Tool Wear Length Estimation with a Self-Learning Fuzzy Inference Algorithm in Finish Milling

An approach for environmental risk assessment of engineered nanomaterials using Analytical Hierarchy Process (AHP) and fuzzy inference rules

A fuzzy radial basis adaptive inference network (FRBAIN) is proposed for multichannel time-varying signal fusion analysis and feature knowledge embedding. The model which combines the prior signal feature embedding mechanism of the radial basis kernel function with the rule-based logic inference ability of fuzzy system is composed of a multichannel time-varying signal input layer, a radial basis fuzzification layer, a rule layer, a regularization layer, and a T-S fuzzy classifier layer. The dynamic fuzzy clustering algorithm was used to divide the sample set pattern class into several subclasses with similar features. The fuzzy radial basis neurons (FRBNs) were defined and used as parameterized membership functions, and typical feature samples of each pattern subclass were used as kernel centers of the FRBN to realize the embedding of the diverse prior feature knowledge and the fuzzification of the input signals. According to the signal categories of FRBN kernel centers, nodes in the rule layer were selectively connected with nodes in the FRBN layer. A fuzzy multiplication operation was used to achieve synthesis of pattern class membership information and establishment of fuzzy inference rules. The excitation intensity of each rule was used as the input of T-S fuzzy classifier to classify the input signals. The FRBAIN can adaptively establish fuzzy set membership functions, fuzzy inference, and classification rules based on the learning of sample set, realize structural and data constraints of the model, and improve the modeling properties of imbalanced datasets. In this paper, the properties of FRBAIN were analyzed and a comprehensive learning algorithm was established. Experimental validation was performed with classification diagnoses from four complex cardiovascular diseases based on 12-lead ECG signals. Results demonstrated that, in the case of small-scale imbalanced datasets, the proposed method significantly improved both classification accuracy and generalizability comparing with other methods in the experiment.

Variables in the production environment inevitably result in deviations from the generated schedules. These variables affecting the system performance should be considered when dealing with dynamic dispatching problems. In addition, determination of the dispatching rules based on a single performance criterion cannot satisfy the requirements of different production performances. In this research, a dynamic dispatching strategy for multiple performance measures based on fuzzy inference is proposed. First, the variables affecting the system performance are identified. Then, the fuzzy membership functions and the fuzzy inference rules are established based on the simulation data. According to the statuses of environment variables, the fuzzy inference is performed to find an appropriate dispatching rule at each decision point to meet the best multiple performance measures. An example of the application is presented. The simulation results indicate that the proposed fuzzy-based dynamic dispatching strategy has a very good and robust performance.

In this paper, we discuss mainly a new method for building the fuzzy controller for controlling aeration devices in the grain-storage system. This new fuzzy-control method is used for designing a special fuzzy-control strategy for the aeration management or in-bin drying stored grain. First, the method defines the fuzzy-control base variables which consist of the fuzzy-control membership function. Then, it constructs the fuzzy-control rule base which supports the fuzzy rule inference. Next, it implements the fuzzy rule inference, so that the rules in the rule base can determine the trace of action that the aeration devices must follow. Finally, it translates the result of the fuzzy inference from a linguistic concept to a crisp output value to drive the aeration devices. Thus, the aeration devices are automatically operated at suitable times to implement the scientific management for in-bin drying stored grain.

The central point in designing a fuzzy system for modeling and control is the generation of a set of efficient and effective fuzzy rules. Generally, fuzzy rules can be generated either from heuristics or from experimental data. Heuristic fuzzy rule generation, as discussed in Chapter 1, consists of the following main steps: Determination of the structure of the fuzzy systems. This includes mainly the selection of the inputs and outputs. Usually, a multi-input multi-output fuzzy systems can be decomposed into a number of multi-input single-output fuzzy systems. Definition of linguistic terms and their fuzzy membership function for each fuzzy variables. If a Mamdani fuzzy system is designed, each input and output can be seen as a linguistic variable. Therefore, it is necessary to define the linguistic terms (e.g., Small, Medium, Large etc.) and their fuzzy membership function. Details about the definition of a linguistic variable is presented in Section 1.2.1. Determination of fuzzy inference method. For example, for fuzzy mapping rules, the fuzzy Cartesian product can be used to define the fuzzy relation. Refer to Section 1.2.2. Defuzzification. If the Mamdani type fuzzy rules are used, the fuzzy output derived from the fuzzy rule base should be defuzzified. Refer also to Section 1.2.2 for different defuzzification methods. If the Takagi-Sugeno fuzzy rules are used, the defuzzification is included in the fuzzy inference and a crisp output is obtained directly.

A broad-deep fusion network-based fuzzy emotional intention inference model for teaching validity evaluation

In the heating, ventilating, and air-conditioning (HVAC) system, chiller is the central part and one of the primary energy consumers. For the purpose of saving energy, the identification of the chiller model is of great significance. In this paper, based on fuzzy inference rules with Zadeh's implication operator, the model of chiller in HVAC is identified. The mean square error (MSE) is employed to evaluate the approximating capability of the fuzzy inference system. The objective of the problem is to minimize MSE. Since the Zadeh's implication operator is adopted in the fuzzy inference, the output of the system becomes a continuous but non-smooth function. In addition, the objective function contains many parameters that need to be optimized, consequently, traditional optimization algorithms based on gradient descent method fail to work. Therefore, an improved genetic algorithm (GA) is applied to minimize the MSE. Actual operational data of a chiller in HVAC are gathered to train the fuzzy inference system. Numerical experiment results validate the accuracy and efficiency of proposed fuzzy model and the improved GA algorithm.

Induction of fuzzy rules and membership functions from training examples

A new algorithm based on fuzzy inference is proposed for nonlinear mathematical programming. The characteristics of nonlinear programming are that the exact functional relationship between the objective function and the decision variables is unknown; the only information to be utilized about it is described in terms of If-Then fuzzy inference rules. Thus, a neuron-fuzzy learning algorithm is adopted to train and learn these fuzzy inference rules so as to determine an approximating function for the objective function. Finally, the proposed theoretical algorithm is applied to a nonlinear programming example and the simulation results are satisfactory.

This paper presents an application of fuzzy logic technique to quantify the equipment voltage sag immunity level. It describes the fuzzy sets and IF-THEN inference rules involved in a process of providing an equipment immunity factor based on equipment voltage tolerance test data. Typical voltage tolerance envelopes, such as IEEE Std. 446 and CBEMA curves, are exploited in defining the fuzzy membership functions corresponding to various classes of voltage sags severity and durations. Using the equipment voltage sag tolerance test data, the proposed fuzzy reasoning process provides a single factor that represents the relative immunity level of the tested equipment. Previous voltage tolerance data of personal computers are used to test the proposed method and the immunity factors distributions of the tested equipment using various fuzzy rules are presented.

In this paper, a fuzzy inference method is proposed for short-term load forecasting. A new technique of parallel tabu search is used to deal with one-day ahead prediction of daily maximum loads. This paper focuses on a fuzzy inference approach due to good understanding of the nonlinear behavior of the model. Fuzzy rules help power system operators to explain their experiences and rules in an intuitive sense. In this paper, parallel tabu search is used to globally optimize the number and location of the fuzzy membership functions. It considers two strategies of the neighborhood decomposition and multiple tabu lengths so that computational efficiency and solution accuracy are improved. The proposed method makes use of the simplified fuzzy inference to alleviate computational effort for calculating the fuzzy membership functions of the output variables. The effectiveness of the proposed method is demonstrated with real data of Chubu Electric Power Company.

Hot words have been widely applied to reflect social opinion in microblogs. Many researchers introduce hard computing techniques to evaluate different trends of hot words, but these methods may result in biased prediction due to inaccurate classification. In this paper, the temporal patterns of hot words are introduced based on fuzzy time series theory, which uses the soft computing method to improve accuracy of classification. Fuzzy membership functions are applied to determine fuzzy sets, which increase flexibility and diversity of time series classification schemes. Based on fuzzy inference rules, specific trends of time series values are schemed to enhance accuracy of time series prediction. Compared with traditional method of time series prediction, experimental results show that our algorithm performs well as for capturing the rise and fall trends and achieving higher accuracy of time series prediction of hot words in microblog.

Look-up decisions tables are favorites in fuzzy control when a complex algorithm of fuzzy rules inference is an impediment for a real time application. The control values of look-up tables are fuzzy singletons in finite number. It is difficult to obtain the best fuzzy control performance in these conditions. The look-up tables can be assimilated to sparse fuzzy rule bases. A linear interpolation method applied in a look-up decision table increase to a large number the fuzzy control values. In this way the fuzzy control performance can be improved. A level fuzzy control of three-tank system is implemented to validate the proposed method.

A new fuzzy inference model, SIRMs (Single Input Rule Modules) Connected Fuzzy Inference Model, is proposed for plural input fuzzy control. For each input item, an importance degree is defined and single input fuzzy rule module is constructed. The importance degrees control the roles of the input items in systems. The model output is obtained by the summation of the products of the importance degree and the fuzzy inference result of each SIRM. The proposed model needs both very few rules and parameters, and the rules can be designed much easier. The new model is first applied to typical secondorder lag systems. The simulation results show that the proposed model can largely improve the control performance compared with that of the conventional fuzzy inference model. The tuning algorithm is then given based on the gradient descent method and used to adjust the parameters of the proposed model for identifying 4-input 1-output nonlinear functions. The identification results indicate that the proposed model also has the ability to identify nonlinear systems.

To construction effective simulation meta-models for complex physical simulation system, the “curse of dimension” and the “uncertain and imprecise information” problems have to be addressed firstly. Although simulation meta-models based on neural networks can obtain well performance, the fuzzy inference mechanism of domain expert for practical application problems cannot be simulated. Thus, some prediction results may be contradicted with that of the actual physical systems. Aim at these problems, a novelty selective ensemble (SEN) simulation meta-modeling approach based on multiple kernel feature extraction and fuzzy inference modeling is proposed in this paper. A new ensemble construction method based on multiple candidate kernel latent features is used to produce candidate training sub-samples. Candidate sub-models based on Mamdani's fuzzy inference are constructed with these training sub-samples. Brand and bound (BB) and adaptive weighting fusion (AWF) algorithms are used to select and combine the ensemble sub-models to obtain final SEN simulation meta-model. Simulate results based on synthetic data show that the proposed approach is effective.