Row-Level Spray Error Detection for Skipped and Duplicate Rows
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for monitoring agricultural spraying operations during nighttime conditions, often conducted by inexperienced or unmotivated workers, fail to provide real-time alerts for incorrect spraying behavior and do not automatically detect rows that have been sprayed an incorrect number of times.
Innovation Solution
The use of sensed tractor data in conjunction with row-level block maps to detect errors and issue alerts, employing sensors such as GNSS receivers, action sensors, and RFID tags to determine tractor activity and compare it against predefined guidelines for speed, flow rate, and location within a block, with algorithms to identify duplicate or skipped spraying.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If manual spraying operations are conducted by untrained workers at night, then labor costs are reduced, but spraying accuracy and error detection capability deteriorate
Solution Approach 1:
The system enables self-service through automated monitoring and detection capabilities. Sensors on the tractor automatically track spraying operations, GPS coordinates are automatically recorded, and the system self-monitors spray application accuracy without requiring trained human operators. The automated error detection system identifies spraying mistakes independently, allowing untrained workers to perform manual spraying while the system ensures accuracy through continuous self-monitoring and alert generation when errors are detected.
2Manufacturing precision
If real-time monitoring systems are implemented to detect spraying errors, then spraying accuracy is improved, but system complexity increases
Solution Approach 1:
The monitoring system achieves multi-functionality by integrating multiple detection capabilities into a single unified platform. The system simultaneously monitors GPS location, spray application rates, tractor speed, and block boundaries using a combination of sensors, GPS receivers, and processing units. This universal approach allows one system to perform multiple functions (error detection, location tracking, spray rate monitoring, and alert generation) rather than requiring separate specialized systems for each function, thereby improving spraying accuracy while managing overall system complexity through consolidation.
3Measurement precision
If continuous monitoring of tractor speed and location is performed, then detection precision is improved, but energy consumption increases
Solution Approach 1:
The system implements periodic monitoring at strategically determined intervals rather than continuous monitoring. The processor evaluates tractor speed, location, and spray application at specific time intervals, comparing current readings against previous measurements and predefined thresholds. This periodic approach maintains sufficient detection precision for identifying spraying errors while significantly reducing energy consumption compared to continuous monitoring, as the system only activates sensors and processing at necessary intervals rather than operating continuously.
Data Source
AI summary
A method includes receiving a location sample; determining whether the location sample is sufficient quality; if the location sample is not sufficient quality, discarding the current location sample; if the location sample is sufficient quality, determining whether the location sample is within a same row as a prior location sample; if the location sample is not within the same row as the prior location sample, discarding the location sample; if the location sample is within the same row as the prior location sample, assigning the location sample to the same row and generating an updated block map; determining whether the updated block map includes a potential skipped row; and issuing an alert if the potential skipped row remains a potential skipped row for an amount of time greater than a first threshold.