# machine-failure-detection

**Repository Path**: zhengkun110/machine-failure-detection

## Basic Information

- **Project Name**: machine-failure-detection
- **Description**: PCA and DBSCAN based anomaly and outlier detection method for time series data.
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-06-05
- **Last Updated**: 2021-07-13

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Predictive-Maintance-Model

A requirement to implement a degradation model for an industrial machine and predict the failures beforehand.
Malfunctioning of machines are captured here as anomalies and failures and its related data are captured here as outliers

### Dependencies

- numpy
- scikit-learn > 0.19.1
- pandas > 0.20.3

### Dataset

pickel files of the dataset: https://www.dropbox.com/s/jt0nsqsmqxm8wz4/pickle.rar?dl=0 

### Dataset structure (Time Synchronized)

![Screenshot](screenshots/dataset_structure.PNG)

### Architecture

![Screenshot](screenshots/current_work.PNG)

### Results of anomaly and outlier detection

![Screenshot](screenshots/results_1.PNG)
![Screenshot](screenshots/results_2.PNG)

### Degradation Model

The degradation model for remaining useful life estimation can be found [here](https://github.com/LahiruJayasinghe/RUL-Net)