Diamond drill bit quality detection method based on multidimensional parameter analysis

Abstract

The invention discloses a diamond bit quality detection method based on multidimensional parameter analysis, and relates to the technical field of quality detection.The method comprises the steps that a function detection tree is constructed through function loss incidence relation analysis, and a root node is appearance detection; and directional data acquisition is carried out according to the root node to obtain single-dimensional detection data, and quality detection analysis is carried out. And if the function detection is passed, data acquisition and analysis of the second-level child nodes are continued according to the detection tree, and a second-level detection result is output. And whether third-level child node detection continues to be executed or not is judged according to the second-level detection result. The detection result of each level determines the execution of the next step, so that the quality defect information set of the diamond drill bit is output step by step, redundant detection is avoided, and the detection efficiency is improved. The technical problems that an existing diamond drill bit quality detection process is tedious, detection resources are wasted and inaccurate are solved, and the technical effect of improving the detection efficiency and accuracy is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of quality detection, and in particular to a diamond drill bit quality detection method based on multi-dimensional parameter analysis. Background Art

[0002] Diamond drill bits are widely used in drilling, cutting and other fields due to their high strength, wear resistance and impact resistance. Their quality directly affects drilling efficiency and safety. Traditional quality inspection methods usually rely on single inspection items, such as appearance inspection, hardness testing and cutting performance testing. These methods are cumbersome and inefficient when faced with complex drill bit structures and multi-functional inspections. The existing technology has the problem of wasting time and resources in the inspection process, especially in the detection of loss of function, the inspection process fails to be accurate and efficient. How to reduce unnecessary inspections and waste of resources while improving inspection accuracy and efficiency has become a key challenge in the production process of diamond drill bits.

[0003] At present, relevant technologies have the following technical problems: the quality inspection process of diamond drill bits is complicated, the inspection resources are wasted, and the inspection is inaccurate. Summary of the invention

[0004] The present application solves the technical problems of the existing diamond drill bit quality inspection process being cumbersome, wasteful of inspection resources and inaccurate by providing a diamond drill bit quality inspection method with multi-dimensional parameter analysis.

[0005] The present application provides a diamond drill bit quality detection method based on multi-dimensional parameter analysis, comprising: The diamond drill bit is analyzed for function loss correlation, and a function detection tree is constructed based on the analysis results, wherein the root node of the function detection tree is the appearance detection; the root node is used as the starting point for quality detection, and the detection data of the diamond drill bit is collected in a directional manner according to the function detection items of the root node to obtain single-dimensional detection data; the diamond drill bit is subjected to quality detection analysis based on the single-dimensional detection data, and the function detection result is output; if the function detection result is passed, the detection data of N secondary sub-nodes are collected under the guidance of the function detection tree, and based on the obtained The diamond drill bit is subjected to quality inspection and analysis based on N-dimensional inspection data, and N secondary inspection results are output; the out-degree connection relationship between the N secondary child nodes and the M tertiary child nodes in the function inspection tree is used as a criterion for judging whether the quality inspection continues to be performed, and the function inspection of the M tertiary child nodes is performed based on the pass identification of the N secondary inspection results, wherein N and M are positive integers and N<M; and by analogy, the quality inspection execution judgment is performed based on the inspection results of the previous level child nodes in the function inspection tree, and a quality defect information set of the diamond drill bit is output.

[0006] The diamond drill bit quality detection method proposed in this application for multi-dimensional parameter analysis first constructs a function detection tree through function loss association analysis, in which the root node is the appearance detection. Directional data collection is performed according to the root node to obtain single-dimensional detection data, and quality detection analysis is performed. If the function test passes, the data collection and analysis of the secondary sub-nodes are continued according to the detection tree, and the secondary detection results are output. Whether to continue to perform the tertiary sub-node detection is determined based on the secondary detection results. The detection results of each level determine the execution of the next step, thereby gradually outputting the quality defect information set of the diamond drill bit, avoiding redundant detection, and improving detection efficiency. The detection process is optimized through function loss association analysis, and unnecessary detection items are reduced, thereby achieving the technical effect of improving detection efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0008] Figure 1 A schematic flow chart of a diamond drill bit quality detection method based on multi-dimensional parameter analysis provided in an embodiment of the present application.

[0009] Figure 2 A schematic diagram of the detection model activation tree construction process of a diamond drill bit quality detection method based on multi-dimensional parameter analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0011] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0012] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0013] The present application embodiment provides a diamond drill bit quality detection method based on multi-dimensional parameter analysis, such as Figure 1 As shown, the method includes: Step S100, analyze the relationship between loss of function of the diamond drill bit, and construct a function detection tree based on the analysis results, wherein the root node of the function detection tree is the appearance detection. Specifically, when constructing the function detection tree of the diamond drill bit, first determine the appearance detection as the root node, because it is intuitive and simple, and can preliminarily evaluate the quality of the drill bit. Then analyze the relationship between loss of function, for example, the decrease in hardness will affect the wear resistance, and the inaccurate cutting edge angle will lead to reduced cutting efficiency. Then determine the secondary child node according to the association, such as the appearance defect is related to the internal structure integrity, and the coating integrity is related to the corrosion resistance, so the internal structure integrity detection and the corrosion resistance detection are set as the secondary child nodes. Then construct the subsequent levels, such as the failure of the internal structure integrity detection will affect the uniformity of the force distribution, and the force distribution uniformity detection can be used as its third-level child node; poor corrosion resistance will affect the service life, and the service life detection can be used as the third-level child node of the corrosion resistance detection. Finally, by setting the logical relationship between nodes "if it fails, no subsequent detection will be performed", the detection efficiency is ensured and unnecessary detection is avoided.

[0014] In a possible implementation, a function loss correlation analysis is performed on the diamond drill bit, and a function detection tree is constructed based on the analysis results, wherein the root node of the function detection tree is the appearance detection, and step S100 further includes step S110, using systematic sampling to sample the diamond drill bit from the drill bit production line. Specifically, the rules and intervals of the systematic sampling are determined. For example, representative diamond drill bit samples are selected from the drill bit production line at a certain interval (such as 1 drill bit is selected for every 50 drill bits produced). The randomness and uniformity of the sampling can be guaranteed, so that the sampled samples can reflect the product quality characteristics of the entire production line. During the sampling process, it is necessary to ensure that the sampling environment and operation meet the specifications to avoid introducing additional errors or deviations due to improper sampling, thereby providing reliable basic data for subsequent testing and analysis.

[0015] Step S120, interactively obtain the batch production use scenario of the drill bit production line, and obtain the use scenario setting by collecting extreme use data for the batch production use scenario. Specifically, communicate and exchange with multiple parties such as the production department, sales department, and actual users to collect information about the use of the drill bit under different working conditions, including but not limited to geological conditions (such as soft rock, hard rock, mixed formation, etc.), drilling depth, drilling fluid type, speed and torque requirements. Then, sort out and analyze the batch production use scenarios to find out the most extreme use scenarios. For example, if the drill bit of this model is used for drilling shallow soft soil formations and mining deep hard rock formations, then the use scenario of deep hard rock formations with high speed and high torque is determined as an extreme use scenario. For extreme use scenarios, data acquisition equipment and sensors are used to monitor and record various performance parameters of the drill bit in this scenario (such as stress conditions, wear degree, temperature changes, etc.) in real time, so as to obtain detailed extreme use data. By sorting and summarizing the extreme usage data, we determine the usage scenario settings that can cover the worst working conditions to ensure the rigor and comprehensiveness of subsequent testing, so that the test results can reflect the performance of the drill bit under various actual usage conditions, providing a strong basis for product quality evaluation.

[0016] Step S130, according to the use scenario setting, network data call is performed to obtain the detection item set of the diamond drill bit, wherein the detection item set includes H kinds of functional detection items, wherein H is a positive integer greater than M. Specifically, according to the determined use scenario setting, a connection is made to a relevant database or network platform, which contains information resources such as standard detection items in the industry, previous detection experience data of similar products, and technical reports issued by professional research institutions. By inputting the key parameters of the use scenario (such as formation hardness, drilling depth, etc.) as search conditions, the detection item information closely related to the current diamond drill bit in the use scenario is filtered out from the massive data. For example, in the use scenario of extreme hard rock formations, hardness detection, wear resistance detection, impact resistance detection and other items will be screened out; for scenarios with high speed requirements, cutting performance detection and dynamic balance detection and other items will also be included. After integration and screening, we finally obtained a test item set that includes H types of functional test items. The test items will comprehensively cover various performance challenges that the drill bit may face in the set usage scenarios, and provide detailed test indicators and directions for subsequent quality inspections, ensuring that all functions of the product can be fully evaluated and verified to meet the needs of actual use and improve the reliability and applicability of the product.

[0017] Step S140, using the test item set as a constraint call to obtain historical functional defect records. Specifically, the test item set obtained above is used as a key constraint condition, and the information sources such as the quality database within the enterprise, customer feedback records, and the fault case library in the industry are accessed again. In the data source, according to the category and specific requirements of the test items, the historical functional defect records related to the H types of functional test items of the current diamond drill bit are searched and extracted. For example, if the test item set includes hardness testing, then the problem description, defect cause analysis, and solution measures of previous products in terms of hardness are found from the historical data; for cutting performance testing, case information of poor cutting performance caused by problems such as cutting edge design, material selection, or processing technology in the past is collected. Through targeted query and screening, detailed historical functional defect records are obtained, which will provide valuable experience data and reference basis for subsequent functional loss correlation analysis, help identify potential risks and weak links that may exist in different functional aspects of the product, so that in the process of quality inspection and improvement, effective prevention and improvement measures can be taken to improve the overall quality level of the product.

[0018] Step S150, analyze the functional loss association relationship of the detection item set according to the historical functional defect records, and construct the functional detection tree based on the analysis results. Specifically, statistical analysis and data mining are performed on the collected historical functional defect records. For example, through the analysis of a large number of hardness defect records, it is found that when the hardness is insufficient, it is often accompanied by a significant decrease in wear resistance and a decrease in cutting performance, indicating that there is a strong functional loss association relationship between the hardness detection item and the wear resistance detection item and the cutting performance detection item. Perform a similar analysis on the historical defect records of other functional detection items to find out the mutual influence and association patterns between the detection items, and construct a functional loss probability matrix or association relationship diagram. On this basis, based on the functional loss association relationship, determine the hierarchy and sequence of the detection items, and construct a functional detection tree. The inspection items that are at the basic or key position in the function loss chain (such as appearance inspection, because appearance defects may often indicate potential problems with the internal structure or other functions) are taken as root nodes or upper nodes, and the inspection items that are strongly associated with the root node are taken as the child nodes of the next level (such as appearance inspection associated with internal structure integrity inspection, coating quality inspection, etc.), and so on, gradually building a complete function inspection tree that reflects the logical relationship and hierarchical structure between the various function inspection items. Through the function inspection tree, the subsequent quality inspection process can be clearly guided, and the decision on whether to conduct the inspection of the next node can be made in a targeted manner based on the inspection results of the previous node, thereby improving the inspection efficiency and accuracy. At the same time, it also helps to understand the quality status of the product more comprehensively and deeply, and provide strong support for product quality improvement and optimization.

[0019] In one possible implementation, the function loss association relationship of the detection item set is analyzed according to the historical function defect records, and the function detection tree is constructed based on the analysis results. Step S150 further includes step S151, by performing function loss synchronization analysis on the H types of function detection items based on the historical function defect records, a function loss probability matrix is ​​constructed. Specifically, first, analysis is performed based on the collected historical function defect records. Suppose we have types of function detection items, marked as A, B, C, ..., E. For each pair of function detection items, such as A and B, analyze the frequency of simultaneous loss of function B when function A is lost. By statistics on a large number of historical function defect records, calculate , which represents the probability of loss of function B when function A is lost. Similarly, the loss probability between all two functions is calculated to construct the function loss probability matrix For example, in the matrix represents the probability of function A losing itself (which may be caused by structural damage, etc. in practice), It represents the probability of loss of function A when function B is lost, and so on.

[0020] Step S152, preset a transition probability association threshold, take appearance detection as the root node, and use appearance detection and the transition probability association threshold to traverse the function loss probability matrix to obtain N function detection items, and use the N function detection items as the N second-level child nodes, wherein the root node is connected to the N second-level child nodes by out-degree. Specifically, set a transition probability association threshold (This threshold is determined based on experience or actual needs.) Assuming that the appearance detection corresponds to function A (this is just an assumption for the convenience of explanation), then look at the probability matrix The first row in (corresponding to function A). Iterate through the probability values ​​in this row, for example If a probability value is greater than or equal to ,for example and , then the detection items corresponding to function B and function C are selected as second-level child nodes, and the number is N (here N=2, i.e., the detection items corresponding to function B and function C). Appearance detection (root node) and these N second-level child nodes (detection items corresponding to function B and function C) establish an out-degree connection relationship, indicating that the appearance detection can be transitioned to these N second-level child nodes for detection.

[0021] Step S153, traverse the function loss probability matrix using the N secondary child nodes and the transition probability association threshold to obtain N groups of function detection items. Specifically, for the N secondary child nodes obtained in the previous step, assume that they are detection items corresponding to function B and function C. For the detection item corresponding to function B, check the probability matrix The row corresponding to B (the second row) is associated with the threshold according to the transition probability For example, if and , then the test items corresponding to function D and function E form a group. For the test items corresponding to function C, look at the row corresponding to C (the third row), assuming and , then the test items corresponding to function F and function G form another group. In this way, N groups of functional test items are obtained.

[0022] Step S154, construct N groups of three-level child nodes of the N groups of functional detection items, and connect the N second-level child nodes with the N groups of three-level child nodes out-degree, wherein the N groups of three-level child nodes include the M three-level child nodes in total. Specifically, for the N groups of functional detection items obtained in the previous step, each group is constructed as a three-level child node. For example, the detection items corresponding to the functions D and E screened out from function B constitute a group of three-level child nodes, and the detection items corresponding to the functions F and G screened out from function C constitute another group of three-level child nodes. Then the second-level child nodes (the detection items corresponding to the functions B and C) are connected to their corresponding three-level child nodes (such as the detection items corresponding to the functions D and E corresponding to the functions B, and the detection items corresponding to the functions F and G corresponding to the functions C). The total number of all three-level child nodes here is M (in the above example, M=4, i.e., the detection items corresponding to the functions D, E, F and G).

[0023] Step S155, and so on, until the nodes in the function detection tree cover the H kinds of function detection items, and the construction of the function detection tree is completed. Specifically, according to the above method, continue to filter downward from the third-level child nodes. For example, for the detection item corresponding to function D (assuming it is one of the third-level child nodes), check the corresponding row in the probability matrix again, and filter out the next-level child nodes according to the transition probability association threshold. Repeat this process until the nodes in the function detection tree can cover all H kinds of function detection items. In this way, the construction of the entire function detection tree is completed, and each node in the tree represents a function detection item, and the connection relationship between the nodes reflects the detection order and logic based on the probability of function loss.

[0024] In a possible implementation, by performing a function loss synchronization analysis on the H kinds of function detection items based on the historical function defect records, a function loss probability matrix is ​​constructed and generated, and step S151 further includes step S1511, based on the function loss synchronization, disassembling the historical function defect records to obtain the first function association information set of the first function detection item in the detection item set. Specifically, there are historical function defect records, and the records contain the result data of the detection of the H kinds of function detection items. Assuming that the first function detection item is A, all records when function A is lost are filtered out from the historical records. For example, in past detections, when function A is detected to be invalid, the conditions of other function detection items will be recorded at the same time. When function A is lost, the combination of the conditions of other function detection items constitutes the first function association information set of the first function detection item A. For example, when A is lost, there may be multiple records showing that functions B and C cannot detect normal results, then the combination of (B, C) and the like is part of the first function association information set.

[0025] Step S1512, perform repetition frequency statistics of H-1 kinds of function detection items on the first function association information set to obtain a first group of loss transition probabilities, wherein the first group of loss transition probabilities includes H-1 function loss transition probabilities. Specifically, for the first function association information set obtained above, the occurrence frequency of the other H-1 kinds of function detection items is to be counted. Assume that in addition to the first function detection item A, there are functions B, C, ..., E (a total of H-1 kinds). Check each record in the first function association information set and count the number of times function B appears in these records Similarly, count the number of times function C appears , and so on. Then calculate the first set of loss transition probabilities. For example, the loss transition probability from function A to function B is ,here It is the sum of the number of occurrences of other functions except A in the first function association information set. H-1 function loss transition probabilities are obtained, that is, the first group of loss transition probabilities.

[0026] Step S1513, and so on, based on the historical function defect records, the function loss synchronization analysis is performed on the H kinds of function detection items to obtain H groups of function loss transition probabilities. Specifically, according to the above steps, we analyze each function detection item in turn. When analyzing function B, find out the combination of other function detection items when function B is lost from the historical function defect records, and obtain the function association information set of function B. Then perform similar repetition frequency statistics on this information set, calculate the loss transition probability of function B to other functions, and obtain the second group of loss transition probabilities. Repeat this process until all H kinds of function detection items have been analyzed in this way, thereby obtaining H groups of function loss transition probabilities.

[0027] Step S1514, construct and generate the function loss probability matrix based on the H function detection items and H groups of function loss transition probabilities. Specifically, we have H function detection items, marked as A, B, C, ..., E. H groups of function loss transition probabilities are obtained from the previous steps, and each group corresponds to the transition probability of one function detection item to other function detection items. Constructing the function loss probability matrix , the elements in the matrix Indicates that from the function To function For example, is one of the first set of loss transition probabilities, located in the first row and second column of the matrix, indicating the loss transition probability from function A to function B. Similarly, Located in the second row and first column, it represents the loss transition probability from function B to function A. In this way, a function loss probability matrix is ​​constructed based on H functional test items and H groups of function loss transition probabilities. .

[0028] Step S200, taking the root node as the starting point of quality inspection, and collecting the inspection data of the diamond drill bit in a targeted manner according to the functional inspection items of the root node, to obtain single-dimensional inspection data. Specifically, when the root node is used as the starting point of quality inspection, the functional inspection items of the root node (set as appearance inspection) must first be clarified, including aspects such as surface integrity, shape and dimensional accuracy, and coating quality (if there is a coating). Targeted inspection data collection is carried out for each item. For example, for surface integrity, surface cracks and scratches can be observed and recorded through an optical or electron microscope, or visual grading records can be made; for shape and dimensional accuracy, key dimensions such as drill diameter can be measured multiple times with a high-precision measuring tool, and the cutting edge angle can be measured with an angle measuring instrument; for coating quality (if any), the coating thickness and uniformity can be measured through an optical microscope, and the coating adhesion can be detected by a cross-cutting test. Through the above operations, single-dimensional inspection data related only to the dimension of appearance inspection is obtained, and the data will serve as the basis for subsequent quality judgment.

[0029] Step S300, the diamond drill bit is quality inspected and analyzed according to the unidimensional inspection data, and the functional inspection results are output. Specifically, the quality standards corresponding to the unidimensional inspection data are clarified, such as the surface integrity, the crack length, depth and the size and number of defects such as scratches, pits and protrusions are strictly limited; the shape and dimensional accuracy, the cutting edge angle, drill diameter and length have specific design requirements and tolerance ranges; the thickness and uniformity of the coating quality (if any), and the adhesion also have corresponding indicators. Then the inspection data is compared and analyzed with these standards one by one, such as if the surface crack length exceeds the standard value, the surface integrity does not meet the requirements, the cutting edge angle deviation is at the edge of the allowable range, it is in a critical state, the coating thickness is not in the standard range or the adhesion is not up to standard, the coating quality is unqualified, etc. Finally, the results of various aspects of the analysis are combined to determine whether the appearance function inspection of the diamond drill bit has passed, and it is output in the form of a report, listing the data, standards and judgment of each inspection item in detail, and giving the overall functional inspection results, such as "pass" or "fail" and the corresponding unqualified item records, so that subsequent measures can be taken.

[0030] In one possible implementation, Figure 2As shown, the diamond drill bit is subjected to quality inspection and analysis according to the single-dimensional inspection data, and the functional inspection results are output. Step S300 further includes step S310, interactively obtaining H reference data requirements for the H functional inspection items. Specifically, a team consisting of quality engineers, production technicians and industry experts is organized to conduct in-depth discussions and analyses on each functional inspection item. Taking hardness inspection as an example, considering the working characteristics and material properties of the diamond drill bit, it is determined that the data on its overall hardness, the hardness difference of different parts (such as cutting edge, drill body, etc.) and the change of hardness with temperature need to be detected. These specific data indicators constitute the reference data requirements for the hardness inspection item. For cutting performance inspection, the reference data range and accuracy requirements for cutting force, cutting speed, chip shape, etc. should be determined; for wear resistance inspection, the collection standards and methods of relevant data such as wear amount, wear rate, and wear uniformity should be clarified, so as to obtain detailed reference data requirements corresponding to each of the H functional inspection items, and provide accurate guidance for subsequent data acquisition and model establishment.

[0031] Step S320, according to the H reference data requirements and the model information of the diamond drill bit, network data call is performed to obtain H quality anomaly information sets, wherein each quality anomaly information set includes multiple sample reference data and multiple sample anomaly detection results. Specifically, data acquisition software and network interface are used to connect to resource libraries such as the quality database within the enterprise, the industry standard database, and the research results database of relevant scientific research institutions. When performing data call, the specific model information of the diamond drill bit is first input to filter out data that is highly relevant to the model. Combined with the H reference data requirements determined previously, search algorithms and data screening tools are used to extract information that meets the requirements from massive data. For example, for appearance inspection projects, according to the detection requirements for surface cracks, pores, flaws, wear and other defects in the reference data requirements, multiple appearance image data of the drill bit of this model in different production batches and different use stages are searched and collected from the database as sample reference data, as well as corresponding sample anomaly detection results such as crack size and defect area ratio, and the data together constitute the quality anomaly information set of the appearance inspection project. This process is repeated for each functional test item, and finally H complete quality abnormality information sets are obtained, providing rich and targeted actual data support for subsequent model training.

[0032] Step S330, pre-configure H standard anomaly detection models according to the H detection feature differences of the H functional detection items. Specifically, based on the analysis of the data of the H functional detection items, analyze the unique detection features and data patterns of each functional detection item. Taking hardness detection as an example, its detection features are the distribution range of hardness values, the relationship between hardness values ​​and material structure, etc. According to the above features, select a suitable machine learning algorithm, such as an anomaly detection algorithm based on statistical analysis, to construct a standard anomaly detection model for hardness detection. For cutting performance detection, since its detection features involve complex factors such as the dynamic changes of cutting force and the morphological characteristics of chips, a convolutional neural network in a deep learning algorithm is used to construct a model to better capture complex patterns and abnormal conditions in the cutting process. For wear resistance detection, the time series characteristics of wear data are analyzed, and a recurrent neural network or time series analysis method is selected to construct a corresponding standard anomaly detection model. Through differentiated model selection and pre-configuration for different detection features, H initial standard anomaly detection models are tailored for each functional detection item, laying the foundation for subsequent model optimization.

[0033] Step S340, using the H quality anomaly information sets as training data to perform directional parameter optimization of the H standard anomaly detection models, and obtaining H quality anomaly detection models. Specifically, for each pre-configured standard anomaly detection model, the corresponding quality anomaly information set is subjected to data preprocessing operations, including data cleaning (removing noise data, outlier processing, etc.), data normalization (converting data of different scales into a unified numerical range) and data feature engineering (extracting key features, reducing dimensions, etc.) to improve the quality and availability of the data. The processed quality anomaly information set is divided into a training set and a validation set according to a certain ratio, and the standard anomaly detection model is trained using the training set. During the training process, by adjusting the internal parameters of the model (such as the weights and biases of the neural network, the parameter estimates of the statistical model, etc.), with the goal of minimizing the difference between the model prediction results and the actual sample anomaly detection results, an appropriate optimization algorithm (such as the gradient descent method, the stochastic gradient descent method, etc.) is used for iterative optimization. The performance of the model is evaluated and verified using the validation set to prevent the occurrence of overfitting. After multiple training and validation cycles, the model parameters are continuously adjusted until the performance of the model on the validation set reaches the expected indicators, thereby obtaining H optimized quality anomaly detection models for H functional inspection items. The model can more accurately identify and predict the quality anomalies of diamond drill bits in different functional inspection items.

[0034] Step S350, according to the hierarchical relationship of the H kinds of functional detection items in the functional detection tree, construct the activation hierarchical structure of the H quality anomaly detection models, and complete the establishment of the detection model activation tree. Specifically, analyze the hierarchical position and logical relationship of the H kinds of functional detection items in the constructed functional detection tree. For example, in the functional detection tree, the appearance detection is usually at the root node or the upper layer, because the appearance defects can often intuitively reflect other potential quality problems that may exist in the drill bit. If the appearance detection passes, then it is necessary to further detect the subsequent functional detection items associated with it, such as internal structure integrity detection, coating quality detection, etc. Based on the hierarchical relationship, the quality anomaly detection model corresponding to the appearance detection is set to the model that is first activated at the beginning of the detection process. If the appearance detection model is judged to be passed, then according to the logic of the functional detection tree, the quality anomaly detection models corresponding to the internal structure integrity detection and the coating quality detection are activated, and so on, to construct the activation hierarchical structure of the H quality anomaly detection models. In this structure, the activation order and conditions of the model are determined according to the sequence and logical dependencies of the functional detection items in the functional detection tree, thereby completing the establishment of the detection model activation tree. When performing quality inspection on diamond drill bits, the corresponding quality anomaly detection models can be called in a reasonable order, thereby improving detection efficiency and accuracy, avoiding unnecessary waste of detection resources, and being able to more comprehensively and systematically discover and diagnose quality problems of drill bits, providing strong technical support for the enhancement and improvement of product quality.

[0035] In a possible implementation, the diamond drill bit is subjected to quality inspection and analysis according to the single-dimensional inspection data, and the functional inspection result is output. Step S300 further includes step S360, calling the first reference data requirement from the H reference data requirements according to the functional inspection item of the root node. Specifically, the functional inspection item of the root node is clarified. Assuming that the root node is appearance inspection, the inspection items covered may include surface crack inspection, shape and size measurement, coating integrity assessment, etc. Then, the first reference data requirement related to the appearance inspection item is screened out from the predetermined H reference data requirements. For example, if the appearance inspection focuses on surface cracks, the first reference data requirement may involve specific data standards and collection methods for the length, width, number, and distribution location of the cracks; for shape and size measurement, it will include the tolerance range and measurement accuracy requirements of the drill bit diameter, length, cutting edge angle, etc.; for coating integrity, it will specify the allowable range of coating thickness, the roughness index of the coating surface, etc. Through matching, the first reference data requirement dedicated to appearance inspection is extracted from the numerous reference data requirements, providing clear guidance and specifications for subsequent data collection.

[0036] Step S370, according to the first reference data requirement, the diamond drill bit is subjected to directional detection data collection to obtain the single-dimensional detection data. Specifically, according to the first reference data requirement obtained above, professional detection personnel are organized and equipped with appropriate detection equipment to carry out data collection. For surface crack inspection, if the first reference data requirement stipulates the use of an optical microscope for detection, the detection personnel will conduct a comprehensive and detailed scan of the drill bit surface from a specified observation angle under specific lighting conditions, and record the relevant data of all cracks found, such as length accurate to millimeters, width accurate to microns, and the specific location coordinates of the cracks; when measuring the shape and size, high-precision calipers, micrometers or optical measuring instruments are used as required to measure the diameter of the drill bit at multiple locations to ensure the accuracy and repeatability of the measurement results, and the length and cutting edge angle are also accurately measured and recorded according to standard measurement methods; for coating integrity assessment, a coating thickness gauge is used to measure the coating thickness, and a roughness meter is used to detect the roughness of the coating surface. Data collection is performed according to pre-set sampling points and measurement paths to ensure that the key areas of the entire coating surface are covered. Through targeted inspection operations, single-dimensional inspection data related only to appearance inspection is collected, and the data will serve as the basic input for subsequent quality assessment.

[0037] Step S380, according to the root node, the first quality anomaly detection model is activated in the detection model activation tree mapping. Specifically, it is known that the root node is appearance detection, and the corresponding node is found in the pre-constructed detection model activation tree. The detection model activation tree is constructed based on the logical relationship and importance of the functional detection items. The appearance detection is used as the starting node, and there are potential associations and trigger conditions with other subsequent functional detection items (such as hardness detection, cutting performance detection, etc.). When it is determined to be an appearance detection, according to the mapping mechanism of the activation tree, the first quality anomaly detection model designed specifically for appearance detection is found and activated. The model is obtained by training and optimization based on a large amount of historical appearance detection data and quality anomaly cases. It can quickly and accurately analyze the collected appearance detection data to determine whether there are abnormal conditions. For example, through the comprehensive analysis of surface crack data, shape and size deviation data, and coating integrity data, it can identify whether the appearance of the drill bit meets the quality standards and whether there are potential quality risks.

[0038] Step S390, loading the single-dimensional detection data into the first quality anomaly detection model for quality detection analysis, and outputting the functional detection result, wherein when the functional detection result is not passed, the functional detection result also includes the functional anomaly detection result. Specifically, the single-dimensional detection data collected previously is loaded according to the format and input method required by the first quality anomaly detection model. The model will analyze these data according to the built-in algorithm and the parameters obtained by training. For example, for surface crack data, the model will compare the crack feature distribution of normal drill bits in historical data to determine whether the number, length and distribution of cracks currently detected exceed the normal range; for shape and size data, it will check whether the measured value is within the predetermined tolerance range. If it exceeds the tolerance range, it will be determined to be abnormal; for coating integrity data, analyze whether the coating thickness deviation and roughness index meet the quality requirements. After comprehensive analysis by the model, if all data meet the quality standards, the output functional test result is "passed", indicating that the diamond drill bit has reached the expected quality level in appearance inspection and the subsequent inspection process can continue (if necessary); if the model finds that any data does not meet the requirements, that is, the functional test result is judged to be "failed", in addition to outputting the overall result of "failed", the functional abnormality test result will also be output, clearly indicating which specific test items are abnormal, such as "the surface crack length exceeds the standard value, the maximum crack length reaches 5 mm, and the standard requirement is not more than 3 mm" or "the cutting edge angle deviation is too large, the measured angle is 125°, and the standard range is 118°~122°", etc., so that subsequent quality improvement and problem troubleshooting work can quickly locate the problem and take targeted measures to repair or adjust it. At the same time, according to the "failed" result, according to the pre-set rules, stop subsequent unnecessary inspection processes such as hardness testing and cutting performance testing to avoid waste of resources and time consumption, and improve overall inspection efficiency and cost-effectiveness.

[0039] Step S400, if the functional test result is passed, the test data of N secondary sub-nodes are collected under the guidance of the functional test tree, and the diamond drill bit is quality tested and analyzed based on the obtained N-dimensional test data, and N secondary test results are output. Specifically, when the functional test result is passed, the N secondary sub-nodes and their corresponding functional test items are determined under the guidance of the functional test tree. For example, hardness test requires clear measurement location, method, accuracy and number of collection points, coating adhesion test requires determination of test standards, regions and quantitative evaluation indicators, and internal structure integrity test involves flaw detection technical means and defect information collection requirements. Test data collection is performed separately, such as hardness test, multiple measurements and recording of hardness values ​​at each key location, coating adhesion test uses the cross-cutting method to make patterns, rating and recording of shedding characteristics after tape tearing, and internal structure integrity test uses X-ray flaw detection to obtain images and analyze defect parameters. Quality inspection and analysis are carried out based on the collected N-dimensional inspection data. The hardness condition is judged by comparing the hardness data with the standard through statistical analysis. Whether it is good is analyzed based on the coating adhesion rating and shedding characteristics. Whether there are any internal problems is judged based on the defect information of the internal structure integrity inspection, thereby outputting N secondary inspection results.

[0040] In a possible implementation, if the function test result is passed, the function test tree is used as a guide to collect test data of N secondary sub-nodes, and the diamond drill bit is subjected to quality test analysis based on the obtained N-dimensional test data, and N secondary test results are output. Step S400 further includes step S410, if the function test result is passed, the function test tree is used as a guide to call the N reference data requirements of the N secondary sub-nodes from the H reference data requirements. Specifically, after confirming that the function test result of the root node (such as appearance test) is "passed" (with 1 indicating the pass state), the next step is performed based on the constructed function test tree. The function test tree is constructed based on the association relationship and importance hierarchy between the functions of the diamond drill bit, in which the logical path from the root node to each secondary sub-node is clarified. It is known that there are a total of H function test items and the corresponding H reference data requirements. According to the guidance of the function test tree, the function test items corresponding to the N secondary sub-nodes are accurately located. For example, if the second-level sub-nodes include hardness testing, cutting performance testing, and wear resistance testing, the detailed reference data requirements corresponding to each of these three test items are selected from the H reference data requirements. For example, the reference data requirements for hardness testing cover the hardness value range of different parts, the standard method of hardness testing, and the allowable hardness deviation; the reference data requirements for cutting performance testing involve the maximum and minimum values ​​of cutting force, the reasonable range of cutting speed, the shape and size standards of chips, etc.; the reference data requirements for wear resistance testing include the limit value of wear, wear uniformity index, and the number and conditions of wear resistance test cycles, etc., so as to clarify the direction and standards for subsequent test data collection.

[0041] Step S420, according to the N reference data requirements, the diamond drill bit is subjected to directional data collection to obtain the N-dimensional test data. Specifically, according to the reference data requirements of the N secondary subnodes called in the previous step, professional test personnel are organized and equipped with corresponding high-precision test equipment to perform data collection. Taking hardness detection as an example, if the reference data requirements stipulate that hardness measurement is performed on the cutting edge, side and center of the drill bit, and the Rockwell hardness test method is adopted, the test personnel will use the Rockwell hardness tester to select multiple evenly distributed test points (such as 5 points) on the cutting edge, apply the specified load according to the standard test process, and record the hardness value of each point; and select a suitable number of test points (such as 3 points each) on the side and center to perform the same operation, and obtain a series of test data on hardness. For cutting performance detection, the conditions of the cutting experiment are set according to the reference data requirements, such as using a specific cutting tool, a fixed cutting speed and feed rate. In the cutting process simulating actual work, the cutting force, cutting temperature and other data are collected in real time through the sensor installed on the equipment, and the shape and size of the chips are measured and recorded. For wear resistance testing, the drill bit is installed on a special wear resistance test device, and the experiment is carried out according to the predetermined wear test cycle number and loading conditions. The wear of the drill bit is measured regularly, the uniformity of wear is observed, and the data of each measurement is recorded. Through targeted testing operations on the test items of each secondary sub-node, multi-dimensional test data related to N secondary sub-nodes, namely N-dimensional test data, are collected, and the data will serve as the basic input for subsequent quality inspection and analysis.

[0042] Step S430, N quality anomaly detection models are mapped and activated in the detection model activation tree according to the hierarchical features of the N secondary sub-nodes. Specifically, the detection model activation tree is constructed according to the hierarchical relationship and logical order of the functional detection items, and is interrelated with the functional detection tree but focuses on the activation control of the model. Each secondary sub-node has a corresponding node position and activation condition in the detection model activation tree. After the N secondary sub-nodes are determined, the model activation operation is performed according to the hierarchical features in the detection model activation tree. For example, the quality anomaly detection model corresponding to hardness detection may be trained based on a large amount of historical hardness detection data and known quality anomaly cases using machine learning algorithms (such as support vector machines, neural networks, etc.). When hardness detection is triggered as a secondary sub-node, the mapping mechanism of the detection model activation tree is used to find and activate the quality anomaly detection model for hardness detection, so that it is in a state of preparing to receive data for analysis. For the secondary sub-nodes of cutting performance detection and wear resistance detection, the corresponding quality anomaly detection models are also activated respectively. After pre-training and optimization, the models can perform efficient and accurate anomaly analysis and quality assessment on the corresponding detection data, providing intelligent support for subsequent quality detection analysis.

[0043] Step S440, by loading the N-dimensional detection data into the N quality anomaly detection models for quality detection analysis, the N secondary detection results are output. Specifically, the N-dimensional detection data collected previously are sorted and loaded according to the format and data preprocessing method required by the corresponding quality anomaly detection models. For example, for hardness detection data, data normalization processing is required to convert the hardness value to a specific numerical range to meet the requirements of model input; for cutting performance detection data, feature engineering processing is required for multiple variables such as cutting force and cutting temperature, and key features are extracted and combined into a vector form suitable for model input. The processed N-dimensional detection data are input into the corresponding N quality anomaly detection models respectively. The model will perform in-depth analysis and pattern recognition on the input data based on the built-in algorithm and trained parameters. Taking the quality anomaly detection model of hardness detection as an example, the input hardness data will be compared with the distribution characteristics of historical normal data to determine whether there is a hardness anomaly, such as whether there is a local hardness that is too low or uneven hardness; the quality anomaly detection model of cutting performance detection will analyze the fluctuation of cutting force, the trend of cutting temperature change, and the abnormal characteristics of chip morphology, and comprehensively judge whether the cutting performance meets the quality requirements; the quality anomaly detection model of wear resistance detection will evaluate whether the wear resistance of the drill bit meets the standard based on the growth trend of wear volume, the distribution of wear, and the degree of difference from the expected wear resistance. After independent analysis of each model, N secondary test results are output, and each result clearly indicates whether the corresponding secondary sub-node test item has passed the quality inspection, such as "hardness test passed", "cutting performance test failed, cutting force is too large", "wear resistance test passed", etc. The secondary test results will provide detailed and accurate basis for further testing decisions and quality assessments, and guide the subsequent investigation of diamond drill bit quality problems and the formulation of improvement measures.

[0044] Step S500, the out-degree connection relationship between the N secondary sub-nodes and the M tertiary sub-nodes in the function detection tree is used as a criterion for judging whether the quality detection continues to be performed, and the function detection of the M tertiary sub-nodes is performed according to the pass mark of the N secondary detection results, wherein N and M are positive integers, and N<M. Specifically, the out-degree connection relationship between the N secondary sub-nodes and the M tertiary sub-nodes in the function detection tree is clarified, and this relationship is constructed based on a deep understanding of the internal logic and mutual influence of each function of the diamond drill bit. For example, the association between "drill bit hardness detection" and "cutting performance detection", "coating quality detection" and "corrosion resistance detection" and the like exists, and the connection relationship is set as a criterion for judging whether the quality detection continues. After completing the detection of N secondary sub-nodes and obtaining the corresponding secondary detection results with a pass mark (such as 1 for pass and 0 for fail), the detection execution of the tertiary sub-node is determined according to the judgment criterion. If the second-level sub-node test passes and has an out-degree connection with the third-level sub-node, such as if the "drill bit hardness test" passes, the "cutting performance test" will be started, and the testers will test and analyze indicators such as cutting force according to established standards and methods; if the second-level sub-node test fails, such as if the "coating quality test" fails, the third-level sub-node tests such as the "corrosion resistance test" associated with it will be directly skipped. This can ensure that the test is comprehensive and avoid invalid detection, effectively improving the efficiency and pertinence of diamond drill bit quality inspection.

[0045] Step S600, and so on, quality inspection is performed according to the inspection results of the previous level sub-nodes in the functional inspection tree, and the quality defect information set of the diamond drill bit is output. Specifically, the inspection is started from the root node (such as appearance inspection) of the functional inspection tree, and the inspection is carried out and the results are obtained according to the established process and standards. If the root node fails, the appearance-related defect details (such as crack position and size deviation value, etc.) are immediately recorded as the initial content of the quality defect information set; if the root node passes, the second-level sub-nodes are inspected according to the tree structure to obtain the results (pass or fail). Whether the third-level sub-node is inspected or not is determined based on the inspection results of the second-level sub-nodes and their out-degree connection relationship with the third-level sub-nodes. If the second-level sub-node fails, the associated third-level sub-node inspection is skipped. If it passes, the corresponding inspection is started. For example, if the "hardness inspection" passes, the "cutting performance inspection" is carried out. In each level of testing, once a sub-node fails, its functional abnormality and data (such as excessive cutting force, abnormal chip shape and measurement data when the "cutting performance test" fails) will be recorded in detail and included in the quality defect information set. This cycle will be repeated, and the subsequent level detection judgment will be promoted based on the results of the previous level. The quality defect information will be continuously updated and summarized until all necessary levels of testing are completed. The final output quality defect information set will comprehensively cover all types of quality problems detected in diamond drill bits, providing an accurate basis for subsequent work to improve product quality.

[0046] In a possible implementation, by analogy, quality inspection is performed according to the inspection results of the previous level sub-node in the functional inspection tree, and the quality defect information set of the diamond drill bit is output. Step S600 further includes step S610, judging whether the quality defect information set covers the H types of functional inspection items. Specifically, an existing quality defect information set is obtained, which is accumulated in the process of gradually inspecting the diamond drill bit, and contains various quality problems that have been found and their related data. Each problem corresponds to a specific functional inspection item. The functional inspection items involved in the information set are compared one by one with the total H types of functional inspection items. For example, the existing quality defect information set records the problems found in appearance inspection, hardness inspection and cutting performance inspection, and the total functional inspection items include appearance inspection, hardness inspection, cutting performance inspection, wear resistance inspection, impact resistance inspection, etc. H types (assuming H=5). By checking, it is confirmed whether the quality defect information set covers 5 types of functional inspection items. This step is the key basis for subsequent decision-making, and can clarify the degree of integrity of the current inspection and whether further inspection operations are required.

[0047] Step S620, if the quality defect information set does not cover the H types of functional detection items, then the detection item deviation set is output. Specifically, when it is found through the above judgment that the quality defect information set does not cover all of the H types of functional detection items, it is necessary to determine which functional detection items are omitted. The items that do not appear in the quality defect information set among the H types of functional detection items are extracted to form a detection item deviation set. For example, if the quality defect information set lacks relevant information on wear resistance testing and impact resistance testing, then the detection item deviation set includes these two items. The purpose of outputting the deviation set is to clarify the direction that needs to be focused on in subsequent detection work, so as to carry out supplementary testing in a targeted manner, thereby improving the comprehensive understanding of the quality status of the diamond drill bit and ensuring that no important functional quality issues are ignored.

[0048] Step S630, after sampling the sample drill bits of the same batch of the diamond drill bits through systematic sampling, the quality inspection of the sample drill bits is carried out according to the functional inspection tree and the detection model activation tree, and the quality defect information set is updated based on the inspection results until the quality defect information set covers the H types of functional inspection items. Specifically, once the deviation set of the inspection items is determined, it is necessary to conduct further sampling inspection on the diamond drill bits of the same batch. Using the systematic sampling method, sample drill bits are selected from the drill bits of the same batch according to certain sampling rules (such as selecting one drill bit every N drill bits) to ensure the randomness and representativeness of the sampling. For the sample drill bits extracted, quality inspection work is carried out according to the previously constructed functional inspection tree and the detection model activation tree. The functional inspection tree provides a clear hierarchical structure and logical order for the inspection process. Starting from the root node, it is decided whether to inspect the sub-nodes of the next level according to the inspection results of the previous level, and the inspection process of each functional inspection item is gradually promoted. The detection model activation tree activates the corresponding quality anomaly detection model in a timely manner according to the characteristics and hierarchical relationship of the functional detection items, and analyzes the collected detection data efficiently and accurately. For example, when an abnormality is detected in a functional detection item of the sample drill bit, the abnormal situation and its related data are recorded in detail, and included in the quality defect information set, and the information set is updated. Then it is judged again whether the updated quality defect information set covers the H types of functional detection items. If it is still not fully covered, the system sampling and sample drill bit detection will continue, and the above process will be repeated to continuously supplement and improve the quality defect information set until it finally covers all H types of functional detection items. At this time, it can be considered that the quality inspection of this batch of diamond drill bits has reached a relatively comprehensive and in-depth level, which can provide sufficient basis for subsequent quality assessment, formulation of improvement measures, etc., to ensure the quality stability and reliability of the product.

[0049] The embodiment of the present application adopts the method of constructing a function detection tree through function loss association analysis, in which the root node is the appearance detection. Directional data collection is performed according to the root node to obtain single-dimensional detection data, and quality detection analysis is performed. If the function test passes, the data collection and analysis of the second-level sub-nodes are continued according to the detection tree, and the second-level detection results are output. According to the second-level detection results, it is determined whether to continue to perform the third-level sub-node detection. The detection results of each level determine the execution of the next step, thereby gradually outputting the quality defect information set of the diamond drill bit, avoiding redundant detection, improving detection efficiency, optimizing the detection process through function loss association analysis, reducing unnecessary detection items, and achieving the technical effect of improving detection efficiency and accuracy.

[0050] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A diamond drill bit quality detection method based on multi-dimensional parameter analysis, characterized in that: The method comprises: Performing function loss correlation analysis on the diamond drill bit, and constructing a function detection tree based on the analysis results, wherein the root node of the function detection tree is appearance detection; Taking the root node as the starting point of quality inspection, performing directional collection of inspection data of the diamond drill bit according to the functional inspection items of the root node to obtain single-dimensional inspection data; Performing quality inspection and analysis on the diamond drill bit according to the single-dimensional inspection data, and outputting a functional inspection result; If the function test result is passed, the test data of N secondary sub-nodes are collected under the guidance of the function test tree, and the quality test analysis of the diamond drill bit is performed based on the obtained N-dimensional test data, and N secondary test results are output; The out-degree connection relationship between the N second-level child nodes and the M third-level child nodes in the function detection tree is used as a criterion for determining whether to continue the quality detection, and the function detection of the M third-level child nodes is performed according to the pass identification of the N second-level detection results, wherein N and M are positive integers and N<M; By analogy, quality inspection is performed based on the inspection results of the previous level child nodes in the function inspection tree, and a quality defect information set of the diamond drill bit is output.

2. A diamond drill bit quality detection method based on multi-dimensional parameter analysis as claimed in claim 1, characterized in that: Performing function loss correlation analysis on the diamond drill bit and constructing a function detection tree based on the analysis results, the method further includes: The diamond drill bits are obtained by sampling from a drill bit production line using systematic sampling; Interactively obtain the batch production usage scenario of the drill production line, and obtain the usage scenario setting by collecting extreme usage data of the batch production usage scenario; Performing online data call according to the usage scenario setting to obtain a detection item set of the diamond drill bit, wherein the detection item set includes H types of functional detection items, wherein H is a positive integer greater than M; Using the detection item set as a constraint call to obtain historical functional defect records; The function loss association relationship of the detection item set is analyzed according to the historical function defect records, and the function detection tree is constructed based on the analysis results.

3. A diamond drill bit quality detection method based on multi-dimensional parameter analysis as claimed in claim 2, characterized in that: Performing a function loss association analysis on the detection item set according to the historical function defect records, and constructing the function detection tree based on the analysis results, the method further includes: By performing a function loss synchronization analysis on the H types of function detection items based on the historical function defect records, a function loss probability matrix is ​​constructed; Preset a transition probability association threshold, take appearance detection as a root node, and use appearance detection and the transition probability association threshold to traverse the function loss probability matrix to obtain N function detection items, and use the N function detection items as the N second-level child nodes, wherein the root node is out-degree connected to the N second-level child nodes; Using the N secondary child nodes and the transition probability associated threshold to traverse the function loss probability matrix, to obtain N groups of function detection items; Constructing N groups of third-level child nodes of the N groups of functional detection items, and connecting the N second-level child nodes with the N groups of third-level child nodes out-degree, wherein the N groups of third-level child nodes include the M third-level child nodes in total; And so on, until the nodes in the function detection tree cover the H types of function detection items, the construction of the function detection tree is completed.

4. A diamond drill bit quality detection method based on multi-dimensional parameter analysis as claimed in claim 3, characterized in that: By performing a function loss synchronization analysis on the three function detection items based on the historical function defect records, a function loss probability matrix is ​​constructed and generated, and the method further includes: Based on the function loss synchronization, disassembling the historical function defect record to obtain a first function association information set of the first function test item in the test item set; Performing repetition frequency statistics of H-1 kinds of function detection items on the first function association information set to obtain a first group of loss transition probabilities, wherein the first group of loss transition probabilities includes H-1 function loss transition probabilities; Similarly, based on the historical functional defect records, functional loss synchronization analysis is performed on the H functional detection items to obtain the functional loss transition probability of H groups; The function loss probability matrix is ​​constructed and generated according to the H kinds of function detection items and H groups of function loss transition probabilities.

5. A diamond drill bit quality detection method based on multi-dimensional parameter analysis as claimed in claim 2, characterized in that: Before performing quality inspection and analysis on the diamond drill bit according to the single-dimensional inspection data and outputting a functional inspection result, the method further includes: Interactively obtain H reference data requirements for the H functional detection items; Performing online data calling according to the H reference data requirements and the model information of the diamond drill bit to obtain H quality anomaly information sets, wherein each quality anomaly information set includes a plurality of sample reference data and a plurality of sample anomaly detection results; Pre-configure H standard anomaly detection models according to the H detection feature differences of the H functional detection items; Using the H quality anomaly information sets as training data to perform directional parameter optimization of the H standard anomaly detection models, to obtain H quality anomaly detection models; According to the hierarchical relationship of the H types of functional detection items in the functional detection tree, the activation hierarchical structure of the H quality anomaly detection models is constructed to complete the establishment of the detection model activation tree.

6. A diamond drill bit quality detection method based on multi-dimensional parameter analysis as claimed in claim 5, characterized in that: Performing quality inspection and analysis on the diamond drill bit according to the single-dimensional inspection data and outputting a functional inspection result, the method further includes: calling a first reference data requirement from the H reference data requirements according to the function detection item of the root node; According to the first reference data requirement, performing directional acquisition of detection data of the diamond drill bit to obtain the one-dimensional detection data; activating a first quality anomaly detection model according to the root node in the detection model activation tree mapping; The single-dimensional detection data is loaded into the first quality anomaly detection model for quality detection analysis, and the functional detection result is output, wherein when the functional detection result is failed, the functional detection result also includes a functional anomaly detection result.

7. A diamond drill bit quality detection method based on multi-dimensional parameter analysis as claimed in claim 6, characterized in that: If the function test result is passed, the function test tree is used as a guide to collect test data of N secondary sub-nodes, and the diamond drill bit is quality tested and analyzed based on the obtained N-dimensional test data, and N secondary test results are output. The method also includes: If the function detection result is passed, calling the N reference data requirements of the N secondary child nodes from the H reference data requirements with the function detection tree as a guide; According to the N reference data requirements, the diamond drill bit is subjected to directional detection data collection to obtain the N-dimensional detection data; Activating N quality anomaly detection models in the detection model activation tree mapping according to the hierarchical features of the N secondary sub-nodes; The N-dimensional detection data is loaded into the N quality anomaly detection models for quality detection analysis, and the N secondary detection results are output.

8. The method for detecting diamond drill bit quality by multi-dimensional parameter analysis as claimed in claim 5, characterized in that: The method comprises: Determining whether the quality defect information set covers the H types of functional detection items; If the quality defect information set does not cover the H types of functional test items, output a test item deviation set; After sampling sample drill bits from the same batch of the diamond drill bits through systematic sampling, quality inspection of the sample drill bits is performed according to the functional inspection tree and the inspection model activation tree, and the quality defect information set is updated based on the inspection results until the quality defect information set covers the H types of functional inspection items.

Images