Sensor Data Time-Series Projection for Bus Delay Synchronization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In vehicles and industrial machines, sensor data often becomes out-of-sync due to delays in bus system transmission and encoding/decoding processes, leading to inefficiencies and the need for improved synchronization methods.
Innovation Solution
The use of time-series projection based on auto-regressive statistical models, such as ARIMA or ARMA, to estimate and synchronize sensor data by predicting future trends and compensating for time offsets, ensuring data is synchronized with reference times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If sensor data is transmitted via bus system, then data can be shared across multiple ECUs, but time delays occur during transmission and encoding/decoding
Solution Approach 1:
The system performs preliminary actions by storing historical sensor data samples and building autoregressive models in advance. When synchronization is needed, the model can quickly generate estimated values based on pre-stored historical patterns, reducing the real-time processing delay caused by bus transmission.
Solution Approach 2:
The system creates a copy of the sensor data stream by generating estimated values through the autoregressive model. This copied data stream serves as a placeholder or prediction that can be used immediately while the actual sensor data is still being transmitted through the bus system, effectively bypassing the transmission delay.
2Measurement precision
If multiple sensors are used in distributed systems, then measurement coverage is improved, but sensor data becomes out-of-sync due to transmission delays
Solution Approach 1:
The system uses feedback by continuously comparing the actual sensor data with the model-predicted values. The model is trained on historical data and adjusted based on the difference between predicted and actual measurements, allowing it to adapt to changing conditions and maintain accurate predictions despite variable transmission delays.
Solution Approach 2:
The system changes parameters by dynamically adjusting the autoregressive model based on the specific characteristics of each sensor and its transmission delay profile. Different sensors can have different model parameters optimized for their specific delay patterns, allowing the system to handle heterogeneous sensor networks with varying synchronization requirements.
3Productivity
If real-time processing is required, then system responsiveness is improved, but data accuracy deteriorates due to time offsets
Solution Approach 1:
The autoregressive model acts as an intermediary between the delayed sensor data and the real-time processing requirements. Instead of directly using the delayed actual measurements, the system uses the model's predicted values as an intermediate representation that reflects the current state, bridging the gap between past measurements and present processing needs.
Data Source
Figure 1a~1c
Figure 2a~3
Figure 4a~4b
AI summary
Examples relate to a system, method and computer program for determining estimated sensor data using time-series projection. The system comprises processing circuitry configured to obtain a plurality of samples of sensor data of the sensor. The processing circuitry is configured to obtain information on a time offset between the sensor data of the sensor and a reference time. The processing circuitry is configured to perform a time-series projection based on the plurality of samples of the sensor data. The time-series projection is performed using an auto-regressive statistical model. The processing circuitry I configured to determine an estimate of the sensor data for the reference time based on the time-series projection and based on the time offset between the sensor data and the reference time. Thus, the time-series projection may be used to bridge the time offset between the sensor data of the sensor and the reference time.