Optical Sensor Neural System Code Detection Signal Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Optical sensors face limitations in detecting codes due to varying signal levels from different reading situations, leading to information loss and incorrect code detection, as the analog-digital converter's limited range causes signal limitations that reduce the signal-to-noise ratio and result in incorrect code detections.
Innovation Solution
Incorporating a neural system downstream of the analog-digital converter and upstream of the edge detection unit, which differentiates and samples the received signals, allowing the neural system to recover lost code information and compensate for signal limitations, thereby enhancing error security and decoding reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the analog-to-digital converter operates with limited dynamic range, then device complexity is reduced, but code detection reliability deteriorates due to signal limitation and information loss
Solution Approach 1:
A neural system is introduced as an intermediary component between the analog-to-digital converter and the code detection system. This neural system receives limited digital signals from the converter, processes them to recover lost information about edge positions and signal characteristics, and outputs enhanced signals that maintain code detection reliability without requiring a more complex high-range converter
Solution Approach 2:
The neural system dynamically adjusts signal parameters including amplitude, frequency, and temporal characteristics to compensate for the limitations imposed by the fixed dynamic range of the analog-to-digital converter. By learning from training data, the system adapts parameter transformations that recover information about edge positions even when input signals are compressed to fit the converter's limited range
2Stability of the object's composition
If compression circuits are used to limit signal levels, then signal level variations are reduced, but signal-to-noise ratio deteriorates because noise components are not reduced
Solution Approach 1:
The neural system performs intelligent parameter transformation on the compressed signals, using learned models to distinguish between compressed signal components and noise. By analyzing temporal patterns, frequency characteristics, and contextual information from training data, the system recovers signal parameters while filtering out noise that was not reduced by the compression circuits
Solution Approach 2:
The neural system incorporates feedback mechanisms where output signals are compared with expected patterns from training data, and adjustment is made to recover accurate edge position information. This feedback loop allows the system to compensate for noise contamination introduced by compression, maintaining signal-to-noise ratio despite level limiting
3Speed
If the dynamic range of the analog-to-digital converter is exceeded, then signal processing speed is maintained, but information about edge positions is lost
Solution Approach 1:
The neural system is pre-trained with extensive training data that includes various signal levels, noise conditions, and edge position patterns. This preliminary training equips the system with learned models that enable it to quickly process limited-range signals and recover edge position information without requiring slow additional measurement cycles or higher-range converters
Solution Approach 2:
The patent replaces the mechanical/approach of using a high-range analog-to-digital converter with a neural processing approach. Instead of relying on the converter's dynamic range to preserve signal information, the system uses neural network processing to computationally recover edge position information from limited-range digital signals, achieving the same information preservation goal through a different mechanism
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The neural system effectively recovers lost information and improves the accuracy of code detection, enabling reliable decoding and expanding the reading range of the optical sensor by training on various reading situations to adapt to different noise levels and signal frequencies.
Implementation Method 1
a transmitter (3) emitting light beams (2) and a receiver (4) receiving light beams (2)
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
The invention relates to an optical sensor (1) for detecting codes, comprising a light beam emitting transmitter (2) and a light beam receiving receiver (4), both configured for scanning codes, and an evaluation unit configured for determining code information of the codes depending on the received signals of the receiver (4). The received signals of the receiver (4) are fed to an evaluation circuit in which sampled received signals are generated from the received signals. A neural system is provided in which limitations of the sampled received signals are compensated. The invention further relates to a method for detecting codes.