pith. sign in

USPTO: us-12642177 · published 2026-06-02 · patents · A01D 41/1277· A01D 41/1272· A01D 41/1273· A01D 41/1275· A01F 12/444· G01F 1/76· G01G 19/08· G01N 33/02

Kernel-level grain monitoring systems for combine harvesters

Pith reviewed 2026-06-03 10:30 UTC · model grok-4.3

classification patents A01D 41/1277A01D 41/1272A01D 41/1273A01D 41/1275A01F 12/444G01F 1/76G01G 19/08G01N 33/02
keywords combine harvestergrain monitoringkernel volumemass flow ratestrike plate sensorimage analysisharvest parameters
0
0 comments X

The pith

A combine harvester controller uses camera images of bulk grain plus strike-plate impacts to compute average per-kernel volume and real-time mass flow.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The patent describes an onboard monitoring system that photographs grain samples as they move through the harvester and processes those images to find an average per-kernel volume. That volume is converted to an estimated mass per kernel, which is then combined with impact data from a strike plate to track mass flow rate. The same controller calculates topline harvesting parameters from the volume data and displays them to the operator. A sympathetic reader sees the value in replacing periodic manual sampling with continuous, kernel-level measurements that could improve yield estimates and machine settings during harvest.

Core claim

The central claim is a controller architecture that receives bulk-grain images from a camera and impact signals from a strike-plate sensor, derives average per-kernel volume directly from the images, multiplies by density to obtain average per-kernel mass, uses that mass together with impact counts to produce a mass-flow rate, computes harvesting parameters from the volume figure, and presents the results to the operator.

What carries the argument

Controller architecture that fuses image-derived average per-kernel volume with strike-plate impact data to generate mass-flow rate and topline harvest parameters.

If this is right

  • Mass-flow rate becomes continuously available rather than sampled at intervals.
  • Operator receives updated topline parameters derived from the same volume measurement used for flow.
  • Yield maps can be generated at the resolution of individual kernel statistics.
  • Machine settings such as rotor speed or concave clearance can be adjusted using the live per-kernel data.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The architecture could be extended to flag quality deviations if volume statistics drift outside expected ranges for a given crop variety.
  • Integration with GPS would allow spatially resolved maps of kernel-size variation across a field.
  • Similar camera-plus-impact sensing might be adapted to other bulk-flow processes such as seed processing or grain elevators.

Load-bearing premise

Image analysis of bulk grain can reliably extract a representative average per-kernel volume despite dust, vibration, variable lighting, and kernel overlap.

What would settle it

Field trials showing that the camera-derived average per-kernel volume deviates more than a stated tolerance from manual kernel counts and volume measurements taken on the same grain stream under actual harvest conditions.

read the original abstract

1 . A kernel-level grain monitoring system utilized onboard a combine harvester, the kernel-level grain monitoring system comprising: a grain camera positioned to capture bulk grain sample images of a currently-harvested grain taken into and processed by the combine harvester; and a strike plate sensor configured to be impacted by kernels of the currently-harvested grain; a controller architecture coupled to the grain camera and to the strike plate sensor, the controller architecture configured to: analyze the bulk grain sample images, as received from the grain camera, to determine an average per kernel (APK) volume representing an estimated volume of a single average kernel of the currently-harvested grain; estimate an APK mass of the currently-harvested grain utilizing the APK volume; monitor a mass flow rate of the currently-harvested grain based, at least in part, on the estimated APK mass and impact data provided by the strike plate sensor; calculate one or more topline harvesting parameters based, at least in part, on the determined APK volume; and output the topline harvesting parameters to an operator of the combine harvester.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript is a utility patent claim describing a kernel-level grain monitoring system for combine harvesters. It comprises a grain camera that captures bulk sample images, a strike-plate sensor that registers kernel impacts, and a controller that (i) extracts an average per-kernel (APK) volume from the images, (ii) converts APK volume to APK mass, (iii) computes mass-flow rate from the APK mass and impact data, (iv) derives topline harvesting parameters, and (v) displays the parameters to the operator.

Significance. If the claimed functions could be realized with field-robust accuracy, the architecture would supply operators with real-time, kernel-resolved grain metrics that are not available from conventional yield monitors. The text, however, supplies neither algorithms, performance metrics, nor validation data, so the practical significance cannot be assessed from the given document.

major comments (1)
  1. Claim 1 asserts that the controller 'analyze[s] the bulk grain sample images … to determine an average per kernel (APK) volume' under unspecified field conditions, yet the specification contains no image-processing method, calibration procedure, or error analysis that would support this determination. This absence renders the central functional claim unsupported.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for reviewing the utility patent application. The document is a claim set for a novel system architecture rather than an algorithmic or empirical study; we address the single major comment below.

read point-by-point responses
  1. Referee: Claim 1 asserts that the controller 'analyze[s] the bulk grain sample images … to determine an average per kernel (APK) volume' under unspecified field conditions, yet the specification contains no image-processing method, calibration procedure, or error analysis that would support this determination. This absence renders the central functional claim unsupported.

    Authors: The patent claims a system architecture that integrates a grain camera, strike-plate sensor, and controller to produce kernel-resolved metrics. Under U.S. patent practice, the claim need only recite the functional elements; enablement is satisfied when a person of ordinary skill can implement the image-analysis step with known computer-vision techniques without undue experimentation. Detailed algorithms, calibration routines, and error budgets are therefore omitted from the specification, as is conventional for utility patents of this type. revision: no

Circularity Check

0 steps flagged

No significant circularity

full rationale

The document is a utility patent whose sole content is a functional architecture claim (camera + strike-plate + controller performing APK volume estimation, mass-flow calculation, and parameter output). No equations, derivations, fitted parameters, predictions, or self-citations appear anywhere in the text. Consequently no load-bearing step can reduce to its own inputs by construction, and the circularity score is 0.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The patent rests on unstated engineering assumptions about sensor accuracy and image-processing robustness rather than explicit free parameters, axioms, or invented physical entities.

pith-pipeline@v0.9.0 · 5819 in / 1001 out tokens · 30680 ms · 2026-06-03T10:30:49.240975+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.