Professional Documents
Culture Documents
Project Guide
Mr. Sudarshan
Assistant Professor
Dept. of ECE
BNMIT, Bengaluru
Literature Survey
Reference Description Limitation Or Gap
Remaining Useful Life In this paper, a multivariate The current model just selects two
Prediction for a Machine with degradation modeling approach based typical BDLMs, linear growth
Multiple Dependent Features on the Bayesian dynamic linear model model and seasonal factors model.
Based on Bayesian Dynamic (BDLM) is proposed to calculate the In the future, more types of BDLM
Linear Model and Copulas RULs of degradation features, and the should be investigated.
Copula function is employed to capture No scope for non-linearity in
Date added to IEEE Access, the dependence among RUL degradation process.
August 4, 2017, distributions.
Literature Survey
Reference Description Limitation Or Gap
Battery remaining useful life In this paper, an improved method is The algorithm uses a non-linear
prediction algorithm based on proposed by using support vector exponential model, which may
support vector regression and regression-unscented particle filter show a certain deviation at
unscented particle filter (SVR-UPF), which increases the extreme values .Future works
accuracy of the RUL prediction results. include changing the regression
Date Added to IEEE Xplore: 15 Firstly, an exponential model is algorithm in re-sampling process
August 2016 adopted to approximately express the and finding a better degeneration
degeneration of battery capacity. model to imitate the evolution of
Secondly, a novel SVR-UPF method is capacity.
presented to solve the degeneracy
phenomenon of the UPF algorithm,
and then it is applied to predict the
battery RUL.
Reference Description Limitations / Gap
A New Method Based on This paper proposes a new method The limitation is that the model
Stochastic Process Models for based on stochastic process parameters need to be initialized
Machine Remaining Useful Life models for machine RUL using large numbers of available
Prediction prediction. First, a new stochastic measurements that are hard to be
process model is constructed acquired in real applications.
IEEE TRANSACTIONS ON considering the multiple variability MLE is used to initialize the
INSTRUMENTATION AND MEASUREMENT,
VOL. 65, NO. 12, DECEMBER 2016
sources of machine stochastic parameters.
degradation processes Accelerated degradation alters
simultaneously. Then the Kalman degradation mechanism.
particle filtering algorithm is used
to estimate the system states and
predict the RUL.
Run ML
Procure data & Suggest class Store the data
algorithm to
pre process based on RUL for future use
find RUL
RUL Classes,
Data
Data collection Data Analysis Data
Cleaning/wrangling
Visualization
Supervised
Learning
Applying ML Splitting Feature
Algorithms Training Dataset Engineering
Unsupervised
Learning
Selecting the
model
Comparing
Optimized Output
Data visualization of the various sensor outputs plot of all the sensor data
• OLS is the method used to find the simple linear regression of a set of data.
• In statistics, ordinary least squares are a type of linear least squares method for estimating the
unknown parameters in a linear regression model.
• Before training the model we first know about the importance of the
feature such as which feature is more useful.
• Below figure show the chi2 test scores of the different features
used in this project, the scores are in descending order the variables
which is more important at top and so on.
• Regression algorithm similar to SVM
• In SVR we try to fit the error within a certain threshold
SVR Result
➢ Random forests or random decision forests are an Ensemble learning method Classification /
regression by constructing a multitude of decision trees at training time and outputting the class that is
the mode of the classes (classification) or mean prediction (regression) of the individual trees.
➢ Random decision forests correct for decision trees' habit of Over Fitting.
❑ Figure shows the relation between the x (Actual value
of X_test i.e y_test) and y (predicted value of X_test).
The word ‘stochastic‘ means a system or a process that is linked with a random probability.
Gradient Descent can be described as an iterative method which is used to find the values of the parameters of a
function that minimizes the cost function as much as possible.
Thus in SGD, we find out the gradient of the cost function of a single example at each iteration instead of the sum
of the gradient of the cost function of all the examples.
Path taken by
Stochastic
Gradient Descent
In this sequential model we use the different number of epochs (200, 300 and 2000) and batch size (100, 200 and 900)
and checks the performance of the model. In the model two activation function Sigmoidal and Rectifier function is
used, the learning rate is 0.001 and the optimizer is Stochastic Gradient Descent (SGD).
By viewing this plot, we say that the performance of the model is good and it is observed that the accuracy of
the model is very good if the remaining useful life of any engine exceeds the value of 200 life cycles.
We get a huge list of RULs, the sample output is shown here. 255 [190.0] [-65.0]
We see that the accuracy is better using SGD than other 254 [198.0] [-56.0]
algorithms. 253 [186.0] [-67.0]
252 [227.0] [-25.0]
251 [195.0] [-56.0]
250 [192.0] [-58.0]
Final Result
A breakthrough in machine learning would be worth
ten Microsofts
-Bill Gates