CN-121855405-B - High-precision detection method and system for outline size of glass observation window of auxiliary washing machine

CN121855405BCN 121855405 BCN121855405 BCN 121855405BCN-121855405-B

Abstract

The invention relates to the field of detection of the outline size of a glass observation window of a washing machine, and discloses a method and a system for high-precision detection of the outline size of the glass observation window of an auxiliary washing machine, wherein the method comprises the steps of sampling at equal space intervals in the acquisition step to obtain a point cloud data set with uniform space distribution; the method comprises the steps of preprocessing point cloud data, carrying out local surface feature analysis on the point cloud data, marking edge candidate points, carrying out space connectivity analysis, removing isolated points to obtain the edge point cloud data, carrying out iterative adjustment on a standard geometric model based on geometric constraint conditions in a fitting step until the integral accumulated deviation variation is smaller than a convergence threshold value, and extracting outline dimension parameters in a dimension generating step. The system comprises a signal acquisition module, a data preprocessing module, a geometric fitting module and a parameter extraction module. The invention eliminates the influence of motion speed fluctuation on sampling uniformity, effectively eliminates surface defect interference, and realizes high-precision and high-efficiency automatic detection of the contour size of the glass observation window of the washing machine.

Inventors

JING LI
ZHANG DONGSHENG
LI BO
SUN YU
LIU ZHENGQIANG
LV YUNPENG
ZHANG XIANGYUN

Assignees

绥中明晖工业技术有限公司

Dates

Publication Date: 20260508
Application Date: 20260318

Claims (6)

1. The high-precision detection method for the outline size of the glass observation window of the auxiliary washing machine is applied to a detection system comprising a point laser displacement sensor and a driving mechanism, and is characterized by comprising the following steps of: in the process that the driving mechanism drives the point laser displacement sensor to move along a preset scanning path, setting a trigger sampling mode to be equal space interval sampling according to the moving track of the driving mechanism so as to eliminate the influence of motion speed fluctuation on the uniformity of the distribution of sampling points, triggering the sensor to acquire data according to the preset space sampling interval, and performing analog-to-digital conversion on acquired analog quantity signals to obtain a point cloud data set which is uniformly distributed in space on the preset scanning path; the preprocessing step comprises the steps of carrying out local surface feature analysis on a point cloud data set to obtain a curvature value at each sampling point, marking the sampling points with the curvature value exceeding a preset curvature threshold as edge candidate points, carrying out space connectivity analysis on the edge candidate points, eliminating isolated edge candidate points which cannot form a communication area with a main edge, and determining the reserved edge candidate points with continuous distribution features as edge point cloud data; Selecting a plurality of characteristic points from the edge point cloud data, iteratively adjusting the pose of the standard geometric model based on a preset geometric constraint condition, re-determining the integral accumulated deviation between the standard geometric model and the plurality of characteristic points after each adjustment, stopping adjustment when the variation of the integral accumulated deviation after two adjacent adjustments is smaller than a preset convergence threshold, and taking the current standard geometric model as a final fitting result; And a dimension generating step, namely extracting the outline dimension parameter of the glass observation window of the washing machine based on the standard geometric model, wherein the outline dimension parameter comprises at least one of diameter, roundness and curvature radius.
2. The method for detecting the outline dimension of the glass observation window of the auxiliary washing machine with high precision according to claim 1, wherein the noise filtering processing is performed on the point cloud data set in the preprocessing step, further comprising: carrying out statistical analysis on the point cloud data set, determining the average distance between each sampling point and the adjacent point, judging the sampling points with the average distance exceeding the whole distribution threshold range as outliers, and removing the outliers to obtain a first point cloud data set; The first point cloud data set is smoothed to eliminate random fluctuations caused by sensor electrical noise or microscopic surface irregularities.
3. The method for high-precision detection of the outline dimensions of a glass viewing window of an auxiliary washing machine according to claim 1, wherein the preset geometric constraint condition comprises constraint of a spatial relationship between a central axis of a standard geometric model and a designed rotation central axis of the glass viewing window of the washing machine, and the fitting step further comprises: determining an initial pose for the standard geometric model, so that the central axis of the standard geometric model is positioned in the adjacent area of the designed rotation central axis; Continuously monitoring the deviation degree between the central axis of the standard geometric model and the designed rotation central axis in the iterative adjustment process; and stopping adjustment when the variation of the integral accumulated deviation is smaller than a preset convergence threshold value and the deviation degree tends to be stable, and taking the current standard geometric model as a final fitting result.
4. A high-precision detection system for the outline dimensions of a glass viewing window of an auxiliary washing machine, for implementing the method of any one of claims 1 to 3, characterized in that it comprises: the signal acquisition module is used for setting a trigger sampling mode to be equal space interval sampling according to the moving track of the driving mechanism in the process that the driving mechanism drives the point laser displacement sensor to move along a preset scanning path so as to eliminate the influence of movement speed fluctuation on the uniformity of distribution of sampling points, triggering the sensor to acquire data according to the preset space sampling interval, and performing analog-to-digital conversion on acquired analog quantity signals to obtain a point cloud data set which is uniformly distributed in space on the preset scanning path; The data preprocessing module is used for carrying out local curved surface feature analysis on the point cloud data set to obtain a curvature value at each sampling point, marking the sampling points with the curvature value exceeding a preset curvature threshold as edge candidate points, carrying out space connectivity analysis on the edge candidate points, removing isolated edge candidate points which cannot form a communication area with a main edge, and determining the reserved edge candidate points with continuous distribution features as edge point cloud data; The geometric fitting module is used for selecting a plurality of characteristic points from the edge point cloud data, carrying out iterative adjustment on the pose of the standard geometric model based on a preset geometric constraint condition, re-determining the integral accumulated deviation between the standard geometric model and the plurality of characteristic points after each adjustment, stopping adjustment when the variation of the integral accumulated deviation after two adjacent adjustments is smaller than a preset convergence threshold value, and taking the current standard geometric model as a final fitting result; And the parameter extraction module is used for extracting the outline size parameter of the glass observation window of the washing machine based on the standard geometric model, wherein the outline size parameter comprises at least one of diameter, roundness and curvature radius.
5. The system for detecting the outline dimension high precision of the glass observation window of the auxiliary washing machine according to claim 4, wherein the data preprocessing module comprises a noise filtering unit and an edge recognition unit; The noise filtering unit is used for carrying out statistical analysis on the point cloud data set, determining the average distance between each sampling point and the adjacent points, judging the sampling points with the average distance exceeding the whole distribution threshold range as outliers and removing the outliers to obtain a first point cloud data set, and carrying out smooth filtering on the first point cloud data set to eliminate random fluctuation; The edge recognition unit is used for carrying out local surface feature analysis on the point cloud data set subjected to noise filtering processing, analyzing to obtain a curvature value at each sampling point, marking the sampling points with the curvature value exceeding a preset curvature threshold as edge candidate points, carrying out space connectivity analysis on the edge candidate points, eliminating isolated edge candidate points which cannot form a communication area with a main edge as interference points, reserving the edge candidate points with continuous distribution features, and determining the edge candidate points as edge point cloud data.
6. The system for high-precision detection of the contour dimension of a glass viewing window of an auxiliary washer of claim 4, wherein the geometric fitting module is further configured to: selecting a plurality of characteristic points from the edge point cloud data; determining an initial pose for a standard geometric model, and enabling the model to be in initial correspondence with a plurality of characteristic points in space; Iteratively adjusting the pose of the standard geometric model based on a preset geometric constraint condition, and re-determining the integral accumulated deviation between the standard geometric model and a plurality of characteristic points after each adjustment; Comparing the integral accumulated deviation obtained after each adjustment with the integral accumulated deviation obtained after the previous adjustment; When the variation of the integral accumulated deviation obtained after two adjacent adjustments is smaller than a preset convergence threshold, the iteration process is judged to converge, the adjustment is stopped, and the current standard geometric model is used as a final fitting result.

Description

High-precision detection method and system for outline size of glass observation window of auxiliary washing machine Technical Field The invention relates to the technical field of detection of the outline size of a glass observation window of a washing machine, in particular to a high-precision detection method and a high-precision detection system for the outline size of the glass observation window of an auxiliary washing machine. Background The glass observation window of the washing machine is a key component of the drum washing machine, and the outline dimensional accuracy directly influences the sealing performance and the appearance quality of the whole machine. In the prior art, the detection of the outline size of the glass observation window of the washing machine is mainly carried out by adopting a manual detection tool or a contact type three-coordinate measuring machine, the detection mode of the manual detection tool depends on the experience judgment of operators, the detection efficiency is low, the subjectivity is high, the consistency and the accuracy of a detection result are difficult to ensure, the contact type three-coordinate measuring machine has the advantages of high measurement accuracy, low measurement speed, scratch possibly caused by the contact of a probe with the glass surface, high equipment cost and incapability of meeting the requirement of online full detection of a production line due to the fact that the contact type three-coordinate measuring machine is only suitable for laboratory sampling. In addition, when the traditional laser scanning mode is adopted for detection, because the glass material has light transmission characteristics and the surface curvature is complex, measurement noise and edge recognition errors are easy to generate, and the contour dimension detection precision is difficult to meet the assembly requirement. Disclosure of Invention The invention aims to provide a high-precision detection method and a high-precision detection system for the outline size of an auxiliary washing machine glass observation window, so as to solve the problems in the background art. In order to achieve the above purpose, the invention provides a technical scheme that the high-precision detection method for the outline dimension of the glass observation window of the auxiliary washing machine is applied to a detection system comprising a point laser displacement sensor and a driving mechanism, and comprises the following steps: in the process that the driving mechanism drives the point laser displacement sensor to move along a preset scanning path, setting a trigger sampling mode to be equal space interval sampling according to the moving track of the driving mechanism so as to eliminate the influence of motion speed fluctuation on the uniformity of the distribution of sampling points, triggering the sensor to acquire data according to the preset space sampling interval, and performing analog-to-digital conversion on acquired analog quantity signals to obtain a point cloud data set which is uniformly distributed in space on the preset scanning path; the preprocessing step comprises the steps of carrying out local surface feature analysis on a point cloud data set to obtain a curvature value at each sampling point, marking the sampling points with the curvature value exceeding a preset curvature threshold as edge candidate points, carrying out space connectivity analysis on the edge candidate points, eliminating isolated edge candidate points which cannot form a communication area with a main edge, and determining the reserved edge candidate points with continuous distribution features as edge point cloud data; Selecting a plurality of characteristic points from the edge point cloud data, iteratively adjusting the pose of the standard geometric model based on a preset geometric constraint condition, re-determining the integral accumulated deviation between the standard geometric model and the plurality of characteristic points after each adjustment, stopping adjustment when the variation of the integral accumulated deviation after two adjacent adjustments is smaller than a preset convergence threshold, and taking the current standard geometric model as a final fitting result; And a dimension generating step, namely extracting the outline dimension parameter of the glass observation window of the washing machine based on the standard geometric model, wherein the outline dimension parameter comprises at least one of diameter, roundness and curvature radius. As a preferred technical solution of the present invention, the noise filtering processing is performed on the point cloud data set in the preprocessing step, and the method further includes: carrying out statistical analysis on the point cloud data set, determining the average distance between each sampling point and the adjacent point, judging the sampling points with the average distance exceeding the whole distributi