Torque Estimator Using Histogram Analysis for Drivetrain Monitoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing torque estimation systems for machine drivetrains are unable to detect imminent component failure in real-time and require complex neural networks and equations, making them inefficient for processing limited parameters and automatic configuration across different machine types.

Innovation Solution

A computer system with a torque estimator module that receives engine and drivetrain parameters to determine estimated torque, using a histogram data structure to update and analyze torque values, allowing for real-time detection of excessive torque and automatic configuration based on machine type.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If neural networks and equations are used to estimate torque, then torque estimation capability is improved, but device complexity increases

Engineering Contradiction:
Improvetorque estimation accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the essential torque estimation functionality from complex neural networks and equations, isolating only the critical parameters needed for accurate torque estimation. This reduces system complexity while maintaining measurement precision by removing unnecessary computational complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces expensive, complex neural network models with simpler, computationally inexpensive estimation methods that can be quickly executed. This approach uses lightweight algorithms that consume fewer resources while still providing accurate torque estimates in real-time.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

2Measurement precision

If more engine and drivetrain parameters are processed, then torque estimation accuracy is improved, but processing time increases

Engineering Contradiction:
Improvetorque estimation accuracyVSAvoidcomputational time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts and processes only the most critical engine and drivetrain parameters that have the greatest impact on torque estimation. By identifying and eliminating less significant parameters, the system maintains high estimation accuracy while reducing computational time and processing load.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent processes a selective subset of parameters rather than all available parameters. This partial action approach focuses computational resources on the most influential parameters, achieving sufficient accuracy without the time cost of processing every possible parameter.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If real-time torque estimation is implemented, then component failure detection capability is improved, but computational load increases

Engineering Contradiction:
Improvefailure detection capabilityVSAvoidcomputational energy
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent employs computationally inexpensive algorithms that can execute in real-time with minimal energy consumption. These lightweight estimation methods provide continuous monitoring capability for component failure detection without imposing excessive computational or energy loads on the system.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The system performs self-monitoring using readily available sensor data from the drivetrain, eliminating the need for additional expensive sensors or complex external monitoring systems. The torque estimation leverages existing system data to provide real-time reliability monitoring with minimal additional energy expenditure.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS7970523B2Torque estimator for a machine
Publication Date: 2011.06.28 CATERPILLAR INC
  • US7970523B2 patent drawing
  • US7970523B2 patent drawing
  • US7970523B2 patent drawing

AI summary

A torque estimator is disclosed for estimating torque on a machine. A computer system may include a torque estimator module located on the machine. The torque estimator module may be configured to receive a plurality of engine parameters, receive a drivetrain component parameter, determine an estimated torque value at the drivetrain component based on the plurality of engine parameters and the drivetrain component parameter. The computer system also may include an analysis module located on the machine. The analysis module may be configured to receive the estimated torque value and the drivetrain component parameter, and update a histogram data structure based on the estimated torque value and the drivetrain component parameter. The analysis module may also be configured to evaluate the histogram data structure in order to determine if excessive torque is being applied to a drivetrain component.