AI-Driven Predictive Maintenance Using Vibration Sensor Data

This research project benchmarks machine-learning approaches for predictive maintenance of rotating machinery using vibration signals captured from a low-cost MEMS accelerometer, aiming to detect bearing faults before they cause unplanned downtime.

Raw time-domain vibration signals are transformed into frequency-domain features (via FFT) and time-frequency features (via wavelet transform), which are then fed into and compared across several classifiers — random forest, 1D-CNN operating directly on raw signal windows, and a support vector machine — for identifying healthy versus multiple fault-severity states.

The study finds that the 1D-CNN operating on raw signals outperforms hand-engineered-feature classifiers at higher fault-severity granularity, and discusses the trade-off between model complexity and the feasibility of deploying such a model directly on an edge microcontroller for on-machine inference.

Detailed Project Description

AI-Driven Predictive Maintenance Using Vibration Sensor Data applies machine learning to a real dataset: it prepares the data, trains and evaluates a model, and exposes the trained model through a simple interface so predictions can be made on new inputs.

How It Works
1. The dataset is collected/loaded, cleaned and explored (missing values, encoding, scaling).
2. Features are engineered and the data split into training and test sets.
3. One or more models are trained and compared using accuracy, precision/recall, F1 or RMSE.
4. The best model is saved and served through a web/GUI form that returns predictions.

Technology Roles
- Python
- Scikit-learn
- 1D-CNN
- Signal Processing
- FFT

Implementation Steps
1. Collect the dataset (public repository or own data) and understand each attribute.
2. Set up the environment (Python, SciPy, TensorFlow) and load the data into a notebook.
3. Clean the data: handle missing values, outliers, encoding and scaling; visualise distributions.
4. Split into train/validation/test sets and engineer relevant features.
5. Train several candidate models, tune hyper-parameters and compare metrics.
6. Save the best model and wrap it in a simple web/GUI form for live predictions.
7. Document results with plots, confusion matrix / error charts and conclusions.

Key Features
- Data pre-processing pipeline
- Model comparison
- Evaluation metrics and plots
- Prediction interface

Expected Output
On completion the student will have evaluation results (metrics, confusion matrix or error plots) and a working prediction form.

Deliverables
- Notebook / source code with comments
- Cleaned dataset and trained model file
- Evaluation report with metrics and plots
- Prediction interface