Sofiane Achiche

Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: System description

This paper proposes a system for wind turbine condition monitoring using Adaptive Neuro-Fuzzy Interference Systems (ANFIS). For this purpose: (1) ANFIS normal behavior models for common Supervisory Control And Data Acquisition (SCADA) data are developed in order to detect abnormal behavior of the captured signals and indicate component malfunctions or faults using the prediction error. 33 different standard SCADA signals are used and described, for which 45 normal behavior models are developed. The performance of these models is evaluated in terms of the prediction error standard deviations to show the applicability of ANFIS models for monitoring wind turbine SCADA signals. The computational time needed for model training is compared to Neural Network (NN) models showing the strength of ANFIS in training speed. (2) For automation of fault diagnosis Fuzzy Interference Systems (FIS) are used to analyze the prediction errors for fault patterns. The outputs are both the condition of the component and a possible root cause for the anomaly. The output is generated by the aid of rules that capture the existing expert knowledge linking observed prediction error patterns to specific faults. The work is based on continuously measured wind turbine SCADA data from 18 turbines of the 2 MW class covering a period of 30 months. The system proposed in this paper shows a novelty approach with regard to the usage of ANFIS models in this context and the application of the proposed procedure to a wide range of SCADA signals. The applicability of the set up ANFIS models for anomaly detection is proved by the achieved performance of the models. In combination with the FIS the prediction errors can provide information about the condition of the monitored components. In this paper the condition monitoring system is described. Part two will entirely focus on application examples and further efficiency evaluation of the system.

Using Data-Mining Approaches for Wind Turbine Power Curve Monitoring: A Comparative Study

Four data-mining approaches for wind turbine power curve monitoring are compared. Power curve monitoring can be applied to evaluate the turbine power output and detect deviations, causing financial loss. In this research, cluster center fuzzy logic, neural network, and k-nearest neighbor models are built and their performance compared against literature. Recently developed adaptive neuro-fuzzy-interference system models are set up and their performance compared with the other models, using the same data. Literature models often neglect the influence of the ambient temperature and the wind direction. The ambient temperature can influence the power output up to 20%. Nearby obstacles can lower the power output for certain wind directions. The approaches proposed in literature and the ANFIS models are compared by using wind speed only and two additional inputs. The comparison is based on the mean absolute error, root mean squared error, mean absolute percentage error, and standard deviation using data coming from three pitch regulated turbines rating 2 MW each. The ability to highlight performance deviations is investigated by use of real measurements. The comparison shows the decrease of error rates and of the ANFIS models when taking into account the two additional inputs and the ability to detect faults earlier.

Design, modelling, simulation and integration of cyber physical systems

Presentation of a systematic classification of systems and new CPS paradigms.Analyses of literature conducted across a range of different perspectives.A systematic review of CPS-design literature was carried out, with an emphasis on the design, modelling, simulation and integration of CPS.An architectural and behavioural paradigm for CPS.Compilation of different viewpoints referring to applications at different levels of granularity. The main drivers for the development and evolution of Cyber Physical Systems (CPS) are the reduction of development costs and time along with the enhancement of the designed products. The aim of this survey paper is to provide an overview of different types of system and the associated transition process from mechatronics to CPS and cloud-based (IoT) systems. It will further consider the requirement that methodologies for CPS-design should be part of a multi-disciplinary development process within which designers should focus not only on the separate physical and computational components, but also on their integration and interaction. Challenges related to CPS-design are therefore considered in the paper from the perspectives of the physical processes, computation and integration respectively. Illustrative case studies are selected from different system levels starting with the description of the overlaying concept of Cyber Physical Production Systems (CPPSs). The analysis and evaluation of the specific properties of a sub-system using a condition monitoring system, important for the maintenance purposes, is then given for a wind turbine.

Tool wear monitoring using genetically-generated fuzzy knowledge bases

Fuzzy logic is an AI method that is being implemented in a growing number of different fields. One of these applications is tool wear monitoring. The construction of a fuzzy knowledge base from a set of experimental data by a human expert however, is a time consuming task, and hence, limits the expansion of the use of this AI method. Alternatively, the fuzzy knowledge base can be automatically constructed by a genetic algorithm from the same set of experimental data without requiring any human expert. This paper compares these two fuzzy knowledge base construction methods and the results obtained in a tool wear monitoring application.

Type-2 fuzzy tool condition monitoring system based on acoustic emission in micromilling

In this paper, a micromilling type-2 fuzzy tool condition monitoring system based on multiple AE acoustic emission signal features is proposed. The type-2 fuzzy logic system is used as not only a powerful tool to model acoustic emission signal, but also a great estimator for the ambiguities and uncertainties associated with the signal itself. Using the results of root-mean-square error estimation and the variations in the results of type-2 fuzzy modeling of all signal features, the most reliable ones are selected and integrated into cutting tool life estimation models. The obtained results show that the type-2 fuzzy tool life estimation is in accordance with the cutting tool wear state during the micromilling process. The information about uncertainty prediction of tool life is of great importance for tool condition investigation and crucial when making decisions about maintaining the machining quality.

Fuzzy decision support system knowledge base generation using a genetic algorithm

Abstract This paper presents a genetic algorithm (GA) that automatically constructs the knowledge base used by fuzzy decision support systems (FDSS). The GA produces an optimal approximation of a set of sampled data from a very small amount of input information. The main interest of this method is that it can be used to automatically generate (without the help of an expert) a fuzzy knowledge base – i.e., the fuzzy sets for premises, conclusions and the fuzzy rules. This knowledge base is composed of the minimum number of fuzzy sets and rules. This minimalist approach produces fuzzy knowledge bases that are still manageable a posteriori by a human expert for fine tuning. The GA is validated through several examples of known behaviors and, finally, applied to experimental data.

Challenges in Designing Mechatronic Systems

Development of mechatronic products is traditionally carried out by several design experts from different design domains. Performing development of mechatronic products is thus greatly challenging. ...

Experimental and fuzzy modelling analysis on dynamic cutting force in micro milling

Prediction of cutting forces is very important for the design of cutting tools and for process planning. This paper presents a fuzzy modelling method of cutting forces based on subtractive clustering. The subtractive clustering combined with the least-square algorithm identifies the fuzzy prediction model directly from the information obtained from the sensors. In the micro-milling experimental case study, four sets of cutting force data are used to generate the learning systems. The systems are tested against each other to choose the best model. The obtained results prove that the proposed solution has the capability to model the cutting force in spite of uncertainties in the micromilling process.

MAPPING SHAPE GEOMETRY AND EMOTIONS USING FUZZY LOGIC

An important aspect of artifact/product design is defining the aesthetic and emotional value. The success of a product is not only dependent on it’s functionality but also on the emotional value that it creates to its user. However, if several designers are faced with a task to create an object that would evoke a certain emotion (aggressive, soft, heavy, friendly, etc.) each would most likely interpret the emotion with a different set of geometric features and shapes. In this paper the authors propose an approach to formalize the relationship between geometric information of a 3D object and the intended emotion using fuzzy logic. To achieve this; 3D objects (shapes) created by design engineering students to match a set of words/emotions were analyzed. The authors identified geometric information as inputs of the fuzzy model and developed a set of fuzzy if/then rules to map the relationships between the fuzzy sets on each input premise and the output premise. In our case the output premise of the fuzzy logic model is the level of belonging to the design context (emotion). An evaluation of how users perceived the shapes was conducted to validate the fuzzy logic model and showed a high correlation between the fuzzy logic model and user perception.Copyright

Real/binary-like coded versus binary coded genetic algorithms to automatically generate fuzzy knowledge bases: a comparative study

Abstract Nowadays fuzzy logic is increasingly used in decision-aided systems since it offers several advantages over other traditional decision-making techniques. The fuzzy decision support systems can easily deal with incomplete and/or imprecise knowledge applied to either linear or nonlinear problems. This paper presents the implementation of a combination of a Real/Binary-Like coded Genetic Algorithm (RBLGA) and a Binary coded Genetic Algorithm (BGA) to automatically generate Fuzzy Knowledge Bases (FKB) from a set of numerical data. Both algorithms allow one to fulfill a contradictory paradigm in terms of FKB precision and simplicity (high precision generally translates into a higher level of complexity) considering a randomly generated population of potential FKBs. The RBLGA is divided into two principal coding methods: (1) a real coded genetic algorithm that maps the fuzzy sets repartition and number (which drives the number of fuzzy rules) into a set of real numbers and (2) a binary like coded genetic algorithm that deals with the fuzzy rule base relationships (a set of integers). The BGA deals with the entire FKB using a single bit string, which is called a genotype. The RBLGA uses three reproduction mechanisms, a BLX- α , a simple crossover and a fuzzy set reducer, while the BGA uses a simple crossover, a fuzzy set displacement mechanism and a rule reducer. Both GAs are tested on theoretical surfaces, a comparison study of the performances is discussed, along with the influences of some evolution criteria.