Equivalent ECU Speed Derivation From GPS for Fleet Monitoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Fleet management systems face challenges in continuously tracking engine control unit (ECU) speed of vehicles due to prioritization of location data over ECU data, leading to incomplete information and potential speed reporting issues, which can result in unnecessary alerts and increased wear on vehicles.

Innovation Solution

A monitoring platform that trains a machine learning model using historical location, ECU, and distance data to derive an equivalent real-time ECU speed when only GPS speed is available, allowing for accurate prediction and alerting of excessive speeds, thereby improving safety and reducing vehicle wear.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If location data is prioritized over ECU data for transmission, then network bandwidth is conserved and transmission efficiency is improved, but ECU speed tracking completeness deteriorates and data accuracy is lost

Engineering Contradiction:

Improvetransmission efficiencyVSAvoidECU speed data completeness

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The patent creates a virtual copy of ECU speed data by training a machine learning model to predict ECU speed values based on available GPS location data. The model learns the relationship between GPS speed and actual ECU speed from historical data, then generates predicted ECU speed values that replicate the missing information without requiring actual ECU data transmission, thus conserving bandwidth while maintaining data completeness.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent introduces a machine learning model as an intermediary between GPS location data and ECU speed tracking. This intermediary processes the available location data and transforms it into predicted ECU speed values, bridging the gap caused by prioritizing location data transmission over ECU data transmission.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of energy

If ECU data transmission is reduced to conserve bandwidth, then network resource consumption is decreased, but speed monitoring accuracy deteriorates and false alerts increase

Engineering Contradiction:

Improvenetwork resource consumptionVSAvoidspeed monitoring accuracy

Core Design Contradiction:

Loss of energyVSMeasurement precision

Solution Approach 1:

The machine learning model creates accurate predictions of ECU speed values by learning from historical relationships between GPS and ECU data. This copying approach reconstructs the speed information that would otherwise be lost due to reduced ECU data transmission, maintaining monitoring accuracy while conserving network resources.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system performs preliminary training of the machine learning model using historical ECU and GPS data before deployment. This preliminary action establishes the model's predictive capabilities, enabling it to accurately reconstruct ECU speed values from GPS data during operation, thereby ensuring monitoring accuracy is maintained even with reduced data transmission.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If manual data collection and analysis is used to track ECU speed, then data processing accuracy is maintained, but computing resource consumption increases and automation is reduced

Engineering Contradiction:

Improvedata processing accuracyVSAvoiddata processing automation

Core Design Contradiction:

Measurement precisionVSExtent of automation

Solution Approach 1:

The machine learning model enables the system to automatically process and analyze data without manual intervention. The model self-adjusts its parameters through training on historical data and autonomously predicts ECU speed values from GPS data, eliminating the need for manual data collection and analysis while maintaining high accuracy through automated pattern recognition.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical data processing with an automated machine learning system. The model automatically learns relationships from historical data and generates predictions without human intervention, substituting the manual analysis process with an automated computational system that maintains or improves accuracy while reducing resource consumption.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11887482B2Deriving an equivalent real-time engine control unit (ECU) speed of a vehicle

Publication Date: 2024.01.30 VERIZON PATENT & LICENSING INC

AI summary

A server device can obtain historical location data, concerning a vehicle, captured by a global positioning system (GPS) device of the vehicle and historical engine control unit (ECU) data concerning the vehicle captured by an ECU of the vehicle. The server device can process the historical location data and the historical ECU data to train a machine learning model to determine a relationship between the historical location data and the historical ECU data. The server device can receive location data and ECU data concerning the vehicle and update the machine learning model based on the location data and the ECU data. The server device can receive real-time location data concerning the vehicle and derive an equivalent real-time ECU speed using the machine learning model. The server device can generate a message regarding the equivalent real-time ECU speed of the vehicle and send the message to a remote device for display.