Predictive Maintenance of Turbofan Engine

Using time series data and asking RNN ‘When does the next fault occur ?’

Image for post

Predictive maintenance is very important for manufacturers as well as the maintainers, which lowers maintenance cost, extend equipment life, reduce downtime and improve production quality by addressing problems before they cause equipment failures.

“Predictive maintenance techniques are designed to help determine the condition of in-service equipment in order to estimate when maintenance should be performed” — source Wikipedia

_In this post, I would like to demonstrate that the use of __RNN(Recurrent Neural Network)/LSTM(Long Short Term Memory) __architecture is not only __more accurate but it performs better in classifying the results accurately __when compared to the previous __CNN (Convolution Neural Network) _approach, written by Marco Cerliani (read here).

Dataset

This post uses the C-MAPSS datasetfor the predictive maintenance of the Turbofan Engine. Here the challenge is to determine the **Remaining Useful Life (RUL) **until next fault that occur in the engine.

The dataset can be found (here), here’s a brief on the dataset,

“The engine is operating normally at the start of each time series, and develops a fault at some point during the series.

In the training set, the fault grows in magnitude until system failure.

In the test set, the time series ends some time prior to system failure.

The following are the conditions of the engine that are used in the training of the model

Train trjectories: 100

Test trajectories: 100

Conditions: ONE (Sea Level)

Fault Modes: ONE (HPC Degradation)

Understanding the Dataset

Once we load the dataset, we obtain the time series data of 100 engines that contains the operational settings and sensor readings of each 100 engines with different senarios where the fault occurs and a total of 20631 training examples. To illustrate, below are the first 5 training examples of our training dataset.

train_df.head()

Image for post

Fig 1 : Training Data

To further understand the data given, (see Fig 2) describes that for a given engine how many cycles are left before the next fault occurs.

Example 1 : Engine id number 69 (farthest left) approximately has 360 cycles remaining before fault.

Example 2 : Engine id number 39 (farthest right) approximately has 110 cycles remaining before fault.

train_df.id.value_counts().plot.bar()

Image for post

Fig 2: Engine with their respective Remaining Useful Cycles until fault

The following (Fig3 and Fig 4) are time series data for engine whose id is 69,

engine_id = train_df[train_df['id'] == 69]

ax1 = engine_id[train_df.columns[2:]].plot(subplots=True, sharex=True, figsize=(20,30))

Image for post

Fig 3: Time series readings of Operational setting 1,2 and 3 and sensors reading of s2 up until s7

Image for post

Fig 4: Time series readings for the sensors s8 up until s20

*The images (fig2, fig 3 and fig4) are obtained by using the source code from GitHub Notebook (here), by Marco Cerliani.

#predictive-analytics #deep-learning #deep learning

What is GEEK

Buddha Community

Predictive Maintenance of Turbofan Engine
Rahim Makhani

Rahim Makhani

1622435294

Website Support & Maintenance Service | Web Maintenance Company In India

The performance of the website leaves a major impact on the customer’s usage. As we all know the importance of the website in business and the effects it creates on the customers who visit your website.

Web performance is important for accessibility and also for another website that serves the goal of an organization or business. The good or bad performance of a website indirectly relates to the user experience as well as the overall performance of your business. This is why the maintenance of the website is a major thing to consider.

For website maintenance services you must contact Nevina Infotech that is the best company for website maintenance and services and has dedicated developers who will solve all the bugs from your website and improve the performance of your website.

#website maintenance services #website support and maintenance #website maintenance support #website maintenance packages #website maintenance company #website maintenance plans

Rahim Makhani

Rahim Makhani

1620968589

Get a Bug Free and smooth website with website Maintenance

Having a website for your own firm or business is very important as it can benefit you in many ways like your users can get 24/7 service from your company, you can exchange your information, it can help you to expand your business in the market. One must also maintain their website to keep it bug free and updated.

Your website should be bug free because if there is any bug in your website it will slow down the performance of it and will not even work properly if this happens then there are chances that you may lose your customers.

Are you searching for a company that can provide you with website support and maintenance? Nevina Infotech is the best company that can help you with the maintenance and support, as we have enthusiastic web app developers who can help you to maintain your website.

#website maintenance services #website support and maintenance #website maintenance support #website maintenance packages #website maintenance company #website maintenance plans

Rahim Makhani

Rahim Makhani

1621312845

Improve your mobile app with Mobile App Maintenance

Mobile apps play a vital role in today’s mobile phone industry. Without any mobile app, our smartphones will become useless. With the development of mobile apps, its maintenance is also important to run your mobile app in a better way.

To maintain the applications, mobile app maintenance services have to take care of all the aspects regarding the app. To keep your mobile app more advanced its maintenance is required.

If you want to maintain your mobile app you can select our company, Nevina Infotech, which will give you the best maintenance service for your mobile app. We have dedicated mobile app developers that will help you to fulfill your requirements.

#mobile app maintenance #android app maintenance #mobile app maintenance services #app maintenance companies #mobile app maintenance services #mobile app maintenance and support

Wanda  Huel

Wanda Huel

1603018800

Time series analysis for predictive maintenance of turbofan engines

<disclaimer: I aim to showcase the effect of different methods and choices made during model development. These effects are often shown using the test set, something which is considered (very) bad practice but helps for educational purposes.>

Welcome to another installment of the ‘Exploring NASA’s turbofan dataset’ series. This will be the third analysis on FD001, where all engines run on the same operating condition and develop the same fault.

Initially we assumed the Remaining Useful Life (RUL) of the engines to decline linearly. In my last post we re-examined this assumption by clipping any values above 125. Clipping the RUL improved the baseline linear regression by 31% (from an RMSE of 31.95 to an RMSE of 21.90). We then switched to a Support Vector Regression and squeezed out another 6% improvement for a total RMSE of 20.54.

Today, we’ll focus on time series analysis to forecast when the engines are due for maintenance. But, before getting into the time series part, we first have to recap a few processing steps. Let’s get started!

Loading data

First, we’ll import some libraries and read the data.

import numpy as np
	import pandas as pd
	import matplotlib.pyplot as plt

	from sklearn.linear_model import LinearRegression
	from sklearn.metrics import mean_squared_error, r2_score

	%matplotlib inline

define filepath to read data

dir_path = './CMAPSSData/'

## define column names for easy indexing
index_names = ['unit_nr', 'time_cycles']
setting_names = ['setting_1', 'setting_2', 'setting_3']
sensor_names = ['s_{}'.format(i) for i in range(1,22)] 
col_names = index_names + setting_names + sensor_names

## read data
train = pd.read_csv((dir_path+'train_FD001.txt'), sep='\s+', header=None, names=col_names)
test = pd.read_csv((dir_path+'test_FD001.txt'), sep='\s+', header=None, names=col_names)
y_test = pd.read_csv((dir_path+'RUL_FD001.txt'), sep='\s+', header=None, names=['RUL'])

## inspect first few rows
train.head()

#machine-learning #predictive-maintenance #timeseries #data-science #exploring-nasa-turbofan

Rahim Makhani

Rahim Makhani

1622605776

Get a Bug free and user-friendly mobile app with mobile app Maintenance

We all know the importance of mobile apps in today’s era and the changes mobile apps have made in our lives. With the help of mobile applications, our life has become so easy and fast. We can do anything with just one click.

Mobile app maintenance is also required along with using it. If your mobile app is not maintained properly it can create a bug and the performance of your mobile app can decrease in the long term so it is important to maintain your mobile app as well.

Nevina Infotech is the leading mobile app development company that can help you to get a bug-free and user-friendly mobile app and will also provide mobile app maintenance. As we have the best team of developers that can develop your app as per your requirement.

#mobile app maintenance #mobile app maintenance services #mobile application maintenance and support #app maintenance companies #mobile app maintenance costs #mobile app maintenance services