Energy Prediction Model for Equipment Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for monitoring and predicting the energy levels of electromechanical equipment are inefficient, as they often require frequent and energy-consuming measurements, which can stress the equipment's components and fail to account for varying energy production and consumption patterns due to environmental and usage context changes.
Innovation Solution
A method that builds and selects prediction models based on historical energy measurement data and contextual information, dynamically adapting measurement frequencies and steps to optimize energy level prediction while minimizing the number and frequency of actual measurements, using techniques like neural networks and pruning to reduce resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If frequent measurements of energy level are performed to monitor equipment, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The system performs preliminary actions by training multiple prediction models with different measurement frequencies during a training phase. These models are prepared in advance to predict energy levels at various measurement intervals, allowing the system to select the most appropriate model without needing to perform exhaustive real-time measurements.
Solution Approach 2:
The invention changes the parameter of measurement frequency by creating multiple prediction models, each trained with different measurement frequencies. The system selects and switches between these models based on current energy levels and contextual factors, thereby optimizing the measurement frequency parameter dynamically to balance accuracy with energy consumption.
2Reliability
If measurement frequency is increased to capture energy variations, then reliability of energy monitoring is improved, but loss of energy increases
Solution Approach 1:
The system dynamically adapts measurement frequency by selecting from multiple pre-trained prediction models, each optimized for different measurement intervals. This dynamic selection allows the system to increase measurement frequency when reliability is critical (e.g., low energy levels) and decrease it when energy is abundant, optimizing the trade-off between reliability and energy loss in real-time.
Solution Approach 2:
The system incorporates feedback mechanisms where prediction accuracy is continuously evaluated against actual measurements. This feedback loop allows the system to learn from measurement discrepancies and improve future predictions, enhancing reliability while reducing the need for excessive measurements by leveraging learned patterns from contextual data.
3Adaptability or versatility
If multiple prediction models are built with different measurement frequencies, then adaptability of energy prediction is improved, but device complexity increases
Solution Approach 1:
The system segments the energy prediction task into multiple specialized prediction models, each handling specific measurement frequency scenarios. This segmentation allows each model to be optimized for its specific frequency range, improving overall adaptability while organizing complexity into manageable, modular components that can be independently trained and selected.
4Measurement precision
If contextual data is collected and used for prediction, then measurement precision is improved, but quantity of substance (data processing load) increases
Solution Approach 1:
The system applies partial action by selectively using contextual data based on the specific prediction scenario and energy level. Rather than processing all available contextual data uniformly, the system adapts which contextual factors are incorporated into predictions, reducing unnecessary data processing while maintaining prediction accuracy for critical energy monitoring situations.
Data Source
AI summary
A method for monitoring the energy of an equipment. The method includes: obtaining a first energy prediction model and an energy measurement frequency; predicting energy, via the prediction model, using, as input for the model, the result of a first energy measurement and contextual data of the equipment during and/or since the first measurement, the prediction being carried out before and/or during a second measurement subsequent to the first measurement and carried out with the obtained measurement frequency with respect to the first measurement; and varying the measurement frequency for a third subsequent energy measurement, as a function of a difference between the predicted energy and the second measurement. A method for building the first energy prediction model, corresponding electronic devices, system, computer program products and recording medium.