A hierarchical method for detecting and evaluating the grinding status of drill bits

Abstract

This application provides a hierarchical method for detecting and evaluating the grinding status of drill bits, relating to the field of data processing technology. The method includes: determining a preset grinding precision, performing hierarchical profiling, calculating hierarchical correlation coefficients, performing hierarchical multivariate coordinate transformation, supervising and training a precision detection module, determining a spatiotemporal detection point cloud, combining a signal processing model, performing bias correction and local feature enhancement processing, determining distributed surface features, performing overall analysis, determining a precision detection column, and displaying it visually on a terminal. This application addresses the technical problem in existing technologies where the limited precision of manual inspection leads to unstable drill bit surface grinding quality, further affecting drilling accuracy and production efficiency. It effectively performs bias correction and local feature enhancement processing on the spatiotemporal detection point cloud, thereby improving the recognition and accuracy of surface features, optimizing the production process, and improving product quality.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a hierarchical method for detecting and evaluating the grinding status of drill bits. Background Technology

[0002] As a commonly used tool in industrial processing, the surface precision of drill bits directly affects their service life, drilling quality, and processing efficiency. With the rapid development of high-tech and precision manufacturing, the requirements for the grinding precision of drill bit outer surfaces are becoming increasingly stringent. Traditional inspection methods rely heavily on manual experience and simple measuring tools such as magnifying glasses and micrometers. These methods are not only inefficient but also have limited accuracy, failing to meet the high precision requirements of modern industry.

[0003] Currently, existing drill bit outer surface grinding accuracy testing technology mainly relies on manual experience and simple measuring tools, lacking high-precision and automated testing methods.

[0004] In summary, existing technologies suffer from the technical problem of unstable grinding quality of drill bit surfaces due to the limited accuracy of manual inspection, which further affects drilling accuracy and production efficiency. Summary of the Invention

[0005] The purpose of this application is to provide a hierarchical method for detecting and evaluating the grinding status of drill bits, in order to solve the technical problem that the grinding quality of drill bit surfaces is unstable due to the limited accuracy of manual detection in the existing technology, which further affects drilling accuracy and production efficiency. The method effectively performs bias correction and local feature enhancement processing on the spatiotemporal detection point cloud, thereby improving the recognition and accuracy of surface features, optimizing the production process, and improving product quality.

[0006] In view of the above problems, this application provides a hierarchical method for detecting and evaluating the grinding status of drill bits.

[0007] This application provides a hierarchical method for detecting and evaluating the grinding status of drill bits. The method includes: determining a preset grinding precision based on the processing standards of the target drill bit, and performing hierarchical decomposition of precision elements, cascading a precision system, wherein the decomposition hierarchy includes at least an index layer and a feature layer; traversing the cascaded precision system, calculating hierarchical correlation coefficients, and performing hierarchical multivariate coordinate transformation to distribute the baseline coordinates of the preset grinding precision, thus determining a hierarchical detection coordinate system; supervising and training a precision detection module based on the hierarchical detection coordinate system; performing laser scanning and integration on the target drill bit based on spatiotemporal characteristics to determine a spatiotemporal detection point cloud; combining a signal processing model to perform bias correction and local feature enhancement processing on the spatiotemporal detection point cloud to determine distributed surface features, wherein the feature enhancement processing methods include joint detection fitting and algorithm processing; and based on the precision detection module, performing state evaluation and overall analysis on the distributed surface features, determining a precision detection column and displaying it visually on a terminal, wherein the analysis criteria include single-point analysis and time-series trend analysis.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] Based on the processing standards of the target drill bit, a preset grinding precision is determined, and a hierarchical breakdown of precision elements is performed, cascading a precision system. The breakdown hierarchy includes at least an index layer and a feature layer. The cascaded precision system is traversed, hierarchical correlation coefficients are calculated, and hierarchical multivariate coordinate transformation is performed to distribute the baseline coordinates of the preset grinding precision, determining the hierarchical detection coordinate system. Based on the hierarchical detection coordinate system, a precision detection module is trained under supervision. Based on spatiotemporal characteristics, the target drill bit is laser-scanned and integrated to determine a spatiotemporal detection point cloud. Combined with a signal processing model, the spatiotemporal detection point cloud undergoes bias correction and local feature enhancement processing to determine... Distributed surface features, wherein feature enhancement processing methods include joint inspection fitting and algorithm processing; based on the accuracy detection module, the distributed surface features are subjected to state evaluation and overall analysis, the accuracy detection column is determined and displayed on the terminal, wherein the analysis criteria include single-point analysis and time-series trend analysis, which effectively solves the technical problem that the limited accuracy of manual inspection in the existing technology leads to unstable grinding quality of drill bit surface, which further affects drilling accuracy and production efficiency. It effectively performs bias correction and local feature enhancement processing on the spatiotemporal detection point cloud, thereby improving the recognition and accuracy of surface features, optimizing the production process and improving product quality.

[0010] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating a hierarchical drill bit grinding condition detection and evaluation method according to this application.

[0013] Figure 2 This is a flowchart illustrating the process of determining the hierarchical detection coordinate system in the hierarchical drill bit grinding condition detection and evaluation method of this application. Detailed Implementation

[0014] This application provides a hierarchical method for detecting and evaluating the grinding status of drill bits, which solves the technical problem in the prior art where the grinding quality of drill bit surfaces is unstable due to the limited accuracy of manual detection, further affecting drilling accuracy and production efficiency. It effectively performs bias correction and local feature enhancement processing on spatiotemporal detection point clouds, thereby improving the recognition and accuracy of surface features, optimizing the production process, and improving product quality.

[0015] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0016] Example 1

[0017] Please see the appendix Figure 1 This application provides a hierarchical method for detecting and evaluating the grinding status of drill bits, wherein the method specifically includes the following steps:

[0018] S1: Based on the processing standards of the target drill bit, determine the preset grinding accuracy and perform hierarchical analysis of the accuracy elements to form a cascaded accuracy system. The analysis hierarchy includes at least an index layer and a feature layer.

[0019] Specifically, the required grinding precision is determined based on the drill bit's intended use, such as the drilling material and hole diameter. For example, in applications requiring high-precision drilling, the grinding precision requirements are even higher. This ensures the drill bit achieves the expected drilling results, such as hole diameter accuracy and hole wall roughness. The hierarchical breakdown of precision elements decomposes the overall grinding precision requirements into more specific and actionable precision elements, including at least an index layer and a feature layer. The index layer includes specific, quantifiable precision indicators, such as the drill bit's diameter error, roundness error, and surface roughness Ra value. The feature layer includes key factors affecting precision indicators, such as the drill bit's material, hardness, heat treatment state, and machining parameters, such as cutting speed, feed rate, and depth of cut. Based on the interrelationships and dependencies between these precision elements, they are organized into a hierarchical system. In this system, higher-level elements guide and constrain lower-level elements.

[0020] S2: Traverse the cascaded precision system, calculate the hierarchical correlation coefficient, perform hierarchical multivariate coordinate transformation, distribute the baseline coordinates of the preset grinding precision, and determine the hierarchical detection coordinate system.

[0021] Specifically, starting from the top layer of the system, each precision element is traversed layer by layer downwards. For each pair of related precision elements, such as elements between the index layer and the feature layer, their correlation coefficient is calculated. The correlation coefficient reflects the degree of association between two elements, such as the Pearson correlation coefficient and the Spearman rank correlation coefficient. Based on the calculated correlation coefficient, each precision element is converted into a coordinate point in a multidimensional space. The dimension of the coordinates corresponds to the hierarchy and number of elements in the cascaded precision system. During the conversion process, principal component analysis or other dimensionality reduction techniques can be used to simplify the coordinate system. In the converted multidimensional space, a baseline coordinate is determined according to the preset grinding precision requirements. This baseline coordinate represents the position of the drill bit that meets the preset precision requirements in the multidimensional space. By comparing the distance between the actual drill bit's coordinates and the baseline coordinates, the grinding precision of the drill bit can be evaluated. A hierarchical detection coordinate system is established with the baseline coordinate as the center. In this coordinate system, each dimension corresponds to a precision element, and the scale on the coordinate axis represents the precision level of that element.

[0022] S3: Based on the aforementioned hierarchical detection coordinate system, supervise the training accuracy detection module.

[0023] Specifically, historical data on drill bit grinding accuracy is collected, including measurement results of various accuracy indicators. This data is then labeled according to the hierarchical detection coordinate system, clearly defining the position of each data point within the coordinate system. The labeled data is then formatted into a dataset suitable for training machine learning models. The dataset should include input features, such as measured values ​​of various accuracy indicators and corresponding output labels, such as their position or accuracy level in the hierarchical detection coordinate system. A suitable supervised learning model is selected, such as a support vector machine, random forest, or neural network. The model is trained using the constructed training dataset, enabling it to learn the mapping relationship from input features to output labels. The trained model is evaluated using a validation set to check its prediction accuracy and generalization ability. Based on the evaluation results, the model is adjusted and optimized, such as adjusting model parameters, changing model structure, or trying different algorithms.

[0024] S4: Based on spatiotemporal characteristics, perform laser scanning and integration on the target drill bit to determine the spatiotemporal detection point cloud.

[0025] Specifically, the target drill bit is fixed within the scanner's working area, ensuring stable lighting in the scanning environment and avoiding interference from external light sources. A laser scanner is used to scan the drill bit 360 degrees to obtain three-dimensional data of its surface. Multiple scans can be performed at different time points, and the data from these scans are integrated to form a unified spatiotemporal point cloud dataset. Registration algorithms, such as ICP, are used to align the scan data from different time points to the same coordinate system. Preprocessing, such as denoising and smoothing, is applied to the spatiotemporal point cloud data to improve its accuracy and readability. Data compression algorithms are then used to compress the spatiotemporal point cloud data to reduce its volume and improve processing efficiency.

[0026] S5: Combining the signal processing model, bias correction and local feature enhancement processing are performed on the spatiotemporal detection point cloud to determine the distributed surface features. The feature enhancement processing methods include joint detection fitting and algorithm processing.

[0027] Specifically, the process involves analyzing point cloud data to identify systematic errors caused by scanning equipment or environmental factors. Geometric transformations or mathematical models are used to correct the point cloud data, eliminating or reducing biases. For example, affine or nonlinear transformations can be used to adjust the position and orientation of the point cloud. The point cloud is segmented into multiple local regions, and surface features such as edges, corners, and bumps are extracted within each region. Algorithms are applied to enhance these features, making them more prominent. For example, high-pass filters can be used to enhance edge features, or morphological operations can be used to enhance specific geometries. Scanning data from different time points or different viewpoints are fused. Fitting algorithms, such as least squares, are used to smooth and integrate the data. Based on the fitting results, the point cloud data is optimized, such as removing outliers and filling in missing data. Machine learning or deep learning algorithms are used to perform feature recognition on the enhanced point cloud data, classifying and labeling different surface features.

[0028] S6: Based on the accuracy detection module, perform state evaluation and assembly analysis on the distributed surface features, determine the accuracy detection column and perform terminal visualization display, wherein the analysis criteria include single-point analysis and time-series trend analysis.

[0029] Specifically, the extracted surface features are categorized as acceptable or unacceptable. Each feature is quantitatively evaluated using specific numerical indicators such as roughness and shape error to describe its state. The evaluation results of all features are combined to comprehensively assess the surface accuracy of the entire drill bit. The interactions between various features and their impact on overall accuracy are analyzed. Detailed analysis is performed on individual feature points or local areas to identify potential problem points or anomalies. For identified problem points, possible causes are analyzed, such as material issues or improper processing parameters. Time-series analysis is performed on data from multiple scans to monitor the changing trends of surface features over time, and based on historical data, future possible changes in accuracy are predicted. The results of the state assessment and overall analysis are recorded in a separate inspection column. Three-dimensional visualization technology is used to visually display the distributed surface features and inspection results on the terminal interface.

[0030] Furthermore, such as Figure 2 As shown, step S2 of this application further includes:

[0031] A cross-layer arbitrary element group is determined, wherein the element group is a feature-indicator or an indicator-precision; based on the element group and in combination with relevant calculation formulas, the correlation between elements in the layers is calculated to determine the correlation coefficient set; a first-layer coordinate system is determined with precision as the origin and multi-dimensional indicators as the coordinate axes, and a second-layer coordinate system is determined with indicators as the origin and multi-dimensional features as the coordinate axes, wherein the second-layer coordinate system includes multiple systems; the first-layer coordinate system and the second-layer coordinate system are fused to determine the hierarchical detection coordinate system.

[0032] Specifically, the specific features of the feature layer, such as surface texture and ripples, are correlated with the quantitative indicators of the indicator layer, such as roughness and shape error, to form feature-indicator element groups. The quantitative indicators of the indicator layer are then correlated with the final polishing accuracy requirements to form indicator-precision element groups. The correlation between the feature-indicator element groups and the indicator-precision element groups is calculated using relevant formulas. A set of correlation coefficients is determined, reflecting the interrelationships and influences between elements at different levels. A first-level coordinate system is established with precision as the origin and the multi-dimensional indicators of the indicator layer as the coordinate axes. This coordinate system can be represented as a point in a multi-dimensional space, with each dimension corresponding to an indicator. A second-level coordinate system is established for each indicator, with each indicator as the origin and the multi-dimensional features of the feature layer as the coordinate axes. Thus, each indicator has an independent coordinate system to describe its associated features. The first-level and second-level coordinate systems are merged to form a comprehensive hierarchical detection coordinate system. This coordinate system integrates information from the precision, indicator, and feature levels, providing a comprehensive reference framework. Within this coordinate system, the impact of different elements on overall precision can be analyzed and evaluated through layer transformations and coordinate point movements.

[0033] Furthermore, this application also includes:

[0034] Obtain the relevant calculation formula:

[0035] ;

[0036] in, The correlation coefficient of the feature group. , For the element group used to perform correlation calculations, The total number of samples for the feature group. , There is a one-to-one correspondence; For the first item sample, For the first item sample, as elements The sample mean, as elements The sample mean; where the sample acquisition standard is continuous samples under time-series polishing.

[0037] Specifically, for continuous samples under time-series grinding, multiple measurements are taken at different time points on the same or multiple drill bits to capture changes in the grinding process. For example, to calculate the correlation coefficient between roughness and surface texture, a series of measurement data is collected, where each data point contains the values ​​of both elements. Then, these data points are substituted into the formula mentioned above to calculate the correlation coefficient.

[0038] Furthermore, this application also includes:

[0039] The surface geometry of the target drill bit is identified, and pre-detection points are set based on a preset step size, wherein the pre-detection points include key detection points and step size setting points; based on the pre-detection points, a scanning trajectory is determined, and based on the material properties of the target drill bit, scanning parameters are determined; based on the scanning trajectory and the scanning parameters, a laser scanner is controlled to scan and detect the target drill bit.

[0040] Specifically, the process involves analyzing the feedback signals from the laser point cloud. Through analysis, various features and other information can be determined, and geometric structure analysis is performed based on the point cloud distribution. Key detection points are set on critical geometric features of the drill bit, focusing on key areas of surface quality, such as the cutting edge. A series of detection points are uniformly set along the drill bit surface based on a preset step size. The step size depends on the required detection accuracy and scanning time. The laser scanner's movement trajectory is planned according to the location of the pre-detection points, ensuring the scanning trajectory covers all pre-detection points and maintains a stable scanning speed and direction during the scanning process. The material properties of the target drill bit, including reflectivity and surface roughness, affect the laser scanning results. The laser scanner parameters, including laser power, scanning speed, and resolution, are adjusted according to these material properties. Scanning control software or an automated control system is used to control the laser scanner based on the scanning trajectory and parameters. The scanning detection is then performed, collecting data from the target drill bit surface.

[0041] Furthermore, this application also includes:

[0042] A multi-level step size is determined, and a measurement point distributor is trained. To assist the measurement point distributor, multiple initial detection points are randomly determined based on the surface geometry, wherein the initial detection points satisfy the dispersion requirement. Based on the multi-level step size, any step size level is randomly determined, and point expansion and progressive iteration are performed on any initial detection point until the surface coverage is satisfied, thus determining the pre-detection points. The pre-detection points exhibit a difference-frequency distribution based on time nodes under time characteristics.

[0043] Specifically, based on the surface geometry of the drill bit and the inspection requirements, multiple different step size levels are determined. Each step size level represents a different inspection accuracy; the smaller the step size, the higher the inspection accuracy. A measurement point distributor model is trained using machine learning or deep learning techniques. This model learns how to generate initial inspection points with specific dispersion requirements based on the surface geometry of the drill bit. Using the trained measurement point distributor, multiple initial inspection points are randomly determined based on the surface geometry of the drill bit. These initial inspection points should meet the dispersion requirements to ensure coverage of all critical areas of the drill bit. Starting from any initial inspection point, the points are expanded outward according to the current step size level. If the inspection points at the current step size level do not cover all critical areas, the step size level is increased, and the point expansion is repeated. This process is repeated until the surface coverage requirements are met. At each step size level, pre-inspection points are finally determined. These pre-inspection points will be used for subsequent laser scanning and accuracy inspection. Under time characteristics, the pre-inspection points will be distributed according to the difference frequency at different time points to adapt to the surface condition of the drill bit at different processing stages.

[0044] Furthermore, step S5 of this application also includes:

[0045] By identifying signal defects from historical laser detection, a preset processing mode is determined, wherein each processing mode is identified by a parallel processing capacity. Based on the preset processing mode, processing blocks are independently trained to determine multiple signal processing blocks. The multiple signal processing blocks are integrated, and operator resources are allocated based on the parallel processing capacity to generate the signal processing model.

[0046] Specifically, the process involves collecting and organizing past laser detection signal data, including all known signal defects and anomalies. This data is then analyzed to identify common signal defect patterns and characteristics. Based on the identified signal defects, different preset processing modes are defined, each corresponding to a specific signal defect type, and its parallel processing capacity is identified. Each processing mode is independently trained based on these preset modes to identify and process the corresponding signal defects. Machine learning algorithms, such as deep learning and support vector machines, are used for training to improve the accuracy and efficiency of signal processing. The trained processing blocks are integrated into a single signal processing model. Operator resources are allocated according to the preset parallel processing capacity to optimize the model's efficiency and processing power. The performance of the signal processing model is validated using unlabeled data or cross-validation methods. Based on the validation results, the model is optimized, including adjusting parameters and adding or removing processing blocks.

[0047] Furthermore, this application also includes:

[0048] Based on the accuracy detection module, the distributed surface features are distributed according to the two-layer coordinate system. Based on the baseline coordinates, the feature coordinates are mapped and differentially measured to measure the feature detection coefficients. Based on the hierarchical mapping of the hierarchical detection coordinate system, combined with the hierarchical correlation coefficient, the feature detection coefficients are calculated once to determine the index detection coefficients. Combined with the hierarchical correlation coefficient, the index detection coefficients are calculated twice to determine the overall detection coefficients. The overall analysis includes the overall analysis of each detection point and the spatial globality.

[0049] Specifically, a two-layer coordinate system is used to locate the coordinates of each distributed surface feature. These coordinates reflect the spatial distribution and relative position of the features on the drill bit surface. The feature coordinates are mapped to the baseline coordinates to determine the actual and relative positions of the features. The difference between the feature coordinates and the baseline coordinates is measured to calculate the deviation of the feature relative to the baseline, measuring the feature detection coefficient, which reflects the difference between the feature and the preset standard. Using the hierarchical mapping of the hierarchical detection coordinate system, the feature detection coefficient is correlated with the coordinates of the index layer and the feature layer. Combined with the hierarchical correlation coefficient, a first overall calculation is performed on the feature detection coefficient to obtain the index detection coefficient. The index detection coefficient reflects the relationship between the feature and the index layer. A second overall calculation is performed on the index detection coefficient to obtain the overall detection coefficient. The overall detection coefficient is a comprehensive result of the feature detection coefficient, the index detection coefficient, and the hierarchical correlation coefficient, reflecting the final difference between the feature and the preset standard. An overall analysis is performed on each detection point to evaluate its deviation from the preset standard. A spatial global analysis is conducted to ensure that the detection points in each region of the drill bit surface meet the preset standard.

[0050] Furthermore, this application also includes:

[0051] Based on the detection steps, the detection link is determined; according to the detection link, the data dimension and coefficient dimension are integrated into a link-based manner to determine the mapping link group; the results of the mapping link group are calibrated and added to the accuracy detection column.

[0052] Specifically, this involves identifying and defining all steps related to drill bit surface grinding accuracy inspection, including laser scanning, signal processing, feature extraction, and accuracy assessment. A complete inspection chain is constructed, describing the entire process from data acquisition to result output. Each step is ensured to be tightly connected to subsequent steps, forming a coherent flow. The positions and relationships of data and coefficient dimensions within the inspection chain are determined, and a mapping chain group is constructed to integrate the data and coefficient dimensions in a chain-like manner. The results of each inspection step are calibrated, including error analysis, correction processing, and quality control. The calibrated results are added to a precision inspection column, which contains all key information such as inspection time, personnel, equipment, and results.

[0053] In summary, the hierarchical drill bit grinding condition detection and evaluation method provided in this application has the following technical effects:

[0054] Based on the processing standards of the target drill bit, a preset grinding precision is determined, and a hierarchical breakdown of precision elements is performed, cascading a precision system. The breakdown hierarchy includes at least an index layer and a feature layer. The cascaded precision system is traversed, hierarchical correlation coefficients are calculated, and hierarchical multivariate coordinate transformation is performed to distribute the baseline coordinates of the preset grinding precision, determining the hierarchical detection coordinate system. Based on the hierarchical detection coordinate system, a precision detection module is trained under supervision. Based on spatiotemporal characteristics, the target drill bit is laser-scanned and integrated to determine a spatiotemporal detection point cloud. Combined with a signal processing model, the spatiotemporal detection point cloud undergoes bias correction and local feature enhancement processing to determine... Distributed surface features, wherein feature enhancement processing methods include joint inspection fitting and algorithm processing; based on the accuracy detection module, the distributed surface features are subjected to state evaluation and overall analysis, the accuracy detection column is determined and displayed on the terminal, wherein the analysis criteria include single-point analysis and time-series trend analysis, which effectively solves the technical problem that the limited accuracy of manual inspection in the existing technology leads to unstable grinding quality of drill bit surface, which further affects drilling accuracy and production efficiency. It effectively performs bias correction and local feature enhancement processing on the spatiotemporal detection point cloud, thereby improving the recognition and accuracy of surface features, optimizing the production process and improving product quality.

[0055] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0056] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A hierarchical drill bit dullness detection assessment method, comprising: The method comprises: Based on the machining standard of the target drill bit, the preset polishing precision is determined, and the hierarchical resolution of the precision elements is carried out, and the cascade precision system is obtained, wherein the resolution level at least includes the index layer and the feature layer; Traverse the cascade precision system, calculate the hierarchical correlation coefficient, and perform hierarchical multivariate coordinate conversion to distribute the baseline coordinates of the preset polishing precision, and determine the hierarchical detection coordinate system; Based on the hierarchical detection coordinate system, the precision detection module is supervised and trained; Based on the space-time characteristics, the target drill bit is scanned and integrated by laser to determine the space-time detection point cloud; Combined with the signal processing model, the space-time detection point cloud is corrected and locally enhanced to determine the distributed surface features, wherein the feature enhancement processing method includes joint inspection fitting and algorithm processing; Based on the precision detection module, the distributed surface features are state evaluated and assembly analyzed to determine the precision detection single column and perform terminal visual display, wherein the analysis standard includes single point analysis and time series trend analysis; The determination of the hierarchical detection coordinate system comprises: Cross-layer determination of any element group, the element group is feature-index, index-precision; Based on the element group, the correlation calculation of the interlayer elements is carried out combined with the related calculation formula to determine the correlation coefficient set; Taking the polishing precision as the origin and the multivariate index as the coordinate axis, a one-layer coordinate system is determined, and taking each index as the origin and the multivariate feature as the coordinate axis, a two-layer coordinate system is determined, the two-layer coordinate system includes multiple; Fusion of the one-layer coordinate system and the two-layer coordinate system to determine the hierarchical detection coordinate system; Constructing a signal processing model comprises: Excavate the signal defects of historical laser detection to determine different preset processing modes, each processing mode corresponds to a specific signal defect type, and the parallel processing amount is identified; Based on the preset processing mode, each processing mode is independently trained to identify and process the corresponding signal defect; Integrate the trained processing blocks into a signal processing model, allocate operator resources based on the parallel processing amount, and generate the signal processing model; The analysis standard includes single point analysis, and the single point analysis is the precision analysis of the polishing result, which comprises: Based on the precision detection module, the feature coordinate distribution of the distributed surface features based on the two-layer coordinate system is carried out, the feature coordinates are mapped and measured based on the baseline coordinates, and the feature detection coefficient is measured; Based on the hierarchical mapping of the hierarchical detection coordinate system, combined with the hierarchical correlation coefficient, the feature detection coefficient is once assembly calculated to determine the index detection coefficient; Combined with the hierarchical correlation coefficient, the index detection coefficient is twice assembly calculated to determine the assembly detection coefficient; Wherein, the assembly analysis includes each detection point assembly and spatial globality.

2. A method of evaluating the state of a drill bit according to claim 1, wherein The method comprises: Obtain the related calculation formula: ； wherein, is the correlation coefficient of the element group, , is the element group for which the correlation is calculated, is the total number of samples of the element group, the samples , there is a one-to-one correspondence; is the first item sample, is the first item sample, is the sample mean of the element , is the sample mean of the element ; Wherein, the sample acquisition standard is the continuous sample under time series polishing.

3. A method of evaluating the state of a drill bit being dressed according to claim 1, wherein, Before laser scanning the target drill bit, it comprises: Identify the surface geometric distribution of the target drill bit, set the pre-detection points based on the preset step length, wherein the pre-detection points include key detection points and step length setting points; Determine a scanning track based on the pre-detection points and determine scanning parameters based on material characteristics of the target drill bit; Control the laser scanner to perform scanning detection on the target drill bit based on the scanning track and the scanning parameters.

4. A method of hierarchical bit dressing condition detection assessment as claimed in claim 3, wherein, The pre-detection points are determined based on a preset step length, which includes: Determine a multi-level step length and train a measurement point distributor; Randomly determine a plurality of initial detection points based on the surface geometry distribution with the assistance of the measurement point distributor, wherein the initial detection points meet the dispersion requirement; Randomly determine a step length level based on the multi-level step length, and perform point expansion and progressive iteration on any initial detection point until the surface coverage degree is met to determine the pre-detection points; Wherein, under the time characteristic, there is a pre-detection point difference frequency distribution based on the time node.

5. The method of claim 1, wherein the method further comprises: It includes: Determine a detection link based on the detection step; According to the detection link, perform link integration of data dimension and coefficient dimension to determine a mapping link group; Calibrate the mapping link group to add to the precision detection single column.

Images