Projects / Programmes
NEURAL NETWORKS FOR DETERMINATION OF POLYMER CREEP RESPONSE AT DIFFERENT TEMPERATURES
| Code |
Science |
Field |
Subfield |
| 2.05.03 |
Engineering sciences and technologies |
Mechanics |
Numerical modelling |
| Code |
Science |
Field |
| T390 |
Technological sciences |
Polymer technology, biopolymers |
| Code |
Science |
Field |
| 2.03 |
Engineering and Technology |
Mechanical engineering |
composite, temperature dependence, polymer matrix, structural health monitoring, neural network
Researchers (1)
| no. |
Code |
Name and surname |
Research area |
Role |
Period |
No. of publicationsNo. of publications |
| 1. |
33907 |
PhD Alexandra Aulova |
Mechanics |
Head |
2019 - 2021 |
95 |
Organisations (1)
Abstract
High performance composites (HPC) are a combination of two distinct components namely, fibers and resin, which exhibits completely different properties from fiber and resin. The new (composite) material shows high strength and stiffness and low weight and is stronger alternative to traditional manufacturing materials including steel and aluminum.
The advantages of HPC materials are accompanied by some challenges related to their implementation into products. The main issues are related to complex mechanical analysis of materials and parts; lack of reliable methods for fatigue and failure prediction and time, temperature and moisture dependent effects. All these factors result in very demanding prediction of failure of the HPC materials and products. Additional problems are associated with increased use of thermoplastic matrices (PES, PEEK, PE, etc.) in composites, since they are more sensitive to temperature and humidity changes compared to conventional crosslinked matrix (e.g. epoxy).
The structural health monitoring (SHM) systems are used, among others, to measure response of structures made from composite materials. Signal from such system is comprised of two signals: one resulting from change in the geometry (cracks and delaminations), the other coming from change in matrix material properties due to temperature and humidity. In order to distinguish between geometry and matrix material related changes in the response signal of a complex and even noisy signal, one needs a robust tool. This tool should be able to solve in a real time the problem interrelating excitation, material properties (time-, temperature- and humidity-dependent) and structure response. Analytical solution interrelating these factors for a complex geometry and custom excitations does not exist. Numerical solution applied to the complex geometry in presence of noise becomes merely computationally impossible in the real time.
That is why, I am proposing within this project to utilize a Multilayer Perceptron Neural Network (MLP NN) for determination of the polymer matrix material creep response exposed to different temperatures. The project aims at modeling behavior of polymer material under ramp and harmonic stress loading and influence of the temperature.
Artificially generated data will allow wide set of investigations to address various practical questions, such as effect of data acquisition rate, frequency and amplitude of dynamic loading, noise level effect, effect of number of training data, effect of temperature on the performance of neural network method. Substantial experience of the researcher in determination of temperature dependent mechanical properties will allow refinement and validation of the NN model using experimental creep data.
Significance for science
With entrance of high performance composites (especially thermoplastic-based composites) on the market of structural engineering it is very important to take into account their temperature and humidity dependence for real-time structural health monitoring and reliable long-term life prediction. Even though the currently used structural health monitoring systems are equipped with soft computing methods and are good at detecting damages related to structural integrity of composite materials they do not take into account effect of environmental conditions. Very limited number of publications has addressed it and only for the civil construction applications. However, temperature significantly changes response of the structure as a whole, which may lead to incorrect conclusions by the system of structural monitoring.
Therefore, the long-term plan is to implement the model as an additional block to the existing real-time health monitoring systems. The neural network block with incorporated temperature dependence of the matrix material (measured in the laboratory conditions) will be trained on the data obtained from the real structure. During application the neural network system will “filter out” of the structure response signal the effects of temperature on the polymer matrix in different temperature conditions. This improved real-time health monitoring system will not be limited to the complex geometry of a structure. Such system will provide the support needed for the existing structural health monitoring systems to reliably estimate status of high performance composite structures.
The proposed project will provide essential for further development information on the performance of chosen neural network and effects of data acquisition rate, noise level, temperature, vibration frequency and amplitude, neural network topology and training parameters. These effects will be investigated using the advantage of artificially generated data based on known closed-form solutions. Validation on the real measurements data will show feasibility of the proposed model.
Additionally, model developed within this project will provide an opportunity to predict behavior of the material at temperatures that were not included in the training data. This will make the whole process of long-term characterization of time-dependent materials faster, cheaper and easier.
Significance for the country
With entrance of high performance composites (especially thermoplastic-based composites) on the market of structural engineering it is very important to take into account their temperature and humidity dependence for real-time structural health monitoring and reliable long-term life prediction. Even though the currently used structural health monitoring systems are equipped with soft computing methods and are good at detecting damages related to structural integrity of composite materials they do not take into account effect of environmental conditions. Very limited number of publications has addressed it and only for the civil construction applications. However, temperature significantly changes response of the structure as a whole, which may lead to incorrect conclusions by the system of structural monitoring.
Therefore, the long-term plan is to implement the model as an additional block to the existing real-time health monitoring systems. The neural network block with incorporated temperature dependence of the matrix material (measured in the laboratory conditions) will be trained on the data obtained from the real structure. During application the neural network system will “filter out” of the structure response signal the effects of temperature on the polymer matrix in different temperature conditions. This improved real-time health monitoring system will not be limited to the complex geometry of a structure. Such system will provide the support needed for the existing structural health monitoring systems to reliably estimate status of high performance composite structures.
The proposed project will provide essential for further development information on the performance of chosen neural network and effects of data acquisition rate, noise level, temperature, vibration frequency and amplitude, neural network topology and training parameters. These effects will be investigated using the advantage of artificially generated data based on known closed-form solutions. Validation on the real measurements data will show feasibility of the proposed model.
Additionally, model developed within this project will provide an opportunity to predict behavior of the material at temperatures that were not included in the training data. This will make the whole process of long-term characterization of time-dependent materials faster, cheaper and easier.
