Machine State Estimation for Usage, Profitability, and Ownership Cost
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately estimate the potential usage, profitability, and cost of ownership of industrial machines based on their physical and mechanical state using sensor information and other data.
Innovation Solution
A method and system that processes sensor data, service history, and dealership data through modules like machine state, population comparison, optimization, and cost of ownership to generate insights on optimal performance, productivity, and projected life cycle costs, utilizing reinforcement learning and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods (engine running hours, service count) are used to estimate machine value and physical state, then the estimation process is simple, but the accuracy and reliability of the estimate deteriorates
Solution Approach 1:
The system segments the machine into multiple components (engine, transmission, hydraulic system, etc.) and evaluates each component's mechanical state separately using sensor data. This segmentation allows for more precise component-level assessment while maintaining a manageable system structure through modular evaluation of individual parts.
Solution Approach 2:
The patent introduces sensor data as an intermediary between the machine's physical state and the estimation process. Sensors continuously monitor mechanical parameters (vibration, temperature, pressure) and transmit this data to the estimation system, providing an objective intermediary measurement that improves accuracy without requiring direct physical inspection of the entire machine.
2Measurement precision
If comprehensive sensor data and multiple data sources are collected and processed, then the accuracy of productivity and cost estimates improves, but the computational complexity and data processing requirements worsen
Solution Approach 1:
The system merges multiple data sources (sensor data, service history, operational data) into a unified estimation framework. By combining these diverse data streams and processing them through integrated algorithms, the system achieves comprehensive accuracy while managing complexity through data consolidation and unified processing protocols.
Solution Approach 2:
The machine's own sensor systems and operational data serve the estimation process autonomously. The machine self-monitors its mechanical state through embedded sensors and automatically provides this data to the estimation system, eliminating the need for external manual data collection and reducing the complexity of data acquisition infrastructure.
3Duration of action of stationary object
If machine state monitoring and analysis systems are implemented, then the ability to optimize performance and extend life cycle improves, but the initial cost and system complexity worsen
Solution Approach 1:
The system performs preliminary analysis of sensor data to predict potential mechanical failures before they occur. By continuously monitoring mechanical state parameters and identifying degradation trends early, the system enables proactive maintenance actions that extend machine life cycle while managing complexity through predictive rather than reactive monitoring approaches.
Solution Approach 2:
The patent implements a feedback loop where sensor data continuously monitors machine mechanical state, the system analyzes this data to assess component health, and maintenance recommendations are fed back to operators. This closed-loop feedback mechanism optimizes performance and extends life cycle by enabling data-driven maintenance decisions while managing complexity through automated monitoring and analysis.
Data Source
AI summary
Techniques are provided that include receiving sensor data from sensors of the machine, service history data, previous dealership data, and owner input data. The techniques include generating a state of the machine and a state of each of individual components by processing such data. Some of such data are processed to generate the measure of projected productivity of the machine and the estimate of projected maintained life cycle and costs. The generated data are input to the machine optimization module to generate the optimal performance level of the machine and data indicative of the optimal performance level of the machine, which are processed to generate productivity data of the machine, which are transmitted to a customer-facing application for display or post-processing.