Mathematical Method of Artificial Neural Networks in Aircraft Maintenance, Repair and Overhaul (original) (raw)
Related papers
Application of Artificial Neural Networks in Aircraft Maintenance, Repair and Overhaul Solutions
Computing Research Repository, 2010
This paper reviews application of Artificial Neural Networks in Aircraft Maintenance, Repair and Overhaul (MRO). MRO solutions are designed to facilitate the authoring and delivery of maintenance and repair information to the line maintenance technicians who need to improve aircraft repair turn around time, optimize the efficiency and consistency of fleet maintenance and ensure regulatory compliance. The technical complexity of
Regression and Classification Model Based Predictive Maintenance of Aircrafts Using Neural Network
International Journal of Innovative Research in Computer Science & Technology, 2022
One of the key objectives of today's businesses and mills is to predict machine problems. Failures must be avoided, because downtimes represent expensive expenses and a loss of productivity. This is why the number of remaining cycles (RULs) until the failure occurs is vital in machine maintenance. The estimations of the RUL should be based on earlier observations, whenever possible under the same conditions. In the research of RUL estimates, the creation of systems that monitor current equipment conditions is becoming crucial. I employed Long Short Term Memory (LSTM) in my project to determine an aircraft's remaining usable lives. The aircraft's functioning condition is also forecast. The former is done by a regression method, using a classification methodology predicted by working circumstances. In order to estimate operating conditions and remaining usable life of the aircraft, data utilized for LSTM models training are derived from 21 aircraft sensor readings located ...
Neural networks for aeronautical components maintenance and management
Aeronautic systems maintenance methodologies and management criteria for the substitution of components are continuously evolving. At first the so called hard time management procedures were utilized for establishing time based components substitutions. Even if safety conditions appeared conservative, costs grew up, both for the anticipated substitution of still good components, and for the stocking critic conditions. Operational reliability techniques were therefore introduced in order to permit components constant monitoring for evaluating the effective capacity to ensure the mission. Those techniques are statistically based. The paper attempts to demonstrate existing possibilities for the application in reliability of neural networks instead of statistical more traditional tools in order to preview the number of faults that might verify on aeronautical on board components in a certain time lapse.
International Journal for Research in Applied Science and Engineering Technology (IJRASET), 2022
Anticipating aircraft breakdowns is one of Industry 4.0's primary goals. It's critical to be able to prevent failures since downtime costs money and results in a loss of productivity. That's why it's critical for aircraft maintenance to figure out how many cycles or RULs are left till the breakdown occurs. The RUL estimates should be based on earlier observations wherever feasible under the same conditions. The research of RUL estimation is primarily centered on the creation of systems that monitor the current condition of equipment. While this topic is extensively researched, there is no single universal approach. This concept, which employs recurrent neural networks (RNN) for the predictive maintenance of the planned system, is motivated by the lack of a generic technique
Increase the aviation efficiency of UAVs using artificial neural networks
Advanced Information Systems, 2017
Purpose. It is known that the flight of the UAV is conducted by sensors that transmit the performance of the UAV and on the basis of this information is controlled on the UAV and give them the orders which are necessary to perform the task of flying UAV. and normal these faults occur during the flight of unmanned air vehicle (UAV), according to the concepts of aviation is a very critical situation that affects the completion of the mission. These faults are mainly due to failure in the sensors, which can be divided into. Flight Situation is about the flying situation of the aircraft, such as (heading, altitude, airspeed, and vertical speed and angle of attack sensors. And Flight Control Situation, this is about the flight control surfaces such as (rudder, aileron, and elevator deflection), pitch attitude, and roll attitude sensors. This paper presents an effective technique to ensure that the sensors can operate with high efficiency. Methods. Two different approaches are used in this work. The first approach is Neural Network (NN) based tool for the modeling, simulation and analysis of aircraft (SFDIA), sensors failure, detection, and identification and accommodation problem. The second approach is Neural Network trained with the (EMRAN) algorithms which is a set of conditions that decide how the (EMRAN) structure should be adapted to better suit the training data. Results. The results from the modeling process and analysis of aircraft sensors showed that the neural network based tool (SFDIA) and the (EMRAN) algorithms are able to show high-resolution results in the behavior of sensors and hence in the (UAV) behavior. Conclusions. The capabilities of (SFDIA) are a consequence of the extensive modularity of the whole simulation tool. It allows an easy change of unmanned air vehicle (UAV), dynamics and feedback control law as well as Neural Network (NN) estimators and (SFDIA) scheme. K e ywor d s : Unmanned aircraft vehicle; Sensor fault detection; Fault diagnosis; Aircraft sensors modeling and simulation.
Neural Network Diagnostics of Aircraft Parts Based on the Results of Operational Processes
Radio Electronics, Computer Science, Control
Context. The problem of synthesis of an optimal neural network model for diagnostics of aircraft parts after operational processes is considered. The object of the study is the process of synthesis of neural network diagnostic models for aircraft parts based on the results of operational processes Objective is to synthesize neural network diagnostic models of aircraft parts after operational processes with a high level of accuracy. Method. It is proposed to research the use of two approaches to the synthesis of neural network diagnostic models. So, using a system of indicators, the topology of the neural network is calculated, which will be trained using the method of Backpropagation method in the future. The second approach is based on the use of a neuroevolutionary approach, which allows for a complete synthesis of the neural network, dynamically modifying the topology of the solution in addition to the parameters. the final decisions are compared in the accuracy of work on the tr...
IEEE Access
One of the challenging problems in the case of aircraft failure is to determine the new altered dynamics of the impaired aircraft. Among various methods, neural networks and neuro-fuzzy systems can be used for high-fidelity modeling of the aircraft nonlinear dynamics with the aim of onboard applications in real-time. However, the method with better generalization capability is more preferred specifically in the case of unpredicted aircraft failures. Generalization of a network is mainly dependent on the network's parameters, the employed training algorithm, and the amount of training data. In this paper, several neural networks and local model networks are trained using different training algorithms and different amounts of training data to model the nonlinear dynamics of an impaired aircraft with damaged rudder. These networks are compared based on their generalizations to the new cases of rudder failure. The effect of using different amounts of training data on the generalization capability and performance of the networks has also been investigated. Results of this study show that both network types have good performance but neural networks generalize better to the new failure cases than local model networks. Also based on the obtained results, a significant reduction in the number of training samples could be accomplished without a considerable decrease in the network's performance and generalization. Finally, a neural network-based sensitivity analysis method is proposed which utilizes network's regression equation as an emulator for fast model evaluations, and can be used as an advisory tool for choosing safer path planning strategies.
Neural network prognostics model for industrial equipment maintenance
… Systems (HIS), 2011 …, 2011
This paper presents a new prognostics model based on neural network technique for supporting industrial maintenance decision. In this study, the probabilities of failure based on the real condition equipment are initially calculated by using logistic regression method. The failure probabilities are subsequently utilized as input for prognostics model to predict the future value of failure condition and then used to estimate remaining useful lifetime of equipment. By having a time series of predicted failure probability, the failure distribution can be generated and used in the maintenance cost model to decide the optimal time to do maintenance. The proposed prognostic model is implemented in the industrial equipment known as autoclave burner. The result from the model reveals that it can give prior warnings and indication to the maintenance department to take an appropriate decision instead of dealing with the failures while the autoclave burner is still operating. This significant contribution provides new insights into the maintenance strategy which enables the use of existing condition data from industrial equipment and prognostics approach
Failure Modeling of C-130 Turbines using Artificial Neural Networks
2021 Annual Reliability and Maintainability Symposium (RAMS), 2022
The C-130 aircraft is one of the most widely used medium transports in the world. It operates virtually everywhere, from the arctic circle to the Sahara. Operation in desert conditions, however, presents a challenge for maintenance engineers regarding preventive maintenance scheduling. Erosion caused by sand particles drastically decreases turbine blades life. Recent studies showed that Artificial Neural Network ANN algorithms have much better capability at modeling reliability and predicting failure than conventional algorithms. In this study, more than thirty years of local operational field data were used for failure rate prediction and validation using several algorithms. These include Weibull regression modeling to establish a reference, feed-forward back-propagation ANN, and radial basis neural network algorithm. Comparison between the three methods is carried out. Results show that the failure rate predicted by both the feed-forward back-propagation artificial neural network model and radial basis neural network model are closer to actual failure data than he failure rate predicted by the Weibull model. The results also give an insight into the reliability of the engine turbine under actual operating conditions, which can be used by aircraft operators for assessing system and component failures and customizing the maintenance programs recommended by the manufacturer.
Applied Mechanics and Materials, 2015
In this paper presents a new hybrid methodology to perform fault detection and classification of aircraft structures using the tool as ARTMAP-Fuzzy and Perceptron multi-layer artificial neural networks. This method is divided into two steps, the first step performed by the multi-layer Perceptron neural network, which consists in the detection of abnormalities in the structure. The second step is performed by ARTMAP-Fuzzy neural network and consists of the classification of faults structural detected in the first time. The main application of this hybrid methodology is to assist in the inspection process of aeronautical structures in order to identify and characterize flaws as well, make decision-making in order to avoid accidents or air crashes. To evaluate this method, the modeling and simulation was carried out signals from a numerical model of an aluminum beam. The results obtained by the methodology demonstrating robustness and accuracy structural flaws.