CN-121978116-A - Intelligent detection method for refractory brick production line

CN121978116ACN 121978116 ACN121978116 ACN 121978116ACN-121978116-A

Abstract

The invention relates to the technical field of refractory materials, in particular to an intelligent detection method for a refractory brick production line, which comprises the steps of detecting a refractory brick rough blank after a firing procedure, obtaining brick body information and an environmental definition index, calculating a characteristic defect index for representing the severity of defects, a characteristic pose index for representing the risk of a defect position and a characteristic confidence coefficient for representing the reliability of data, judging the reliability of the data by comparing the characteristic confidence coefficient with a preset threshold value, determining to execute a cooling operation strategy if the data is reliable, and determining a final cooling parameter according to the comparison result of the characteristic defect index and the characteristic pose index; if the data is unreliable, determining to execute a detection optimization strategy, and detecting after self-optimizing by a detection system to obtain reliable brick information. According to the invention, through performing data reliability pre-evaluation and accurate regulation and control of cooling parameters, the quality consistency, the yield and the intelligent level of a production line of refractory brick production are ensured.

Inventors

LI SHUANGYAN
ZHANG WEI
ZHANG XING
SU SANG

Assignees

冷水江市中孚新材料有限责任公司

Dates

Publication Date: 20260505
Application Date: 20260402

Claims (10)

1. An intelligent detection method for a refractory brick production line is characterized by comprising the following steps: Detecting the rough blank of the refractory brick to obtain brick information and definition indexes; Determining a characteristic defect index and a characteristic pose index based on the brick body information, wherein the brick body information comprises surface layer defect information and pose information; determining a feature confidence based on the definition index, wherein the definition index comprises a first definition index and a second definition index; judging whether the brick information is reliable or not based on the comparison result of the feature confidence and the preset feature confidence, and generating a corresponding control strategy based on the judgment result, If the brick information is determined to be reliable, determining to execute a cooling operation strategy, wherein the execution process comprises determining whether to adjust cooling parameters based on a comparison result of the characteristic defect index and a corresponding preset characteristic index, and adjusting the cooling parameters based on a comparison result of the characteristic pose index and the corresponding preset characteristic index when determining to adjust the cooling parameters, wherein the cooling parameters comprise cooling time and cooling rate, and the preset characteristic index comprises a preset defect index and a preset pose index; If the brick information is determined to be unreliable, determining to execute a detection optimization strategy to obtain an optimization feature defect index and an optimization feature pose index, re-determining whether to adjust the cooling parameters based on the comparison result of the optimization feature defect index and the preset feature index, and adjusting the cooling parameters based on the comparison result of the optimization feature pose index and the preset feature index.
2. The intelligent detection method for a refractory brick production line according to claim 1, wherein the process of determining whether the brick information is reliable based on the comparison result of the feature confidence and a preset feature confidence comprises: If the feature confidence coefficient is larger than the preset feature confidence coefficient, judging that the brick information is reliable, and determining to execute the cooling operation strategy; and if the feature confidence is smaller than or equal to the preset feature confidence, judging that the brick information is unreliable, and determining to execute the detection optimization strategy.
3. The intelligent detection method for a refractory brick production line according to claim 2, wherein the process of executing the cooling operation strategy comprises: If the characteristic defect index is smaller than or equal to the preset defect index, determining an initial cooling parameter as a final cooling parameter; And if the characteristic defect index is larger than the preset defect index, determining whether to adjust the initial cooling parameter or not based on a comparison result of the characteristic pose index and the preset pose index.
4. The intelligent detection method for a refractory brick production line according to claim 3, wherein if the characteristic pose index is less than or equal to the preset pose index, determining a final cooling parameter as the initial cooling parameter; and if the characteristic pose index is larger than the preset pose index, adjusting the initial cooling parameters to obtain finally determined cooling parameters.
5. The intelligent detection method for a refractory brick production line of claim 4, wherein the adjusting the initial cooling parameters to obtain the final determined cooling parameters includes: calculating the difference value between the characteristic pose index and the preset pose index and marking the difference value as a first pose difference value; and determining the adjustment amplitude of the initial cooling parameter based on the first pose difference value, wherein the extension amplitude of the cooling time is positively correlated with the first pose difference value, and the reduction amplitude of the cooling rate is positively correlated with the first pose difference value.
6. The intelligent inspection method for a refractory brick production line of claim 2, wherein the determining to execute the inspection optimization strategy to obtain an optimized characteristic defect index and an optimized characteristic pose index comprises: Performing a corresponding detection optimization operation based on determining that the brick information is unreliable, wherein the detection optimization operation comprises increasing the number of sensors or switching a feature recognition algorithm or adjusting sensor parameters or enabling auxiliary illumination; Determining the optimized characteristic defect index and the optimized characteristic pose index based on the brick information re-acquired after the detection and optimization operation; And executing the cooling operation strategy based on the optimized feature defect index and the optimized feature pose index.
7. The intelligent detection method for a refractory brick production line of claim 6, wherein the process of executing the cooling operation strategy based on the optimized characteristic defect index and the optimized characteristic pose index comprises: If the optimized characteristic defect index is smaller than or equal to the preset defect index, determining an initial cooling parameter as a final cooling parameter; And if the optimized characteristic defect index is larger than the preset defect index, determining whether to adjust the initial cooling parameter or not based on a comparison result of the optimized characteristic pose index and the preset pose index.
8. The intelligent detection method for a refractory brick production line according to claim 7, wherein if the optimized feature pose index is less than or equal to the preset pose index, determining a final cooling parameter as the initial cooling parameter; if the optimized feature pose index is larger than the preset pose index, calculating a difference value between the optimized feature pose index and the preset pose index and marking the difference value as a second pose difference value; and determining the adjustment amplitude of the initial cooling parameter based on the second position difference value, wherein the extension amplitude of the cooling time is positively correlated with the second position difference value, and the reduction amplitude of the cooling rate is positively correlated with the second position difference value.
9. The intelligent detection method for a refractory brick production line according to claim 1, wherein the process of determining a characteristic defect index and a characteristic pose index based on the brick body information comprises: The detection system comprises a first visual detection mechanism and a second visual detection mechanism; Obtaining the surface layer defect information through the first visual detection mechanism, wherein the surface layer defect information at least comprises one of crack defect data or hole defect data; And obtaining pose information through the second visual detection mechanism, wherein the pose information at least comprises position information corresponding to the crack defect data or the hole defect data on the refractory brick rough blank.
10. The intelligent detection method for a refractory brick production line according to claim 1, wherein the determining feature confidence based on the sharpness index comprises: The feature confidence is determined by weighting calculation based on the first definition index and the second definition index; The first definition index is obtained based on the evaluation of the image quality of the brick information, wherein the image quality evaluation comprises the calculation of image contrast and image sharpness; The second definition index is obtained based on evaluation of a detection environment for collecting the brick body information, wherein the detection environment evaluation comprises calculation of a dust concentration index and an ambient light interference index.

Description

Intelligent detection method for refractory brick production line Technical Field The invention relates to the technical field of refractory materials, in particular to an intelligent detection method for a refractory brick production line. Background With the development of intelligent manufacturing technology, the introduction of an automatic detection system to replace traditional manual visual inspection in a production line has become an industry trend. The prior art generally focuses on defect identification and size measurement of the fired refractory brick blank by means of machine vision, laser scanning and the like. For example, some schemes adopt an image processing algorithm to identify surface cracks and carry out simple classification and alarm according to the length, width and other characteristics of the cracks, and other schemes acquire blank point cloud data through three-dimensional scanning and compare the blank point cloud data with a standard CAD model to detect out-of-tolerance of the external dimension. CN115954135A discloses an intelligent control method and system for refractory brick production line, and related technical schemes aim at realizing monitoring and regulation of production process by dividing production process, optimizing process and detecting process and constructing negative feedback and positive feedback paths. However, the above scheme still has the problem that the prior art scheme usually defaults to the detection equipment to work under a constant ideal environment, and the detection result is directly acquired, so that the defect misjudgment, omission or misalignment of the dimension measurement is easily caused. Meanwhile, the existing method is limited to the geometric characteristics of the brick body, but the defects cannot be placed in the overall structure of the blank body and under the stress background for risk assessment, and the defects are not in closed-loop linkage with a downstream cooling and other process detection control system. Therefore, an intelligent detection method capable of intelligently evaluating the reliability of the detection data and converting the multi-dimensional defect information into a process adjustment instruction is urgently needed to improve the quality control level and the automation degree of the refractory brick production line. Disclosure of Invention Therefore, the invention provides an intelligent detection method for a refractory brick production line, which is used for solving the problems that in the prior art, the reliability of detection data cannot be ensured due to environmental influence factors, and defect position risk factors are not considered in defect evaluation. In order to achieve the above object, the present invention provides an intelligent detection method for a refractory brick production line, comprising: Detecting the rough blank of the refractory brick to obtain brick information and definition indexes; Determining a characteristic defect index and a characteristic pose index based on the brick body information, wherein the brick body information comprises surface layer defect information and pose information; determining a feature confidence based on the definition index, wherein the definition index comprises a first definition index and a second definition index; judging whether the brick information is reliable or not based on the comparison result of the feature confidence and the preset feature confidence, and generating a corresponding control strategy based on the judgment result, If the brick information is determined to be reliable, determining to execute a cooling operation strategy, wherein the execution process comprises determining whether to adjust cooling parameters based on a comparison result of the characteristic defect index and a corresponding preset characteristic index, and adjusting the cooling parameters based on a comparison result of the characteristic pose index and the corresponding preset characteristic index when determining to adjust the cooling parameters, wherein the cooling parameters comprise cooling time and cooling rate, and the preset characteristic index comprises a preset defect index and a preset pose index; If the brick information is determined to be unreliable, determining to execute a detection optimization strategy to obtain an optimization feature defect index and an optimization feature pose index, re-determining whether to adjust the cooling parameters based on the comparison result of the optimization feature defect index and the preset feature index, and adjusting the cooling parameters based on the comparison result of the optimization feature pose index and the preset feature index. Further, the process of determining whether the brick information is reliable based on the comparison result of the feature confidence and the preset feature confidence includes: If the feature confidence coefficient is larger than the preset feature conf