Auxiliary error and probability density function based neuro-fuzzy model and its application in batch processes

This paper focuses on resolving the identification problem of a neuro-fuzzy model(NFM) applied in batch processes. A hybrid learning algorithm is introduced to identify the proposed NFM with the idea of auxiliary error model and the identification principle based on the probability density function(PDF). The main contribution is that the NFM parameter updating approach is transformed into the shape control for the PDF of modeling error. More specifically, a virtual adaptive control system is constructed with the aid of the auxiliary error model and then the PDF shape control idea is used to tune NFM parameters so that the PDF of modeling error is controlled to follow a targeted PDF, which is in Gaussian or uniform distribution. Examples are used to validate the applicability of the proposed method and comparisons are made with the minimum mean square error based approaches.

Identification of Neuro-Fuzzy Hammerstein Model Based on Probability Density Function

A new identification method of neuro-uzzy Hammerstein model based on probability density function(PDF) is presented,which is different from the idea that mean squared error(MSE) is employed as the index function in traditional identification methods.Firstly,a neuro-fuzzy based Hammerstein model is constructed to describe the nonlinearity of Hammerstein process without any prior process knowledge.Secondly,a kind of special test signal is used to separate the link parts of the Hammerstein model.More specifically,the conception of PDF is introduced to solve the identification problem of the neuro-fuzzy Hammerstein model.The antecedent parameters are estimated by a clustering algorithm,while the consequent parameters of the model are identified by designing a virtual PDF control system in which the PDF of the modeling error is estimated and controlled to converge to the target.The proposed method not only guarantees the accuracy of the model but also dominates the spatial distribution of PDF of the model error to improve the generalization ability of the model.Simulated results show the effectiveness of the proposed method.

A reversibly used cooling tower with adaptive neuro-fuzzy inference system

An adaptive neuro-fuzzy inference system(ANFIS) for predicting the performance of a reversibly used cooling tower(RUCT) under cross flow conditions as part of a heat pump system for a heating mode in winter was demonstrated.Extensive field experimental work was carried out in order to gather enough data for training and prediction.The statistical methods,such as the correlation coefficient,absolute fraction of variance and root mean square error,were given to compare the predicted and actual values for model validation.The simulation results predicted with the ANFIS can be used to simulate the performance of a reversibly used cooling tower quite accurately.Therefore,the ANFIS approach can reliably be used for forecasting the performance of RUCT.

Method to Improve Airborne Pollution Forecasting by Using Ant Colony Optimization and Neuro-Fuzzy Algorithms

This contribution shows the feasibility of improving the modeling of the non-linear behavior of airborne pollution in large cities. In previous works, models have been constructed using many machine learning algorithms. However, many of them do not work for all the pollutants, or are not consistent or robust for all cities. In this paper, an improved algorithm is proposed using Ant Colony Optimization (ACO) employing models created by a neuro-fuzzy system. This method results in a reduction of prediction error, which results in a more reliable prediction models obtained.

Neuro-fuzzy systems in determining light weight concrete strength

The adaptive neuro-fuzzy inference systems(ANFIS)are widely used in the concrete technology.In this research,the compressive strength of light weight concrete was determined.To this end,the scoria percentage and curing day variables were used as the input parameters,and compressive strength and tensile strength were used as the output parameters.In addition,100 patterns were used,70%of which were used for training and 30%were used for testing.To assess the precision of the neuro-fuzzy system,it was compared using two linear regression models.The comparisons were carried out in the training and testing phases.Research results revealed that the neuro-fuzzy systems model offers more potential,flexibility,and precision than the statistical models.

Optimization of ANFIS Network Using Particle Swarm Optimization Modeling of Scour around Submerged Pipes

In general,submerged pipes passing over the sedimentary bed of seas are installed for transmitting oil and gas to coastal regions.The stability of submerged pipes can be threatened with waves and coastal flows occurring at coastal regions.In this study,for the first time,the adaptive neuro-fuzzy inference system(ANFIS)is optimized using the particle swarm optimization(PSO)algorithm,and a meta-heuristic artificial intelligence model is developed for simulating the scour pattern around submerged pipes located in sedimentary beds.Afterward,six ANFIS-PSO models are developed by means of parameters affecting the scour depth.Then,the superior model is detected through sensitivity analysis.This model has the function of all input parameters.The calculated correlation coefficient and scatter index for this model are 0.993 and 0.047,respectively.The ratio of the pipe distance from the sedimentary bed to the submerged pipe diameter is introduced as the most effective input parameter.PSO significantly improves the performance of the ANFIS model.Approximately 36% of the scour depths simulated using the ANFIS model have an error less than 5%,whereas the value for ANFIS-PSO is roughly 72%.

Kinetic model of vibration screening for granular materials based on biological neural network

The kinetic model is the theoretical basis for optimizing the structure and operation performance of vibration screening devices.In this paper,a biological neurodynamic equation and neural connections were established according to the motion and interaction properties of the material under vibration excitation.The material feeding to the screen and the material passing through apertures were considered as excitatory and inhibitory inputs,respectively,and the generated stable neural activity landscape was used to describe the material distribution on the 2D screen surface.The dynamic process of material vibration screening was simulated using discrete element method(DEM).By comparing the similarity between the material distribution established using biological neural network(BNN)and that obtained using DEM simulation,the optimum coefficients of BNN model under a certain screening parameter were determined,that is,one relationship between the BNN model coefficients and the screening operation parameters was established.Different screening parameters were randomly selected,and the corresponding relationships were established as a database.Then,with straw/grain ratio,aperture diameter,inclination angle,vibration strength in normal and tangential directions as inputs,five independent adaptive neuro-fuzzy inference systems(ANFIS)were established to predict the optimum BNN model coefficients,respectively.The training results indicated that ANFIS models had good stability and accuracy.The flexibility and adaptability of the proposed BNN method was demonstrated by modeling material distribution under complex feeding conditions such as multiple regions and non-uniform rate.

An adaptive neuro-fuzzy inference system white-box model for real-time multiphase flowing bottom-hole pressure prediction in wellbores

The majority of published empirical correlations and mechanistic models are unable to provide accurate flowing bottom-hole pressure(FBHP)predictions when real-time field well data are used.This is because the empirical correlations and the empirical closure correlations for the mechanistic models were developed with experimental datasets.In addition,most machine learning(ML)FBHP prediction models were constructed with real-time well data points and published without any visible mathematical equation.This makes it difficult for other readers to use these ML models since the datasets used in their development are not open-source.This study presents a white-box adaptive neuro-fuzzy inference system(ANFIS)model for real-time prediction of multiphase FBHP in wellbores.1001 real well data points and 1001 normalized well data points were used in constructing twenty-eight different Takagi eSugeno fuzzy inference systems(FIS)structures.The dataset was divided into two sets;80%for training and 20%for testing.Statistical performance analysis showed that a FIS with a 0.3 range of influence and trained with a normalized dataset achieved the best FBHP prediction performance.The optimal ANFIS black-box model was then translated into the ANFIS white-box model with the Gaussian input and the linear output membership functions and the extracted tuned premise and consequence parameter sets.Trend analysis revealed that the novel ANFIS model correctly simulates the anticipated effect of input parameters on FBHP.In addition,graphical and statistical error analyses revealed that the novel ANFIS model performed better than published mechanistic models,empirical correlations,and machine learning models.New training datasets covering wider input parameter ranges should be added to the original training dataset to improve the model's range of applicability and accuracy.

Fatigue Life Estimation of High Strength 2090-T83 Aluminum Alloy under Pure Torsion Loading Using Various Machine Learning Techniques

The ongoing effort to create methods for detecting and quantifying fatigue damage is motivated by the high levels of uncertainty in present fatigue-life prediction approaches and the frequently catastrophic nature of fatigue failure.The fatigue life of high strength aluminum alloy 2090-T83 is predicted in this study using a variety of artificial intelligence and machine learning techniques for constant amplitude and negative stress ratios(R?1).Artificial neural networks(ANN),adaptive neuro-fuzzy inference systems(ANFIS),support-vector machines(SVM),a random forest model(RF),and an extreme-gradient tree-boosting model(XGB)are trained using numerical and experimental input data obtained from fatigue tests based on a relatively low number of stress measurements.In particular,the coefficients of the traditional force law formula are found using relevant numerical methods.It is shown that,in comparison to traditional approaches,the neural network and neuro-fuzzy models produce better results,with the neural network models trained using the boosting iterations technique providing the best performances.Building strong models from weak models,XGB helps to predict fatigue life by reducing model partiality and variation in supervised learning.Fuzzy neural models can be used to predict the fatigue life of alloys more accurately than neural networks and traditional methods.

N-甲酰吗啉芳烃萃取塔等温流率加和法模拟计算

Ｎ－甲酰吗啉是新一代芳烃萃取溶剂。以平衡级的概念为基础，应用等温流率加和法，建立了包括相平衡、物料平衡、分子分数加和式在内的多元体系液－液萃取过程的通用模拟计算程序，在不同的理论板数、溶剂比和回流比下，对以Ｎ－甲酰吗啉为溶剂从重整脱戊烷油中分离芳烃的萃取塔进行了模拟计算。在给定的条件下，得出了一组较适宜的操作参数。当操作温度为６０℃、理论塔板数为６、进料板为５、溶剂比为２．５、溶剂回收率为１．０和塔底萃取相回流比为０．７时，苯的收率可达９９．９９％，甲苯收率可达９９．９７％。

基于即时学习的间歇过程复合模型

通过传统的即时学习(JITL)方法建立间歇过程复合的线性化模型,利用一个具有5层结构的神经模糊模型(NFM)对局部模型的输出误差特性进行分析,建立模型输入与输出误差之间的非线性映射关系,并通过对模型的预测输出进行误差补偿来提高模型精度.仿真结果表明,所提出的基于JITL的间歇过程复合模型相对于传统JITL模型具有更高的精度和更强的噪声抑制能力.

A SELF-SIMILAR LOCAL NEURO-FUZZY MODEL FOR SHORT-TERM DEMAND FORECASTING

This paper proposes a selfsimilar local neurofuzzy （SSLNF） model with mutual informati onbased input selection algorithm for the shortterm electricity demand forecasting. The proposed self similar model is composed of a number of local models, each being a local linear neurofuzzy （LLNF） model, and their associated validity functions and can be interpreted itself as an LLNF model. The proposed model is trained by a nested local liner model tree （NLOLIMOT） learning algorithm which partitions the input space into axisorthogonal subdomains and then fits an LLNF model and its associated validity function on each subdomain. Furthermore, the proposed approach allows different input spaces for rule premises （validity functions） and consequents （local models）. This appealing property is employed to assign the candidate input variables （i.e., previous load and temperature） which influence shortterm electricity demand in linear and nonlinear ways to local models and validity functions, respectively. Numerical results from shortterm load forecasting in the New England in 2002 demonstrated the accuracy of the SSLNF model for the STLF applications.

Intelligent non-linear modelling of an industrial winding process using recurrent local linear neuro-fuzzy networks

This study deals with the neuro-fuzzy (NF) modelling of a real industrial winding process in which the acquired NF model can be exploited to improve control performance and achieve a robust fault-tolerant system. A new simulator model is proposed for a winding process using non-linear identification based on a recurrent local linear neuro-fuzzy (RLLNF) network trained by local linear model tree (LOLIMOT), which is an incremental tree-based learning algorithm. The proposed NF models are compared with other known intelligent identifiers, namely multilayer perceptron (MLP) and radial basis function (RBF). Comparison of our proposed non-linear models and associated models obtained through the least square error (LSE) technique (the optimal modelling method for linear systems) confirms that the winding process is a non-linear system. Experimental results show the effectiveness of our proposed NF modelling approach.

Neuro-fuzzy and model-based motion control for mobile manipulator among dynamic obstacles

This paper focuses on autonomous motion control of a nonholonomic platform with a robotic arm, which is called mobile manipulator. It serves in transportation of loads in imperfectly known industrial environments with unknown dynamic obstacles. A union of both procedures is used to solve the general problems of collision-free motion. The problem of collision-free motion for mobile manipulators has been approached from two directions, Planning and Reactive Control. The dynamic path planning can be used to solve the problem of locomotion of mobile platform, and reactive approaches can be employed to solve the motion planning of the arm. The execution can generate the commands for the servo-systems of the robot so as to follow a given nominal trajectory while reacting in real-time to unexpected events. The execution can be designed as an Adaptive Fuzzy Neural Controller. In real world systems, sensor-based motion control becomes essential to deal with model uncertainties and unexpected obstacles.

ANFIS-PID Control FES-Supported Sit-to-Stand in Paraplegics: (Simulation Study)

Adaptive Neuro-fuzzy Inference System (ANFIS) controller was designed to control knee joint during sit to stand movement through electrical stimuli to quadriceps muscles. The developed ANFIS works as an inverse model to the system (functional electrical stimulation (FES)-induced quadriceps-lower leg system), while there is a proportional-integral-derivative (PID) controller in the feedback control. They were designated as ANFIS-PID controller. To evaluate the ANFIS-PID controller, two controllers were developed: open loop and feedback controllers. The results showed that ANFIS-PID controller not only succeeded in controlling knee joint motion during sit to stand movement, but also reduced the deviations between desired trajectory and actual knee movement to ±5°. Promising simulation results provide the potential for feasible clinical application in the future.

The Influence of Control Design on Energetic Cost during FES Induced Sit-to-Stand

This paper highlights the benefits of using intelligent model based controllers to produce FES induced sit-to-stand movement (FES-STS), in terms of reducing energy cost and producing more natural responses in comparison with conventional controllers. A muscle energy expenditure model for the quadriceps is implemented in the control design of FES-STS, then simulation is run for three different control designs: an adaptive neuro-fuzzy inference system controller (ANFIS), a conventional PID controller, and a hybrid ANFIS-PID controller. The PID control strategy results in negative energy expenditure of the quadriceps at the end of the STS initiation phase, this negative energy is caused by the high lengthening speeds at the muscle fiber level, which may lead to muscle fatigue or damage. Contrary to PID controller, model based controllers show positive energy expenditure, lower energy costs, and more natural curves of energy expenditure and knee torques.

A model of flow separation controlled by dielectric barrier discharge

Flow separation, as an aerodynamic phenomenon, occurs in specific conditions. The conditions are studied in a wind tunnel on different airfoils. The phenomenon can be delayed or suppressed by exerting an external momentum to the flow. Dielectric barrier discharge actuators arranged in a row of 8 and perpendicular to the flow direction can delay flow separation by exerting the momentum. In this study, a mathematical model is developed to predict a parameter, which is utilized to represent flow separation on an NACA0012 airfoil. The model is based on the neurofuzzy method applied to experimental datasets. The neuro model is trained in different flow conditions and the parameter is measured by pressure sensors.

ON THE DESIGN OF A NEURO-FUZZY CONTROLLER–APPLICATION TO THE CONTROL OF A BIOREACTOR

This paper presents a new methodological approach for the synthesis ofa neuro-fuzzy controller, using an on-line learning procedure. A simple algebraic formulation of a Sugeno fuzzy inference system that ensures a coherent universe of discourse, making easy its interpretation by a human being, is proposed and implemented in the case of the control of a bioreactor, which is considered as a complex non linear process.

Direct adaptive regulation of unknown nonlinear systems with analysis of the model order problem

A new method for the direct adaptive regulation of unknown nonlinear dynamical systems is proposed in this paper,paying special attention to the analysis of the model order problem.The method uses a neurofuzzy (NF) modeling of the unknown system,which combines fuzzy systems (FSs) with high order neural networks (HONNs).We propose the approximation of the unknown system by a special form of an NF-dynamical system (NFDS),which,however,may assume a smaller number of states than the original unknown model.The omission of states,referred to as a model order problem,is modeled by introducing a disturbance term in the approximating equations.The development is combined with a sensitivity analysis of the closed loop and provides a comprehensive and rigorous analysis of the stability properties.An adaptive modification method,termed ‘parameter hopping’,is incorporated into the weight estimation algorithm so that the existence and boundedness of the control signal are always assured.The applicability and potency of the method are tested by simulations on well known benchmarks such as ‘DC motor’ and ‘Lorenz system’,where it is shown that it performs quite well under a reduced model order assumption.Moreover,the proposed NF approach is shown to outperform simple recurrent high order neural networks (RHONNs).

Prediction of cutting power and surface quality, and optimization of cutting parameters using new inference system in high-speed milling process

During the actual high-speed machining process,it is necessary to reduce the energy consumption and improve the machined surface quality.However,the appropriate prediction models and optimal cutting parameters are difficult to obtain in complex machining environments.Herein,a novel intelligent system is proposed for prediction and optimization.A novel adaptive neuro-fuzzy inference system(NANFIS)is proposed to predict the energy consumption and surface quality.In the NANFIS model,the membership functions of the inputs are expanded into:membership superior and membership inferior.The membership functions are varied based on the machining theory.The inputs of the NANFIS model are cutting parameters,and the outputs are the machining performances.For optimization,the optimal cutting parameters are obtained using the improved particle swarm optimization(IPSO)algorithm and NANFIS models.Additionally,the IPSO algorithm as a learning algorithm is used to train the NANFIS models.The proposed intelligent system is applied to the high-speed milling process of compacted graphite iron.The experimental results show that the predictions of energy consumption and surface roughness by adopting the NANFIS models are up to 91.2%and 93.4%,respectively.The NANFIS models can predict the energy consumption and surface roughness more accurately compared with other intelligent models.Based on the IPSO algorithm and NANFIS models,the optimal cutting parameters are obtained and validated to reduce both the cutting power and surface roughness and improve the milling efficiency.It is demonstrated that the proposed intelligent system is applicable to actual high-speed milling processes,thereby enabling sustainable and intelligent manufacturing.