Intelligent hole quality detection method and system based on acoustic emission signal and medium

Abstract

The invention relates to an intelligent hole quality detection method and system based on acoustic emission signals and a medium. The method comprises the following steps that the acoustic emission signals generated in the drilling process are collected in real time and preprocessed; the preprocessed acoustic emission signals are input into a hole stage classification model to be processed, and hole drilling stages corresponding to the acoustic emission signals are output; and based on the determined drilling stage, inputting the acoustic emission signal into a corresponding prediction model, and outputting a quality prediction result of the drill hole in the drilling stage. Compared with the prior art, the method has the advantages of monitoring and predicting the quality index of the hole in real time, providing immediate feedback for production personnel and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical manufacturing and quality control, and in particular to an intelligent hole quality detection method, system and medium based on acoustic emission signals. Background Art

[0002] In modern manufacturing, hole processing is one of the indispensable basic processes, and its quality directly affects the performance, reliability and service life of the product. Traditional hole quality inspection methods mostly rely on post-inspection, such as using measuring tools to measure the hole diameter, hole depth and surface roughness. This method is not only inefficient, but also difficult to fully reflect the quality problems in the processing process. In addition, some high-end fields such as aerospace have extremely high requirements for hole processing quality, and any minor defects may lead to serious safety hazards.

[0003] In recent years, with the rapid development of sensor technology and data analysis technology, quality control methods based on real-time monitoring have gradually gained attention. As a non-destructive detection technology, acoustic emission technology can capture stress waves released by materials during force or deformation, and has unique advantages in monitoring small changes in the machining process. However, how to effectively use acoustic emission signals, especially to apply them to real-time prediction and monitoring of hole machining quality, is still a major challenge in the current technical field.

[0004] Considering the demand and inadequacy for online measurement and real-time quality monitoring in the existing production process, developing a nondestructive testing method that can predict and evaluate the hole-making process quality in real time without interfering with the hole-making process has become a problem that needs to be solved. Summary of the invention

[0005] The purpose of the present invention is to provide a real-time, non-destructive hole making quality detection method, system and medium based on acoustic emission signals.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] An intelligent hole quality detection method based on acoustic emission signals comprises the following steps:

[0008] Real-time collection of acoustic emission signals generated during drilling and pre-processing;

[0009] Inputting the preprocessed acoustic emission signal into a hole stage classification model for processing, and outputting the drilling stage corresponding to the acoustic emission signal;

[0010] Based on the determined drilling stage, the acoustic emission signal is input into a corresponding prediction model, and a prediction result of the drilling quality during the drilling stage is output.

[0011] Furthermore, an acoustic emission sensor is used to collect the acoustic emission signal in real time.

[0012] Furthermore, the preprocessing operation includes filtering, denoising, and feature extraction.

[0013] Furthermore, the extracted features include amplitude, frequency and energy of the acoustic emission signal.

[0014] Furthermore, the drilling stage includes three stages, namely, a drilling-in stage, a drilling-in stage and a drilling-out stage.

[0015] Furthermore, the prediction model includes an entrance quality prediction model, a hole wall quality prediction model and an exit quality prediction model, wherein the input of the entrance quality prediction model is the acoustic emission signal of the drilling stage, the input of the hole wall quality prediction model is the acoustic emission signal of the drilling stage, and the input of the exit quality prediction model is the acoustic emission signal of the drilling stage.

[0016] Furthermore, the quality prediction results of the inlet quality prediction model include inlet diameter consistency and surface roughness, the quality prediction results of the hole wall quality prediction model include hole wall thickness uniformity, cracks, and damage, and the quality prediction results of the outlet quality prediction model include outlet diameter and burr conditions.

[0017] Furthermore, the prediction model is trained using a supervised machine learning algorithm, and the supervised machine learning algorithm includes one of a support vector machine, a random forest, a neural network, and a deep learning algorithm.

[0018] The present invention also provides a hole quality intelligent detection system based on acoustic emission signals, comprising:

[0019] Data acquisition module: used to collect the acoustic emission signals generated during the drilling process in real time and perform preprocessing;

[0020] Stage classification module: used for inputting the pre-processed acoustic emission signal into the hole stage classification model for processing, and outputting the drilling stage corresponding to the acoustic emission signal;

[0021] The quality prediction module is used to input the acoustic emission signal into the corresponding prediction model based on the determined drilling stage, and output the quality prediction result of the drilling at the drilling stage.

[0022] The present invention also provides a computer-readable storage medium, comprising one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the intelligent hole quality detection method based on acoustic emission signals as described above.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] (1) The present invention classifies the drilling stages by using a hole stage classification model for the acoustic emission signals generated in real time during the drilling process, and uses a prediction model for the corresponding stage to predict the quality. This can predict the hole production quality during the entire drilling process, and realizes non-destructive testing for real-time prediction and evaluation of hole production quality.

[0025] (2) The prediction models of the present invention not only realize the hole quality prediction at each stage of the drilling process, but also realize the prediction of multiple indicators in each stage, which helps to obtain comprehensive hole quality prediction results, comprehensively reflect the quality problems in the drilling process, and can meet the applications with extremely high requirements for hole processing quality.

[0026] (3) The present invention can monitor and predict the quality index of the hole in real time during the hole making process without interfering with the hole making process, provide immediate feedback to production personnel, help to adjust processing parameters in time, optimize processing technology, significantly improve production efficiency and product quality, and ensure that the final quality of the hole meets the design requirements. It also helps to reduce the scrap rate and production costs, which is of great significance to promoting the intelligent upgrading of the manufacturing industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0028] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0029] This embodiment provides a hole quality intelligent detection method based on acoustic emission signals. Figure 1 As shown, the method comprises the following steps:

[0030] S1. Obtain real-time acoustic emission signals.

[0031] During the hole making process, acoustic emission sensors are used to collect acoustic emission signals generated during the drilling process in real time. Preprocessing is required before stage classification. The preprocessing steps include filtering, denoising, feature extraction (such as signal amplitude, frequency, energy, etc.) to improve the accuracy and efficiency of model training.

[0032] S2. Input the acoustic emission signal into the hole stage classification model and output the drilling stage.

[0033] In this step, the construction process of the hole stage classification model uses a supervised machine learning algorithm, with the real-time collected acoustic emission signal as the input feature and the drilling stage (divided into three categories: drilling in, drilling in, and drilling out) as the output label to train the hole stage classification model. The supervised machine learning algorithm includes but is not limited to a support vector machine, a random forest, a neural network, or a deep learning algorithm.

[0034] After the training, the model validation and optimization steps are carried out to improve the prediction accuracy and generalization ability of the model through methods such as cross-validation and hyperparameter tuning.

[0035] S3. Select a prediction model according to the drilling stage and output the quality prediction result.

[0036] When the hole stage classification model determines that the current stage is drilling, the corresponding acoustic emission signal is input into the entrance quality prediction model, which predicts and evaluates the entrance quality of the hole by analyzing the signal characteristics, such as the consistency of the entrance diameter and the surface roughness.

[0037] When the hole stage classification model determines that the current drilling stage is in progress, the corresponding acoustic emission signal is input into the hole wall quality prediction model. The model uses a deep learning algorithm to analyze subtle changes in the signal and predict the quality status of the hole wall, including the uniformity of hole wall thickness, cracks or damage, etc.

[0038] When the hole stage classification model determines that the current stage is drilling out, the corresponding acoustic emission signal is input into the exit quality prediction model, which evaluates the exit quality of the hole, such as exit diameter, burr condition, etc., to ensure that the final quality of the hole meets the design requirements.

[0039] The above-mentioned entrance quality prediction model: uses a supervised machine learning algorithm, takes the acoustic emission signal in the drilling stage as the input feature, and takes the entrance quality index (such as entrance diameter consistency, surface roughness, etc.) as the output label to train the entrance quality prediction model;

[0040] The above-mentioned hole wall quality prediction model: uses a supervised machine learning algorithm, takes the acoustic emission signal in the drilling stage as the input feature, and takes the hole wall quality index (such as hole wall thickness uniformity, cracks or damage conditions, etc.) as the output label to train the hole wall quality prediction model;

[0041] The above-mentioned export quality prediction model: uses a supervised machine learning algorithm, takes the acoustic emission signal in the drilling stage as the input feature, and takes the export quality index (such as export diameter, burr condition, etc.) as the output label to train the export quality prediction model.

[0042] After the training of each prediction model is completed, the model verification and optimization steps are carried out to improve the prediction accuracy and generalization ability of the model through methods such as cross-validation and hyperparameter tuning.

[0043] Each prediction model outputs the corresponding hole quality index evaluation value according to the input acoustic emission signal, realizing real-time monitoring and prediction of hole making quality. Finally, the processing parameters are adjusted according to the prediction results to realize instant feedback and optimization of hole making quality.

[0044] This embodiment also successfully achieved real-time monitoring and prediction of hole quality during the drilling process of aluminum alloy materials through the above method. The experimental results show that the system can accurately judge the drilling stage and effectively predict key indicators such as entrance quality, hole wall quality and exit quality. In addition, through real-time feedback and adjustment of processing parameters, the drilling quality and production efficiency are significantly improved, and the scrap rate and production cost are reduced.

[0045] Example 2

[0046] This embodiment provides a hole quality intelligent detection system based on acoustic emission signals, including:

[0047] Data acquisition module: used to collect the acoustic emission signals generated during the drilling process in real time and perform preprocessing;

[0048] Stage classification module: used for inputting the pre-processed acoustic emission signal into the hole stage classification model for processing, and outputting the drilling stage corresponding to the acoustic emission signal;

[0049] The quality prediction module is used to input the acoustic emission signal into the corresponding prediction model based on the determined drilling stage, and output the quality prediction result of the drilling at the drilling stage.

[0050] Specifically, the system is divided into hardware and software parts, where the hardware part is:

[0051] Acoustic emission sensor: Select a high-sensitivity, wide-band acoustic emission sensor and install it at a suitable position on the drilling equipment to capture the acoustic emission signals generated during the drilling process.

[0052] Data acquisition module: It consists of a high-performance data acquisition card and related software, responsible for receiving signals from the acoustic emission sensor and performing preliminary filtering and digital processing.

[0053] Computing platform: equipped with high-performance computers or servers for running hole stage classification models, entrance quality prediction models, hole wall quality prediction models and exit quality prediction models.

[0054] The software part is:

[0055] Signal processing software: used to further pre-process the collected acoustic emission signals, including denoising, feature extraction, etc., to improve the accuracy and efficiency of model training.

[0056] Machine Learning Framework: Use a deep learning framework such as TensorFlow or PyTorch to build and train supervised machine learning models.

[0057] User Interface: Develop a user-friendly user interface to display real-time prediction results, historical data analysis, and machining parameter adjustment suggestions.

[0058] The rest is the same as in Example 1.

[0059] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0060] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0064] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0065] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent hole quality detection method based on acoustic emission signals, characterized in that: The following steps are involved: Real-time collection of acoustic emission signals generated during drilling and pre-processing; Inputting the preprocessed acoustic emission signal into a hole stage classification model for processing, and outputting the drilling stage corresponding to the acoustic emission signal; Based on the determined drilling stage, the acoustic emission signal is input into a corresponding prediction model, and a prediction result of the drilling quality during the drilling stage is output.

2. The method for intelligent hole quality detection based on acoustic emission signals according to claim 1, characterized in that: An acoustic emission sensor is used to collect the acoustic emission signal in real time.

3. The method for intelligent hole quality detection based on acoustic emission signals according to claim 1, characterized in that: The preprocessing operations include filtering, denoising, and feature extraction.

4. The method for intelligent hole quality detection based on acoustic emission signals according to claim 3 is characterized in that: The extracted features include the amplitude, frequency and energy of the acoustic emission signal.

5. The method for intelligent hole quality detection based on acoustic emission signals according to claim 1, characterized in that: The drilling stage includes three stages, namely, a drilling-in stage, a drilling-in stage and a drilling-out stage.

6. The method for intelligent hole quality detection based on acoustic emission signals according to claim 5, characterized in that: The prediction model includes an entrance quality prediction model, a hole wall quality prediction model and an exit quality prediction model, wherein the input of the entrance quality prediction model is the acoustic emission signal of the drilling stage, the input of the hole wall quality prediction model is the acoustic emission signal of the drilling stage, and the input of the exit quality prediction model is the acoustic emission signal of the drilling stage.

7. The method for intelligent hole quality detection based on acoustic emission signals according to claim 6, characterized in that: The quality prediction results of the inlet quality prediction model include inlet diameter consistency and surface roughness; the quality prediction results of the hole wall quality prediction model include hole wall thickness uniformity, cracks, and damage; the quality prediction results of the outlet quality prediction model include outlet diameter and burr conditions.

8. The method for intelligent hole quality detection based on acoustic emission signals according to claim 1, characterized in that: The prediction model is trained using a supervised machine learning algorithm, and the supervised machine learning algorithm includes one of a support vector machine, a random forest, a neural network, and a deep learning algorithm.

9. An intelligent hole quality detection system based on acoustic emission signals, characterized in that: include: Data acquisition module: used to collect the acoustic emission signals generated during the drilling process in real time and perform preprocessing; Stage classification module: used for inputting the pre-processed acoustic emission signal into the hole stage classification model for processing, and outputting the drilling stage corresponding to the acoustic emission signal; The quality prediction module is used to input the acoustic emission signal into the corresponding prediction model based on the determined drilling stage, and output the quality prediction result of the drilling at the drilling stage.

10. A computer-readable storage medium, characterized in that: The method comprises one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs comprise instructions for executing the intelligent hole quality detection method based on acoustic emission signals as claimed in any one of claims 1 to 8.

Images