Neural networks from the perspective of measurement systems (original) (raw)
Related papers
Sensor errors prediction using neural networks
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000
The features of neural networks using for increasing of an accuracy of physical quantity measurement are considered by prediction of sensor drift. The technique of data volume increasing for predicting neural network training is offered at the expense of various data types replacement for neural network training and at the expense of the separate approximating neural network using.
The development and commercial use of virtualized sensing (smooth) in the manufacturing of Polyethylene Terephthalate (PET) and sewage treatment are both covered in this paper. The major purpose of using based on an input Artificial Neural Network (ANN) to give operations with real-time estimates of the PET permeability. Additionally, the redundancy viscosity measures provided by the ANN-based soft-sensor (ANNSES) were used to compare the outcomes of the procedure fully equipped. Everything was established that the proposed ANNSES could accurately infer the polymeric viscosity, allowing for the implementation of this soft sensor in real-time system integration. Multidisciplinary modeling, ANN, & a composite method that includes a primary clustering technique are used for data from industrial wastewater operations. The combined ANN approach decreases the overfitting problem with biological systems & improves forecasting accuracy. The results show that the hybrid ANN method can be used to both explain why difficult wastewater treatment processes are nonlinear & to obtain knowledge in imbalanced datasets.
Neural Networks-based Virtual Sensors Methodology
In this work a Methodology framework for implanting Virtual Sensors using Neural Networks will be presented, including the statistical analysis techniques that can be used for studying and processing the data. The proposed Methodology is based upon Software Engineering, Knowledge-based systems and neural networks methodologies. This methodological framework includes both technical and economical feasibility to build the virtual sensors and considers important aspects as the available computational platform, historical data files, data processing requirements such as filtering, pruning, set of variables that must be selected for the best performance of the virtual sensor, etc. There are also presented the statistical consideration and the corresponding techniques for data analysis and processing. The methodology includes techniques as principal components, cluster analysis, factorial analysis, etc.
IEEE Transactions on Instrumentation and Measurement, 1998
The problem of applying the neural networks for static calibration of measuring systems and for measurand reconstruction is addressed. A multilayered neural network based method for the static calibration of this system is proposed. The functioning of the calibrated measuring system is based on three fiber-optic transducers whose static characteristics are nonmonotonic and significantly influenced by temperature. The applicability of the proposed calibration method is demonstrated in the case under consideration using synthetic and real data. The neural network is designed and implemented in a general purpose microcontroller. In comparison with the spline-based method of calibration, for the same reference data, the proposed method allows obtention of a better quality of calibration and, most important, when calibrated, the multilayered neural network does not require the measurement of temperature for pressure reconstruction.
A neural network based approach for measurement dynamics compensation
Applied Artificial Intelligence, 2002
In this article a task-oriented neural network (NN) solution is proposed for the problem of article recovering real process outputs from available distorted measurements. It is shown that a neural network can be used as approximator of inverted ® rst-order measurement dynamics with and without time delay. The trained NN is connected in series with the sensor, resulting in an identity mapping between the inputs and the outputs of the composed system. In this way the network acts as a software mechanism to compensate for the existing dynamics of the whole measurement system and recover the actual process output. For those cases where changes in the measurement system occur, a multiple concurrent-NN recovering scheme is proposed. This requires a periodical path-® nding calibration to be performed. A procedure for such a calibration purpose has also been developed, implemented, and tested. It is shown that it brings adequate robustness to the overall compensation scheme. Results showing the performance of both the NN compensator and the calibration procedure are presented for closed loop system operation.
A neural network approach to fluid quantity measurement in dynamic environments
Mechatronics, 2011
Sloshing causes liquid to fluctuate, making accurate level readings difficult to obtain. In this paper, a measurement system has been described that can accurately determine fluid quantity in the presence of slosh. The measurement system uses a single-tube capacitive sensor to obtain instantaneous level of the fluid surface. A neural network based classification technique has been applied to predict the actual quantity of the fluid under sloshing conditions. Effects of temperature variations and contamination on the capacitive sensor have been discussed and it is proposed that these effects can also be eliminated with the proposed neural network based classification system. To examine the performance of the classification system, many field trials were carried out on a running vehicle at various tank volume levels that range from 5 L to 50 L. The paper also investigates the effectiveness of signal enhancement on the neural network based signal classification system. Signal enhancement is performed using selected signal smoothing functions such Moving Mean, Moving Median, and Wavelet filters. Results obtained from the investigation are compared with traditionally used statistical averaging methods, and it proved that the neural network based measurement system can produce highly accurate fluid quantity measurements in a dynamic environment. The approach demonstrated herein will enable a wide range of fluid quantity measurement applications in the fields of automotive, naval and aviation industries to produce accurate fluid level readings.
Neural network based sensor array signal processing
1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems (Cat. No.96TH8242), 2000
An autoassociative memory using neural networks is proposed for sensor failure detection and correction. A classical approach to sensor failure detection and correction relies upon complex models of physical systems; however, a neural network approach can be used to represent systems through training for which mathematical models can not be formulated. In such cases. a neural network autoassociative memo y can be used to predict sensor outputs. Differences between measured sensor outputs and sensor outputs estimated by the autoassociative memory can be used to identib .faulty sensors. Median filtering or other signal processing schemes may then be used to correct faulty sensor outputs. This technique can be used to process data from MEMS (Micro Electromechanical svstems) or other sensor arrays.