Generator Load Prediction Using External Sensor Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing generator systems face inefficiencies in predicting and managing sudden changes in load demand, leading to unnecessary fuel and resource consumption due to the inability to detect load triggers before they occur, resulting in the need for maintaining excess generation capacity to handle unpredictable loads.

Innovation Solution

A generator system with a controller that utilizes sensors to collect and analyze data on electrical parameters, external factors, and environmental conditions to predict load events, allowing for the identification of useful triggers and adjusting generator configuration accordingly, thereby reducing the number of generators needed online.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If additional generator capacity is maintained online to handle unpredictable high load demands, then system reliability is improved, but fuel consumption and resource usage increase

Engineering Contradiction:
Improvesystem reliabilityVSAvoidfuel consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by detecting load triggers before actual load events occur. The controller monitors external sensor data (temperature, humidity, occupancy, weather conditions) and identifies patterns that precede high load demands, allowing the generator to prepare and respond only when necessary, rather than maintaining constant excess capacity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring both internal generator parameters and external environmental factors. The controller analyzes sensor data in real-time, compares it against learned patterns from historical load events, and adjusts generator operation accordingly. This closed-loop feedback enables dynamic optimization between reliability and fuel consumption.

Inventive Principle:
Principle #23Feedback

2Loss of energy

If the generator system configuration is dynamically adjusted based on predicted load events, then resource efficiency is improved, but system complexity increases

Engineering Contradiction:
Improveresource efficiencyVSAvoidsystem complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The system performs self-service through automated pattern recognition and decision-making. The controller independently analyzes sensor data, identifies load triggers using machine learning algorithms, and adjusts generator configuration without human intervention. This automation handles the complexity internally while presenting a simple interface for resource optimization.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The controller acts as an intermediary between external environmental factors and the generator system. It processes complex sensor data from multiple sources (temperature sensors, humidity sensors, occupancy detectors, weather stations) and translates these into appropriate generator control actions, shielding the physical system from the complexity of environmental monitoring.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If external sensor data is analyzed to identify load triggers, then prediction accuracy is improved, but measurement and detection difficulty increases

Engineering Contradiction:
Improveprediction accuracyVSAvoiddetection difficulty
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system segments the detection task by dividing it into distinct sensor types and data categories. External sensors are organized into specific groups (temperature sensors, humidity sensors, occupancy detectors, weather station data), each monitored independently. The controller processes these segmented data streams separately before integrating them for comprehensive load trigger analysis, making the complex detection task manageable.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3396476B1Predictive generator system
Publication Date: 2020.04.22 KOHLER CO(US)
  • EP3396476B1 patent drawingFigure 1
  • EP3396476B1 patent drawingFigure 2
  • EP3396476B1 patent drawingFigure 3

AI summary

An apparatus for predicting a load event in a generator system or a method for predicting the load event in the generator system may include monitoring output data associated with an electrical output of a generator (11), monitoring external sensor (14) data associated with the generator (11), detecting a load event for the generator (11) from the output data, identifying a subset of the external sensor (14) data that preceded the load event from the output data, performing an analysis of the subset of the external sensor (14) data, and determining a load event characteristic from the analysis, the load event characteristic indicative of a subsequent load event for the generator (11).