scispace - formally typeset
Search or ask a question

Performance evaluation for multi-hole probe with the aid of artificial neural network

01 Jan 2014-
TL;DR: The multi hole conical probe is extensively employed in the fluid fields for estimating the overall and static pressure and velocity of the vibrant fields and the MATLAB software is performed to assess the efficiency of the artificial neural network for various kinds of material probes.
Abstract: The multi hole conical probe is extensively employed in the fluid fields for estimating the overall and static pressure and velocity of the vibrant fields. The probe is formed by various types of materials such as aluminum, copper and stainless steel which are utilized in the wind tunnel to determine the static and total pressure of the fluid fields. Many varied material probes are engaged to assess their efficiency in execution in the concurrent surroundings at diverse Mach number situations and the yields are calculated according to displacement and stress for diverse material probes. The innovative artificial neural network is effectively employed to forecast the varied material accomplishment of the probe by making use of the LevenbergMarquette algorithm of the artificial neural network, which is applied in the artificial neural network to estimate the yields of the various material probes and the outcomes are subjected to analysis and contrast with the Conjugate Gradient with Beale (CGB) algorithm, Variable Learning Rate Gradient Descent (GDX) algorithm and Scaled Conjugate Gradient (SCG) algorithm of the artificial neural network. The MATLAB software is performed to assess the efficiency of the artificial neural network for various kinds of material probes.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: A robust calibration method for seven-hole pressure probes is presented, which can also be applied when a hole port is malfunctioning and can be easily applied to other multi-hole (including but not limited to seven- hole) pressure probes.
Abstract: Multi-hole pressure probe remains an incomparably efficient method of flow measurement due to its simplicity and convenience. An appropriate calibration method is necessary to establish the relations between flow parameters and pressure data. In this paper, a robust calibration method for seven-hole pressure probes is presented, which can also be applied when a hole port is malfunctioning. First, a seven-hole probe was designed and manufactured by 3D printing techniques, and calibration measurements were conducted with a two-degree of freedom calibration apparatus in wind tunnel. Second, theoretical expressions for static pressure coefficients of seven-hole probes were deduced, which guides the establishment of new pressure normalization method in the absence of static and total pressure. Thereafter, a calibration algorithm using the new pressure normalization method was proposed. Finally, effects of sample selection criteria, sample size, and atmospheric static pressure offset on the calibration accuracy of the new algorithm were evaluated. And the case that one port is invalid was studied. Based on the findings obtained from this study, the feasibility and robustness of the new calibration method were validated, and the method can also be easily applied to other multi-hole (including but not limited to seven-hole) pressure probes.

8 citations

Journal ArticleDOI
TL;DR: It is demonstrated that calibrating probes by implementing neural-network-based methods that have not been previously used for probe calibration can reduce the uncertainty in flow angularity by as much as 50% compared to conventional techniques.
Abstract: For measuring three components of velocity in unknown flow fields, multi-hole pressure probes possess a significant advantage. Unlike methods such as hot-wire anemometry, laser-Doppler velocimetry and particle-image velocimetry, multi-hole pressure probes can provide not only the three components of local velocity, but also static and stagnation pressures. However, multi-hole probes do require exhaustive calibration. The traditional technique for calibrating these probes is based on either look-up tables or polynomial curve fitting, but with the low cost and easy availability of powerful computing resources, neural networks are increasingly being used. Here, we explore the possibility to further reduce measurement uncertainty by implementing neural-network-based methods that have not been previously used for probe calibration, including supervised and unsupervised learning neural networks, regression models and elastic-map methods. We demonstrate that calibrating probes in this way can reduce the uncertainty in flow angularity by as much as 50% compared to conventional techniques.

7 citations

Journal ArticleDOI
TL;DR: In this article , the radial basis function (RBF) algorithm was used to link non-dimensional pressure coefficients and flow characteristics to calibrate a five-hole probe in a subsonic open-circuit wind tunnel.

2 citations

Journal ArticleDOI
23 Jan 2023-PLOS ONE
TL;DR: In this article , six typical supervised learning methods in scikit-learn library are selected for parameter adjustment at first, based on the optimal parameters, a comprehensive evaluation is conducted from four aspects: prediction accuracy, prediction efficiency, feature sensitivity and robustness on the failure of some hole port.
Abstract: Machine learning method has become a popular, convenient and efficient computing tool applied to many industries at present. Multi-hole pressure probe is an important technique widely used in flow vector measurement. It is a new attempt to integrate machine learning method into multi-hole probe measurement. In this work, six typical supervised learning methods in scikit-learn library are selected for parameter adjustment at first. Based on the optimal parameters, a comprehensive evaluation is conducted from four aspects: prediction accuracy, prediction efficiency, feature sensitivity and robustness on the failure of some hole port. As results, random forests and K-nearest neighbors’ algorithms have the better comprehensive prediction performance. Compared with the in-house traditional algorithm, the machine learning algorithms have the great advantages in the computational efficiency and the convenience of writing code. Multi-layer perceptron and support vector machines are the most time-consuming algorithms among the six algorithms. The prediction accuracy of all the algorithms is very sensitive to the features. Using the features based on the physical knowledge can obtain a high accuracy predicted results. Finally, KNN algorithm is successfully applied to field measurements on the angle of attack of a wind turbine blades. These findings provided a new reference for the application of machine learning method in multi-hole probe calibration and measurement.
TL;DR: In this paper , the authors investigate various types of assaults and different types of security mechanisms that might be applied based on the network's needs and architecture to defend against network security threats.
Abstract: - Security is an important aspect of computing and networking technology. The first and most important aspect of any network design, planning, construction, and operation is the significance of a solid security strategy. Network security is becoming increasingly critical to personal computer users, businesses, and the military. With the introduction of the internet, security has become a big problem. Many security threats were made possible by the internet's structure. Because of the ease with which intellectual property can be obtained via the internet, network security is becoming increasingly important. When an attack is sent via a network, it can take several forms. Knowing the attack mechanisms enables adequate security to evolve. Many businesses protect themselves from the internet by using of Firewalls and encryption methods are examples of security measures. On global networking infrastructures, there is a vast number of personal, commercial, military, and government information, all of which necessitates different security procedures. In this research, we attempt to investigate numerous types of assaults as well as various types of security mechanisms that might be applied based on the network's needs and architecture.
References
More filters
Journal ArticleDOI
Ozgur Kisi1
TL;DR: Four different ANN algorithms, namely, backpropagation, conjugate gradient, cascade correlation, and Levenberg–Marquardt are applied to continuous streamflow data of the North Platte River in the United States and the results are compared with each other.
Abstract: Forecasts of future events are required in many activities associated with planning and operation of the components of a water resources system. For the hydrologic component, there is a need for both short term and long term forecasts of streamflow events in order to optimize the system or to plan for future expansion or reduction. This paper presents a comparison of different artificial neural networks (ANNs) algorithms for short term daily streamflow forecasting. Four different ANN algorithms, namely, backpropagation, conjugate gradient, cascade correlation, and Levenberg–Marquardt are applied to continuous streamflow data of the North Platte River in the United States. The models are verified with untrained data. The results from the different algorithms are compared with each other. The correlation analysis was used in the study and found to be useful for determining appropriate input vectors to the ANNs.

353 citations

Journal ArticleDOI
TL;DR: In this article, a multi-hole probe (MHP) was used to measure fluctuating parts of the airflow in flight up to 20 Hz, which can be used to estimate the 3D wind vector and turbulent fluxes of heat, momentum, water vapour, etc.
Abstract: . This study deals with the problem of turbulence measurement with small remotely piloted aircraft (RPA). It shows how multi-hole probes (MHPs) can be used to measure fluctuating parts of the airflow in flight up to 20 Hz. Accurate measurement of the transient wind in the outdoor environment is needed for the estimation of the 3-D wind vector as well as turbulent fluxes of heat, momentum, water vapour, etc. In comparison to an established MHP system, experiments were done to show how developments of the system setup can improve data quality. The study includes a re-evaluation of the pneumatic tubing setup, the conversion from pressures to airspeed, the pressure transducers, and the data acquisition system. In each of these fields, the steps that were taken lead to significant improvements. A spectral analysis of airspeed data obtained in flight tests shows the capability of the system to measure atmospheric turbulence up to the desired frequency range.

62 citations

Journal ArticleDOI
TL;DR: In this paper, the tensile strength, hardening behavior, and density properties of different α-Al2O3 particle size (μm)-reinforced metal matrix composites (MMCs), produced by using stir casting process, are predicted by designing a backpropagation (BP) neural network that used gradient-descent learning algorithm.
Abstract: In this article, the tensile strength, hardening behavior, and density properties of different α-Al2O3 particle size (μm)-reinforced metal matrix composites (MMCs), produced by using stir casting process, are predicted by designing a backpropagation (BP) neural network that used gradient-descent learning algorithm. Artificial neural network (ANN) is an intelligent technique that can solve nonlinear problems by learning from the samples. Therefore, some experimental samples are prepared at first to train the ANN to provide (to estimate) tensile strength, hardening behavior, and density properties of the MMCs produced for any given α-Al2O3 particle size (μm). The most important point is that after the ANN has been trained using some experimental samples, it gives approximately correct outputs for some of the experimental inputs that have not been used in the training. First, to prepare the training and test (checking) set of the network, some results are experimentally obtained and recorded in a file on a c...

35 citations

Proceedings ArticleDOI
02 Aug 2010
TL;DR: In this paper, the authors present an algorithm for fault detection and data fusion of air-data system failures in the framework of an unmanned autonomous seaplane with a heritage of air data probe failures.
Abstract: Air-data systems (ADS) measure wind speed and direction, the loss of which requires aerodynamic forces to be estimated from inertial measurements and aircraft dynamics and performance models. The nature of ADS measurements require air-data probes be subject to the spectrum of environmental conditions. Even with designs meant to withstand harsh conditions, instances of ADS probe failure have been recorded for diverse platform types and situations. Further, since all ADS probes on a common platform are subject to the same conditions, instances of multiple simultaneous failures are not uncommon. Robust air data measurement therefore becomes a multi-sensor data-fusion problem wherein the system may be subject to failures that effect groups of like sensors, such as pitot-static probes, simultaneously. This paper presents an algorithm for fault detection and data fusion of ADS failures in the framework of an unmanned autonomous seaplane with a heritage of air-data probe failures. The fault detection scheme is based on sensor signal characterization and monitoring and on the comparison and fusion of redundant sensor measurements. A GPS/INS-driven backup will also be proposed that can be used both as an ADS diagnostic tool and to allow safe flight to an emergency landing or until air-data sensor functionality can otherwise be restored. Flight test data from two generations of unmanned seaplanes demonstrates the efficacy of the algorithm for a range of real-world failure cases with varied sensors.

32 citations

Journal ArticleDOI
TL;DR: The work presented here examines the feasibility of applying SVMs to the aerodynamic modeling field through empirical comparisons between the SVMs and the commonly used neural network technique through two practical data modeling cases.
Abstract: Aerodynamic data modeling plays an important role in aerospace and industrial fluid engineering. Support vector machines (SVMs), as a novel type of learning algorithms based on the statistical learning theory, can be used for regression problems and have been reported to perform well with promising results. The work presented here examines the feasibility of applying SVMs to the aerodynamic modeling field. Mainly, the empirical comparisons between the SVMs and the commonly used neural network technique are carried out through two practical data modeling cases – performance-prediction of a new prototype mixer for engine combustors, and calibration of a five-hole pressure probe. A CFD-based diffuser optimization design is also involved in the article, in which an SVM is used to construct a response surface and hereby to make the optimization perform on an easily computable surrogate space. The obtained simulation results in all the application cases demonstrate that SVMs are the potential options for the ch...

26 citations