Feature engineering is the systematic extraction and construction of predictive variables from raw time-series telemetry, such as dissolved gas concentrations and load currents, to train supervised machine learning models. In transformer diagnostics, this involves calculating gas ratios (e.g., methane/hydrogen), rolling statistics (e.g., 24-hour mean temperature), and lag features that capture temporal degradation trends invisible to instantaneous threshold monitoring.
Glossary
Feature Engineering

What is Feature Engineering?
Feature engineering is the process of transforming raw transformer sensor data into informative, predictive inputs that enhance the accuracy of machine learning models for fault detection and remaining useful life estimation.
Effective feature engineering bridges the gap between operational data historians and physics-informed models by encoding domain expertise, such as IEC 60599 diagnostic ratios or Duval Triangle coordinates, into mathematical representations. This process directly determines a model's ability to distinguish between thermal faults, partial discharge, and normal aging, making it the single highest-leverage step in building reliable predictive maintenance systems.
Core Feature Categories for Transformer ML
The process of creating lag features, rolling statistics, and gas ratios from raw sensor time-series data to improve the predictive performance of transformer diagnostic machine learning models.
Temporal Lag Features
Shifting time-series data backward to capture the sequential dependency of gas generation. Lag features convert a static snapshot of DGA values into a dynamic sequence, allowing models to learn the rate of change.
- Example: A lag-24 feature for acetylene (C₂H₂) represents the gas concentration 24 hours prior.
- Mechanism: Enables tree-based models and LSTMs to detect trends that a single reading cannot reveal.
- Key Insight: Rapidly rising hydrogen (H₂) with a lagged baseline is a critical indicator of partial discharge.
Rolling Window Statistics
Calculating aggregate metrics over a moving temporal window to smooth sensor noise and highlight persistent shifts. Rolling statistics transform volatile raw telemetry into stable, trend-indicating features.
- Rolling Mean: Dampens transient spikes in moisture content to reveal the true drying or wetting trend of solid insulation.
- Rolling Standard Deviation: Quantifies the instability of a load tap changer's motor current, indicating mechanical wear.
- Rolling Min/Max: Captures the daily peak hot-spot temperature, which directly dictates the rate of cellulose aging per IEEE C57.91.
Diagnostic Gas Ratios
Engineering composite features by calculating the ratios of specific dissolved gases to classify fault types. Gas ratios are the foundational input for the Duval Triangle and IEC 60599 interpretation methods.
- Duval Ratio 1 (CH₄/H₂): Differentiates thermal faults from electrical discharges based on the relative production of methane versus hydrogen.
- Duval Ratio 2 (C₂H₂/C₂H₄): High values indicate high-energy arcing due to acetylene generation.
- CO₂/CO Ratio: A critical indicator of paper degradation; a low ratio suggests pyrolysis of cellulose insulation.
Differential & Delta Features
Computing the first-order difference between consecutive time steps to capture the instantaneous velocity of change. This feature type is highly sensitive to incipient faults that manifest as sudden gas spurts.
- Delta Acetylene: A non-zero delta is an immediate red flag for active arcing, as C₂H₂ is not produced by normal aging.
- Rate of Rise: Calculating the ppm-per-day increase in combustible gases to trigger alarms before absolute thresholds are breached.
- Application: Essential for online DGA monitors where trending velocity is more actionable than static concentration.
Fourier & Spectral Features
Transforming time-domain signals into the frequency domain to extract periodic patterns invisible in raw waveforms. Spectral features are critical for analyzing vibration and acoustic partial discharge data.
- Fast Fourier Transform (FFT): Decomposes vibration signals from load tap changers to identify specific mechanical resonance frequencies indicating misalignment.
- Power Spectral Density: Quantifies the energy distribution of acoustic emissions to distinguish internal partial discharge from external corona.
- Cepstral Analysis: Used to detect periodic echoes in Frequency Response Analysis (FRA) traces, revealing winding deformation.
Interaction & Cross-Features
Creating new features by multiplying, dividing, or combining two or more independent variables to capture non-linear physical relationships. Interaction features encode domain expertise directly into the model.
- Load × Ambient Temperature: A combined thermal stress index that better predicts hot-spot temperature than either variable alone.
- Moisture × Oxygen: Models the synergistic catalytic effect that drastically accelerates cellulose depolymerization.
- Gas Ratio × Load: Contextualizes a high acetylene ratio with the transformer's operating state to suppress false positives during transient heavy loading.
Enabling Efficiency, Speed & Accuracy
Intelligent Analysis, Decision & Execution
We build AI systems for teams that need search across company data, workflow automation across tools, or AI features inside products and internal software.
Talk to Us
Search across company data
Give teams answers from docs, tickets, runbooks, and product data with sources and permissions.
Useful when people spend too long searching or get different answers from different systems.

Automate internal workflows
Use AI to route work, draft outputs, trigger actions, and keep approvals and logs in place.
Useful when repetitive work moves across multiple tools and teams.

Add AI to products and internal tools
Build assistants, guided actions, or decision support into the software your team or customers already use.
Useful when AI needs to be part of the product, not a separate tool.
Frequently Asked Questions
Clear, technical answers to the most common questions about building predictive features from raw transformer sensor data for machine learning models.
Feature engineering is the systematic process of transforming raw time-series sensor data—such as dissolved gas concentrations, load current, and top-oil temperature—into informative numerical representations that improve the predictive performance of machine learning models. In transformer diagnostics, this involves creating lag features (prior hourly or daily readings), rolling statistics (moving averages and standard deviations over configurable windows), and domain-specific gas ratios (e.g., methane/hydrogen, acetylene/ethylene) that encode physical fault signatures. The goal is to expose the underlying thermodynamic and chemical degradation patterns to the algorithm, enabling it to distinguish between normal operational transients and incipient faults like partial discharge or thermal overheating. Without rigorous feature engineering, even advanced models like gradient-boosted trees or LSTMs will fail to generalize beyond the training data, as raw sensor values alone rarely capture the temporal dependencies and rate-of-change dynamics critical for early failure detection.
Related Terms
Master the core techniques for transforming raw transformer sensor data into high-signal predictive inputs for machine learning models.
Lag Features
Create temporal predictors by shifting time-series data backward. For Dissolved Gas Analysis (DGA) , generating lag features allows models to learn the rate of gas generation rather than just absolute concentrations.
- Example: Shifting acetylene (C₂H₂) readings by 1, 6, and 24 hours to capture the velocity of arcing faults.
- Key Concept: Transforms a static snapshot into a dynamic trajectory, enabling LSTM and Temporal Fusion Transformer models to detect acceleration trends.
Rolling Statistics
Compute moving averages, standard deviations, and min/max windows over sensor streams to smooth noise and highlight persistent shifts. Essential for Hot-Spot Temperature monitoring.
- Rolling Mean: A 24-hour moving average of winding temperature filters out transient load spikes.
- Rolling Std Dev: Detects increasing vibration variability in Load Tap Changer (LTC) motor signatures before mechanical failure.
- Exponentially Weighted Moving Average (EWMA) : Applies higher weight to recent observations for drift detection.
Gas Ratio Engineering
Construct domain-specific diagnostic ratios from raw DGA ppm values to classify fault types. These ratios form the basis of the Duval Triangle and IEC 60599 interpretation standards.
- Key Ratios: CH₄/H₂ (methane/hydrogen), C₂H₂/C₂H₄ (acetylene/ethylene), C₂H₄/C₂H₆ (ethylene/ethane).
- Duval Triangle 1: Uses %CH₄, %C₂H₄, and %C₂H₂ to map faults to thermal fault, partial discharge, or arcing zones.
- Rogers Ratio: A four-ratio coding scheme for classifying thermal and electrical faults per IEEE C57.104.
Time-Based Decomposition
Separate raw sensor signals into trend, seasonal, and residual components to isolate anomalous behavior from normal cyclic patterns. Critical for Online DGA Monitors with daily load cycles.
- Trend Component: Long-term insulation degradation trajectory extracted from Degree of Polymerization (DP) proxies.
- Seasonal Component: Daily and weekly load-driven temperature cycles removed to expose true thermal anomalies.
- Residual Analysis: The remaining noise component where incipient fault signatures first appear before trending algorithms detect them.
Interaction Features
Engineer cross-variable features that capture the physical coupling between transformer subsystems. Physics-Informed Neural Networks (PINNs) leverage these to enforce thermodynamic constraints.
- Load × Ambient Temperature: Interaction term modeling the non-linear relationship governing Hot-Spot Temperature rise per IEEE C57.91.
- Moisture Content × Temperature: Combined feature predicting bubble evolution temperature and dielectric strength reduction.
- Gas Generation Rate Ratios: Cross-gas rate comparisons (e.g., CO₂/CO generation ratio) indicating paper versus oil degradation.
Frequency-Domain Features
Transform time-series vibration and acoustic signals into the frequency domain using Fast Fourier Transform (FFT) to extract spectral signatures of mechanical faults.
- Spectral Centroid: Tracks shifts in dominant vibration frequency indicating LTC contact wear.
- Harmonic Distortion: Odd-harmonic amplitudes in current waveforms signaling core saturation or geomagnetic induced currents.
- Wavelet Packet Energy: Multi-resolution decomposition capturing transient Partial Discharge pulses across frequency bands for source localization.

About the author
Prasad Kumkar
CEO & MD, Inference Systems
Prasad Kumkar is the CEO & MD of Inference Systems and writes about AI systems architecture, LLM infrastructure, model serving, evaluation, and production deployment. Over 5+ years, he has worked across computer vision models, L5 autonomous vehicle systems, and LLM research, with a focus on taking complex AI ideas into real-world engineering systems.
His work and writing cover AI systems, large language models, AI agents, multimodal systems, autonomous systems, inference optimization, RAG, evaluation, and production AI engineering.
Partnered with leading AI, data, and software stack.
How We Work
Custom AI workflows for your Business
One-fit-all AI don't work for modern businesses. At Inferensys, we aim to understand your business & custom requirements; which we use to define most efficient agentic workflows, the data, and the tools for your business.
01
Review the use case
We understand the task, the users, and where AI can actually help.
Read more02
Pick the right approach
We define what needs search, automation, or product integration.
Read more03
Build the first useful version
We implement the part that proves the value first.
Read more04
Improve from there
We add the checks and visibility needed to keep it useful.
Read moreThe first call is a practical review of your use case and the right next step.
Talk to Us