CfC for Material Science

In this repository it's presented the research I've done at MIT in collaboration with Università la Sapienza di Roma and ENI S.p.a.

In this work is explored the possibility to use a black box approach to make accurate previsions on material properties, after having trained the models on some materials datasets. In this current scenario the coding is entirely done in Python, using the Pytorch library.

The approach used to obtain those results is based on the architecture AutoEncoder, where a first block, called Encoder processes the input datas and project them in a Rn latent sub-space and the Decoder processes the latent information to output predictions.

In my work the Encoder is composed by a series of layer of LSTM+CfC+Multi Head Attention; the Decoder is a Fully Connected Network.

To provide an Uncertainty handling in case of noisy or multiple entries for the same inputs, the model can also use a Variational Approach to calcolate the Mean and the Variance of the Output.
In this case the Decoder is composed by 2 parallel Fully Connected Network with the same structure that output simultaniously Mean and Variance.

Graphical Representation of the Network

The Main Structure of the Network is shown below.

Those Two are the Simplified Diagrams of the Network in Auto-Encoder approach and Variational Auto-Encoder approach respectively

Focusing on the Encoder part, it can be seen clearly as composed by N repetitive blocks connected in series.
Each block is composed by a LSTM Layer, a CfC Layer wired with NCP policy and a Self-Attention mechanism realised using a Multi-Head Attention Layer. Each sub-block is connected in series with the previous one.
In this study each CfC block is wired using the same NCP configuration, but it could be reached further data compression reducing the Total Number of Neurons or increasing the Connection Sparsity at each sub-block subsequential connection.

As for the Encoder section, the first structure the data encounters is a LSTM Layer, a more complex version of a standard Recurrent Neural Network
This type of RNN has two different internal states:

Hidden (h)
Memory (c)

Those states can change value using a gating mechanism shown in the image below. The simultaneus presence of both hidden and cell state allows both long term and short term memory regarding the input datas.
This gives this particular architecture, the ability to better mine the structure of the data, working particularly well when a perioicity of some kind is present.
A downside of this architecture is that, having more variables, is harder to train, for this sometimes is preferred the GRU structure. In this work LSTM convergence was not a problem, so a GRU implementation wasn't needed nor explored.

After the LSTM Layer is present a CfC block. This particular structure is shown below, but it can be imagined as a RNN with time handling.

The CfCs used in this work are a particular approximation of the Liquid Time Constant (LTC), essentially they allow a better continuous transition between hidden states using time data.
Normally in a standard RNN such as GRU or LSTM the hidden states are passed from the state i to the i+1 without considering the effective distance between the entry points.
This isn't a problem in most datasets, because entries are equally spaced between each other, but in case of some unevennes in the data, the accuracy of the predictions quickly deteriorates.
Some attemps have been made using a RNN with a time depending decay, but generally the issue wasn't solved.
A more complete answer to the problem was given using a Neural ODE Network. This kind of network could better model the changing between hidden states. The price to pay in this architecture was the increased complexity and a generally longer runtime and this significantly reduced its applications.
CfC networks on the other hand, are lightweight computational-wise and are more robust to great unevennes in data and are, generally, capable of a better overall convergence and accuracy even in an equally spaced scenario when compared to LSTM and GRU.

The CfC Networks in this study have been wired not using a Fully-Connected Approach, but using the NCP policy to ensure sparsness and faster computation.
A great advantage of this kind of connection is the possibility to cut the synapses between neurons without weighting on the Optimizer. Having a wider structure but with fewer parameters to optimize, allows the network to efficiently learn complex structures in the dataset.
In the image below is shown the discussed wiring between CfC layers

To complete the Encoder Layer, after a CfC block it is present a Self Attention Mechanism. This block receive as inputs all the hidden states retrieved during the CfC pass and it weights them to extract the most important features from the sequence.
Even if it is simple, this structure significantly improved the accuracy of the network.

Lastly after the Encoder Layers, the compressed information is decoded using a Fully Connected Network. In case of noisy input data or some kind of redundace or variance in the data entries, a Variational Approach it has been developed using Two Parallel Fully Connected Network to output both Mean and Variance of the Prediction.

A complete image of the Network is shown below

Research Results

Here, in this section, are presented the model results and performance obtained with the architecture described above.
The Dataset used in the work have data entries representing the Strain Stress behaviour of different metals. The curves were obtained under different conditions, each peculiar of its own dataset. More details can be found here:

The results obtained were encouraging, the images shown below are obtained on unseen data, so the behaviour of the model it is as close to the reality as possible.

Al MultiLoad

AISI

Al-6061 Aged

Al-6061 with composition data

Laser Printed Inconel

Steel Spring Grade

Installation

Once downloaded, extract the folder on your local machine and use the package manager pip to install the required packages

$ pip install -r requirements.txt

In this current version the model libraries are portable, so no further actions are necessary.

Usage

This is a quick guide to run the script, further details are in the sections below this one.

To run the program as it is, use:

$ python run.py

In this case it will run for 500 epochs on CPU using as dataset AISI 316L.

To run it for a user specified number of epochs, use:

$ python run.py -epochs NUM_EPOCHS

To speed up the training process using the parallelization offered by GPU thanks to CUDA, use:

$ python run.py --cuda

To train on different dataset, use:

$ python run.py -dataset DATASET_NAME

The Datasets cleaned and ready to use are:

AISI A Dataset composed by 48 Strain-Stress curves at different Temperatures and Strain Rates. They are generated using Johnson and Cook Law for the Plastic Behaviour and Hooke's Law for the Elastic Behaviour of AISI 316L Steel.
AL_COMP A Dataset of Al-6061 Strain Stress curves at different Temperatures and Strain Rates. Each sample has is own composition and that is used too in the model to made better predictions.
AL_AGED A Dataset of Al-6061 Strain Stress curves taken under different Aging Temperatures and Angles (during the forging of the samples, they have been rolled, so this has caused some anysotropy in the sample. This anysotropy is assumed to be absent in the Aged Samples thanks to the reheating process).
INCONEL A Dataset composed by several Laser Printed Inconel real Stress-Strain curves taken, at different Angles due to the anysotropy of the printed samples. If you choose this dataset you may opting also for the --var option, because in this particular dataset, the inputs have high variance, so an error handling can give both better accuracy and better results interpretability.
STEEL A Dataset composed by several Steel-Spring grade Strain-Stress curves, taken under different Temperatures and Strain Rates. This particular dataset has few entry and the inputs are very noisy. Convergence is not great, but --var helps to have better results.

To see all the parameters accepted, use:

$ python run.py --help

Implementation of a Custom Dataset

In the case you want to use the provided script to train the model on your personal dataset here it is a detailed guide on how to do it:

Locate the custom folder present in dataset dataset/custom
In this folder create 2 folders named numpy and scaler
In the scaler folder there should be 2 files named in_scaler.gz and out_scaler.gz. This 2 files contains the scaling informations of the inputs and outputs. I suggest you to use my custom library to realize this quickly. A easy python implementation could be:
```
from core.utils import CustomScale 
import joblib

in_scaler = CustomScale("positive")
scaled_tensor = in_scaler.fit_transform(unscaled_tensor)
joblib.dump(in_scaler, scaler_folder_path + "in_scaler.gz")
```
Be aware that the fit_transform method takes a numpy array with NxM shape. The array should be arranged to have the various input entries on the rows. Same thing can be done for the out scaler.

In the numpy folder there should be test_dt.npy, test_y.npy, test_x.npy, train_dt.npy, train_y.npy, train_x.npy, dataset_specs.json. To create the npy array you can use my custom library. A easy python implementation could be:

from core.utils import SlidingWindowLoader
import numpy as np

sliding_x_container = SlidingWindowLoader(X,window = window,padding = padding,cpu = True)
X_sequence = sliding_x_container.out_numpy()
np.save(X_sequence, path_numpy_folder+ "train_x.npy")

# X -> NxM numpy array containing for example your train input datas. 
#
# window -> lenght of the window you want to use in the model (CfC is 
# based on RNN, 
# so a moving window approach is REQUIRED)
#
# padding -> allows zero-padding at the beginning of the sequence. 
# It is suitable for datas that begins with zero (for example Strain- 
# Stress curves), 
# but for others such as Weather Data it is not, so in this case it 
# should be set as False.
#
# cpu -> set True, if False it puts the tensors on GPU, but it is an old 
# implementation.

Mind that CfC models uses also time in the form of timespans (Ti - Ti-1), so to generate the sequence in case of zero padding you have to be cautious. In the research it was used this method and it gave good results:

from core.utils import adjust_time
T = np.vstack((np.arange(0,window)[:,np.newaxis],T- T.min()+window))
dT = adjust_time(T)
sliding_dT_container = SlidingWindowLoader(dT,window = window,padding = False,cpu = True)
dT_sequence = sliding_dT_container.out_numpy()
np.save(dT_sequence, path_numpy_folder + "train_dt.npy")

# T -> your train time vector Nx1 (T1,T2,T3,...,Tn)

So essentially the Time vector was expanded inserting a sequence of T entries spaced by one, moving every other entry by a window value.

adjust_time is just a function that performs Ti - Ti-1 on every couple of elements in the array to generate a dT tensor.

With this trick for the zero-padded part of the inputs the dT tensor it will be a sequence of 1, after the zero padding the dT and inputs will be untouched.
This trick allows you to use the first T sequence of input data that would be, otherwise, lost.
If padding is False in the input sequence generation, the time trick doesn't need to be performed.

In the case of multiple curves (like in every datasets used in this research). Assuming you have N curves containing the train data in some .cvs files.

import os
from os.path import join, isfile, listdir
raw_in_list_train = []
raw_out_list_train = []
dt_list_train = []
curves_files = [f for f in listdir(path_train_curves) if isfile(join(path_train_curves, f))]
for curve in curves_files:
    raw = pd.read_csv(path_train_curves + curve)

    time = #your way to extract time data (mind it should be a column vector)
    time = np.vstack((np.arange(0,window)[:,np.newaxis],time-time.min()+window))
    d_time = adjust_time(time)
    dt_container = SlidingWindowLoader(d_time,window = lookback,padding = False,cpu = True)
    dt = dt_container.out_numpy()

    raw_in_temp = #your way to extract input data (mind it should be a column vector)
    raw_out_temp = #your way to extract output data (mind it should be a column vector)
    raw_in_temp = in_scaler.fit_transform(raw_in_temp)   
    # normalization it helps a faster and better convergence
    raw_out_temp = out_scaler.fit_transform(raw_out_temp)
    # normalization it helps a faster and better convergence
    raw_in_container = SlidingWindowLoader(raw_in_temp,window = lookback,padding = True,cpu = True)
    raw_in = raw_in_container.out_numpy()
    raw_out = raw_out_temp

    raw_in_list_test.append(raw_in)
    raw_out_list_test.append(raw_out)
    dt_list_test.append(dt)

x_train = np.concatenate(raw_in_list_train,axis = 0)
y_train = np.concatenate(raw_out_list_train,axis = 0)
dt_train = np.concatenate(dt_list_train,axis = 0)
np.save(path_numpy_folder + "train_x.npy", x_train)
np.save(path_numpy_folder + "train_y.npy", y_train)
np.save(path_numpy_folder + "train_dt.npy", dt_train)

Lastly in the numpy folder you need to create the dataset_specs.json, this would be used in the results plotting. It is a file with a very simple dictionary structure.
Let's dive in in every key-value pair:
- train_curves : This is the number of train curves you used as int
- test_curves : This is the number of test curves you used as int
- input_names: It should be a list of string in the format "Name Entry"+ " " + "(Measure unit used without spacing)"
- output_names: It should be a list of string in the format "Name Entry"+ " " + "(Measure unit used without spacing)"
- title: It should be a string containing the Name you want displayed as a title on the plot
Here there is an example:
```
{
 "train_curves": 100,
 "test_curves": 4,
 "valid_curves": 33,
 "input_names": [
     "Strain (%)",
     "Temp (\u00b0C)",
     "LogSR (s-1)"
 ],
 "output_names": [
     "Stress (MPa)"
 ],
 "title": "AISI 316L"
}
```
In this case the Dataset is AISI, the input data are: Strain, Temp and LogSR and their Measure Units are %, °C and s-1 respectively, meanwhile the output data is Stress and its Measure Unit is MPa
Once you have created the dataset inside the custom folder, you can run the script, use:
```
$ python run.py -dataset CUSTOM
```

Hyperparameters Tuning and Meaning

To manually change the hyperparameters you need to modify the config_model.json located in the main folder.
Essentially the config file has 3 sections: Encoder, Decoder, Training.
Here it is a guide that explain what each entry does:

Encoder
- total_neurons: Number of Total Neurons on the CfC and LSTM layers, it can be virtually any number.
  Do not set a too large value, because the memory needed will increase rapidly and it will slow down the training process making the convergence harder.
  CfC are very efficient so it is really not needed a very wide network.
  So 25,30,35 are good values and it can give a very good performance on a lot of scenarios.
- motor_neurons: Number of Final Neurons of the CfC Layer.
  Data compression is good in the Neural Network applications. A very high number it may capture more features but it can slow down the training, on the other hand a low value it may be not sufficient to capture all the features and the accuracy it will be low.
  Compromise here is the key to obtain good results.
  Mind also that motor_neurons are included in the total_neurons value, so a good rule of thumb it should be motor_neurons < total_neurons/3
- sparsity: This is the main feature of CfC with NCP policy, read the original paper to understand a little more about it. Allowed value are in the range 0-1, a low value it means the network is pratically fully connected, a highy value it means the network has some not connected neurons(and it is here that the magic happens).
  A good starting value could be 0.5.
- n_layers_cfc: This is the number of LSTM-CfC-Multi Head Attention layers present in the Encoder part.
  One is good enought in most application, if you increase the layers the network it will became more complex, but training will be both slower and harder.
- key_size, query_size, value_size: They HAVE to be equal to motor_neurons value.
- heads: It is the number of Heads the Multi Head Attention Module should have. Read the original paper for more details.
  This number it needs to be a divisor of motor_neurons in order to work.
- dropout: It is the dropout probability, read the documentation on Pytorch website for more informations.
  Allowed values are in 0-1 range, with lower value no dropout will happen and little counter-overfitting will happen, with high value this fenomenom will increase in frequency, but the training will be harder.
- symmetric: LEAVE ALWAYS true
Decoder
- layers_fcn: Layers of Fully Connected Network in the Decoder part.
  Allowed values starts from 2, but as a rule of thumb a good starting point is 5 or 6.
- width_fcn: Width of Fully Connected Network in the Decoder part.
  Allowed values starts from 1 (trivial case), but as a rule of thumb a good starting point is 16 or 32.
- decay_fcn: This control the change in width of the FCN for every layer.
  For example having a decay set to 2 and starting with a 64 width the progression will be:
  64 -> 32 -> 16 -> 8 -> 4 ...
  It is useful because it compresses information in the Decoder part.
  Be sure the decay and the number of layers are compatible with the starting width of the FCN network.
- norm: It is a flag that control the presence or not of a Normalization Layer in each FCN layer, read the documentation on Pytorch website for more informations about it.
  Allowed values are false, true.
  With False is Disabled and with True is Enabled.
- variational : It is is a flag that enables the Variational Approach.
  Allowed values are false, true.
  With False is Disabled and with True is Enabled.
- activation: It specifies the activation functions on the FCN layers.
  Allowed values are:
  - relu: LeakyReLU activation function
  - sigmoid: Sigmoid activation function
  - hardtanh: HardTanh activation function
Training
- lr: It is the step the Optimizing Function will use to perform Gradient Descend during Training.
  A good starting value could be 5e-3.
- gamma: It is the value controlling the Exponential Decay of lr each epoch during Training.
  It is used to speed up the training at the beginning, because it allows a greater starting lr value, but decreasing lr during each epoch it permits a better convergence overall.
  A good starting value could be 0.99.

Here it follows an example of the config_model.json template. The same template is also present in the main project folder.

{
    "config_wiring": {
        "motor_neurons": 8,
        "total_neurons": 20,
        "sparsity": 0.5,
        "n_layers_cfc": 1
    },
    "config_attn": {
        "key_size": 8,
        "query_size": 8,
        "value_size": 8,
        "heads": 2,
        "dropout": 0.0,
        "symmetric": true
    },
    "n_layers_cfc": 1,
    "motor_neurons": 8,
    "layers_fcn": 3,
    "width_fcn": 64,
    "decay_fcn": 2,
    "norm": false,
    "variational" : false,
    "activation": "sigmoid",
    "lr" : 5e-3,
    "gamma" : 0.998
}

Visualizing Results

Once you have executed the script the results are stored in the execution folder.
You will notice a new folder has just been created named results, inside there will be a child folder with a name based on your dataset selection.
Inside this folder there will be a folder named normal or var depending on the variational flag settings in the config_model.json.
Inside one of those two folder are stored the results in directory having as a name the timestamp of the script execution.

For example running at 15:30 on 02/05/23 the script with:

$ python run.py --cuda -dataset AISI

You will find the results inside:

results/aisi/var/2023_05_02_15_30/ if variational was set true
results/aisi/normal/2023_05_02_15_30/ if variational was set false

Contributing

For major changes, please open an issue first to discuss what you would like to change.

License

Apache License

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

CfC for Material Science

Index

Graphical Representation of the Network

Research Results

Installation

Usage

Implementation of a Custom Dataset

Hyperparameters Tuning and Meaning

Visualizing Results

Contributing

License

About

Releases

Packages

Languages

Name		Name	Last commit message	Last commit date
Latest commit History 107 Commits
core		core
datasets		datasets
images		images
research_results		research_results
.gitattributes		.gitattributes
README.md		README.md
config_model.json		config_model.json
requirements.txt		requirements.txt
run.py		run.py

Marcelaus98/CfC-for-Material-Science

Folders and files

Latest commit

History

Repository files navigation

CfC for Material Science

Index

Graphical Representation of the Network

Research Results

Installation

Usage

Implementation of a Custom Dataset

Hyperparameters Tuning and Meaning

Visualizing Results

Contributing

License

About

Topics

Resources

Stars

Watchers

Forks

Releases

Packages 0

Languages

Packages