria analysis applied to identify optimal locations for the installation of sanitary landfills

The Urban Solid Waste sector is one of the main contributors to methane emissions. Despite specific legislation, many Brazilian municipalities still maintain outdated waste dumps. Geotechnological tools, such as Fuzzy logic, can provide a viable and efficient solution. This research aimed to evaluate the current location and identify optimal sites for the implementation of sanitary landfills, using Fuzzy logic. We considered were slope, proximity to water bodies, urban areas, roads, and airports, land use and occupation, geology, and pedology. The results showed that the current dump location is inadequate due to its proximity to the airport, roads, and urban center. The suitability map revealed that 35.38% of the studied area has high to very high suitability. The new selected location to landfill having sufficient area, being distant from the airport and urban center, and complying with operational and logistical standards of proximity to highways and water bodies. The research confirms that the current Urban Solid Waste structure is not in compliance with regulations and that Fuzzy logic is effective in selecting sites for new sanitary landfills. This model can serve as a reference for other municipalities, contributing to more efficient and responsible waste management.

Research on Well Selection Method for Intermittent Pumping in Oil Wells Based on the Analytic Network Process and Fuzzy Logic

In the later stages of oilfield development, the decline in oil well production and the increase in development costs, attributed to issues such as insufficient liquid supply, necessitate the implementation of intermittent pumping measures. However, current methods for selecting these wells lack comprehensiveness in the decision-making process. This article proposes a novel method for selecting intermittent pumping wells utilizing the analytic network process (ANP) and fuzzy logic. Initial surveys identified the main factors influencing intermittent pumping effectiveness. The ANP was employed to screen and integrate six core factors, including submergence depth and water cut. Subsequently, a fuzzy-logic-based model was developed, incorporating trapezoidal and rectangular membership functions to establish detailed correlations among the factors. The model’s efficacy was validated and tested using real-world data from the oilfield. Results indicate that the model’s assessments of intermittent pumping wells align closely with professional engineering judgments. This approach not only provides clear guidance for well selection but also demonstrates high scalability and adaptability across different oilfields by adjusting membership functions, thereby showcasing significant practical value.

Forecasting High-Order Multifactor Cross Relations Using Fuzzy Time Series and Frequency Density

The forecasting technique frequently employed for decision-making, initially presented by Song and Cissom utilizing fuzzy logic principles, is Fuzzy Time Series (FTS). The FTS forecasting approach comprises fundamental steps: identifying the conversation universe, segmenting the conversation universe, fuzzification, constructing the fuzzy logic relationship (FLR), and defuzzification. This study involved the modification of the existing methodology to ascertain and categorize the conversational universe, fuzzy logic relationships (FLR), and historical data variations, each utilizing distinct frequency density partitions and cross-relationships, specifically with Indonesian rubber production data. Altering the frequency density partition algorithm to achieve partition universality, followed by fuzzification, cross-relationship analysis, and concluding with the defuzzification procedure. The degree of forecast precision uses the Average Forecasting Error Rate (AFER) to evaluate the revised outcomes against the traditional method. Simulations utilize Indonesian rubber production data from 2000 to 2023, exhibiting an AFER of 3.901%, below 10%, indicating robust forecasting criteria. The forecasting technique frequently employed for decision-making, initially presented by Song and Cissom through the principle of fuzzy logic, is Fuzzy Time Series (FTS). The FTS forecasting approach comprises fundamental steps: identifying the conversation universe, segmenting the conversation universe, fuzzification, constructing the fuzzy logic relationship (FLR), and defuzzification. This study involved the modification of the existing methodology to ascertain and categorize the conversational universe, fuzzy logic relationships, and historical data variations, each employing distinct frequency density partitions and cross-relationships, utilizing Indonesian rubber production data. Altering the frequency density partition algorithm to achieve partition universality, followed by fuzzification, cross-relationship analysis, and concluding with the defuzzification procedure. The degree of forecast precision uses the Average Forecasting Error Rate (AFER) to juxtapose the revised outcomes with the traditional methodology. Simulations utilize Indonesian rubber production data from 2000 to 2023, exhibiting an AFER of 3.901%, below 10%, indicating robust forecasting criteria.

Adaptive fuzzy gain-scheduling robust control for stability of quadrotors

To solve the instability problem in quadrotor control system subject to parametric uncertainties and external disturbances, an attitude control approach integrated with adaptive fuzzy gain-scheduling desired model compensation robust integral of the sign of the error is proposed. Firstly, the original cascade model of attitude motion is transformed into a strict feedback form with lumped disturbances. Secondly, a desired model compensation robust integral of the sign of the error controller is designed to regulate attitude motion for its invariant properties to lumped disturbances, replacing the velocity state in model-based feedforward control with expected value to ensure the robustness of the system against uncertainties without velocity information. To mitigate the chattering caused by continuous switching control, the fuzzy logic system is used to construct the proposed robust control algorithm, in which robust integral feedback gains associated with the sign function based on fuzzy rules are adaptive scheduled, with the filter tracking error and its derivative as inputs to the fuzzy logic system and robust integral feedback gains as outputs. The stability of the designed closed-loop system is verified by analyzing the convergence of output errors. Finally, the effectiveness and robustness of the proposed method in dealing with the stability of the control system are fully demonstrated by extensive simulations and platform experiments.

Incremental model checking for fuzzy computation tree logic

Fuzzy model checking, also called multi-valued model checking, has proved to be an effective technique in verifying properties of fuzzy systems. One important issue with fuzzy model checking, is that a model adopted in fuzzy model checking is frequently updated with small changes, and it is too costly to run a model-checking algorithm from scratch in response to every update. To address the issue, in this paper, we consider the incremental model-checking approach for fuzzy systems by making maximal use of previous model checking results or in other words, by minimizing unnecessary recomputation. The models of our study are fuzzy Kripke structures, which are a fuzzy counterpart of Kripke structures and used to describe fuzzy systems, while the properties of fuzzy systems are expressed using fuzzy computation tree logic, a fuzzy temporal logic derived from computation tree logic. The focus of the paper is on how to design incremental model-checking algorithms for two until-formulas which characterize the maximal or dually minimum constrained reachability properties with respect to fuzzy Kripke structures under transition insertions or deletions but not both. The feasibility of our approach is illustrated by an example arising from the path planning problem of mobile robots.

A comparative analysis of prediction problems utilizing Interval type-2 fuzzy and machine learning models

This paper compares the effectiveness of Interval Type 2 Fuzzy Logic (IT2FL) and Machine Learning (ML) models in addressing real-world challenges. It employs four non-parametric ML algorithms (Support Vector Machine (SVM), K-Nearest Neighbor (KNN), (Random Forest (RF) and Classification and Regression Tree (CART)) and evaluates their performance against IT2FL using parameters generated through Gaussian membership functions. Initially, the IT2FL algorithm preprocesses the dataset by predicting missing values, leveraging IT2F membership to optimize decision-making and mitigate uncertainties. The study assesses the predictive performance, robustness, and interpretability of IT2F-ML models, analyzing datasets from cardiovascular disease patients to predict shock levels. After transforming the dataset using IT2FL, it is divided into 60% training and 40% testing sets to train and test four ML algorithms, aimed at predicting shock levels in patients. The models’ performance is evaluated using various metrics, demonstrating the superior learning enhancement and performance of the IT2F-SVR method compared to other predictive approaches on the same dataset. Moreso, it is observed that the integration of the IT2-FL algorithm with machine learning models offers a promising approach for addressing data incompleteness and improving prediction accuracy. Furthermore, the study provides valuable guidance for researchers and practitioners in selecting suitable methodologies for prediction tasks.