Online monitoring and feedback control system for cladding quality of inner wall of ultra-long deep hole

Abstract

The invention relates to the field of in-hole cladding quality detection, in particular to an on-line monitoring and feedback control system for cladding quality of an inner wall of an ultra-long deep hole, which comprises a detection probe for carrying out real-time detection in a mode of integrating ultrasonic flaw detection, X-ray real-time imaging and spectral analysis, the intelligent feedback adjusting unit is mainly composed of a control system containing a machine learning model. Compared with the prior art, the system has the advantages that firstly, the detection probe is installed beside the cladding laser head and moves along with the working path of the cladding laser head, tracking type real-time detection is achieved, the detection probe achieves multi-mode detection of a hole wall cladding layer by integrating ultrasonic flaw detection, X-ray real-time imaging and spectral analysis, and the detection accuracy is improved. And detection data is subjected to defect analysis through a control system, and a subsequent processing strategy is properly and timely adjusted, so that the defect detection rate is greater than or equal to 99%, the detection speed is synchronous with the processing speed, the cladding qualification rate is increased to 98% from 75%, and the comprehensive cost is reduced by 30%.

Description

Technical Field

[0001] The present invention relates to the field of in-hole cladding quality detection, and in particular to an online monitoring and feedback control system for the cladding quality of the inner wall of an ultra-long deep hole. Background Art

[0002] The deep hole inner wall cladding process has strong sealing properties, and traditional offline testing cannot identify defects in a timely manner, resulting in a high rework rate;

[0003] Existing online monitoring systems are mostly limited to surface topography analysis and lack the ability to accurately detect internal defects (such as microcracks and lack of fusion);

[0004] For this purpose, an online monitoring and feedback control system for the cladding quality of the inner wall of an ultra-long deep hole is provided. Summary of the Invention

[0005] (1) Technical problems solved

[0006] The technical problem to be solved by the present invention is that the traditional detection method performs quality inspection after cladding processing. Defects cannot be corrected in time, resulting in the entire processing process being scrapped and rework being required. In addition, the detection level is low and cannot meet the requirements of high-precision in-depth detection.

[0007] (2) Technical solution

[0008] In order to solve the above technical problems, the present invention provides a technical solution: an online monitoring and feedback control system for the cladding quality of the inner wall of an ultra-long deep hole, including a detection probe.

[0009] The detection probe contains a multimodal detection module and an intelligent feedback control unit.

[0010] The multimodal detection module realizes the simultaneous detection of internal defects and components of the hole wall cladding layer by integrating ultrasonic flaw detection, X-ray real-time imaging and spectral analysis.

[0011] The intelligent feedback control unit includes a control system that is interconnected with the multimodal detection module. The control system is interconnected with the laser irradiation power of the laser head, the powder feeding rate of the powder feeder, and the scanning speed of the detection probe through dynamic adjustment.

[0012] Furthermore, the frequency of the integrated ultrasonic flaw detection is 5 MHz, the resolution is 0.1 mm, the resolution of the X-ray real-time imaging is 10 μm, and the wavelength range of the spectral analysis is between 200-1100 nm.

[0013] Furthermore, the detection probe is coaxially installed with the laser head of the cladding instrument to achieve follow-up scanning.

[0014] Furthermore, it also includes a cladding defect database. The control system and the cladding defect database are mutually associated with a machine learning model. The control system uses the machine learning model to predict process parameters and adjust cladding and detection strategies.

[0015] (3) Beneficial effects

[0016] The advantages of the present invention compared with the existing technology are: the system first installs the detection probe next to the cladding laser head, moves along its working path, and realizes tracking real-time detection. The detection probe realizes multimodal detection of the hole wall cladding layer through integrated ultrasonic testing, X-ray real-time imaging and spectral analysis, and the detection data is analyzed through the defect analysis of the control system to make appropriate and timely adjustments to the subsequent processing strategy, so that the defect detection rate is ≥99%, the detection speed is synchronized with the processing speed, the cladding qualification rate is increased from 75% to 98%, and the overall cost is reduced by 30%. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of the on-line monitoring and feedback control system for the inner wall cladding quality of an ultra-long deep hole during the detection process of the present invention. DETAILED DESCRIPTION

[0018] The present invention will be described in further detail below with reference to the accompanying drawings.

[0019] In order to solve the above technical problems, the technical solution provided by the present invention is:

[0020] Example 1

[0021] Ultra-long deep hole inner wall cladding quality online monitoring and feedback control system, combined with the attached Figure 1 , including a detection probe, which is coaxially installed with the laser head of the cladding instrument to achieve follow-up scanning, and the detection probe contains a multi-modal detection module and an intelligent feedback control unit;

[0022] The multimodal detection module includes an integrated ultrasonic flaw detection function with a frequency of 5 MHz and a resolution of 0.1 mm, an X-ray real-time imaging function with a resolution of 10 μm, and a spectral analysis function with a wavelength range of 200-1100 nm;

[0023] It integrates ultrasonic testing, X-ray real-time imaging and spectral analysis to achieve simultaneous detection of internal defects and components of the hole wall cladding layer;

[0024] The multimodal detection module performs real-time quality inspection of the cladding layer during the hole wall cladding process through multi-angle and multi-method detection. The detection probe is installed on the laser head and moves along the cladding processing path to realize tracking detection. Through real-time, point-to-point quality detection, it can effectively find deficiencies, discover problems in time, and make reasonable adjustments through the intelligent feedback control unit.

[0025] Example 2

[0026] Combined with attachment Figure 1 , the intelligent feedback control unit includes a control system interconnected with the multimodal detection module, and the control system is interconnected with the laser irradiation power of the laser head, the powder feeding rate of the powder feeder and the scanning speed of the detection probe through dynamic adjustment;

[0027] Based on the problems found in the inspection report, the control system sends instructions to the corresponding terminal in a timely manner to adjust parameters such as laser power, powder feeding rate and scanning speed, so as to avoid the recurrence of the corresponding defects as much as possible in the subsequent cladding process;

[0028] The control system and the cladding defect database are mutually associated with a machine learning model, and the control system predicts process parameters and adjusts cladding and detection strategies through the machine learning model;

[0029] There are many situations when the quality defects of the hole wall cladding layer are subdivided. These discovered accident states are stored in the cloud to establish a cladding defect database as reference information for resource sharing. A machine learning model is associated with the system and the cloud database. It can effectively provide a response mechanism by combining the on-site trial detection data and historical fault defect information obtained from the two, predict the next cladding processing parameters, and provide relative adjustment strategies to maximize the quality of subsequent cladding processing and make the defect repair rate ≥90%.

[0030] In the specific implementation of the present invention, the detection probe included in the system is coaxially installed with the laser head of the cladding process;

[0031] While the laser head penetrates deep into the hole to perform cladding processing, the detection probe nearby also performs real-time quality inspection of the completed cladding layer from the perspective of integrated ultrasonic testing, X-ray real-time imaging and spectral analysis;

[0032] The detection data is sent back to the control system server. The control system determines whether the inspected cladding layer is defective after comparing it with the data downloaded from the cladding defect database, and performs defect analysis, process analysis and other related work. If there is a defect, the relevant control strategy is given, and the strategy instructions will be issued to each operating terminal to improve the subsequent cladding processing quality by changing and adjusting the laser power, powder feeding rate and scanning speed.

[0033] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An online monitoring and feedback control system for the cladding quality of the inner wall of an ultra-long deep hole, including a detection probe, is characterized by: The detection probe contains a multimodal detection module and an intelligent feedback control unit; The multimodal detection module integrates ultrasonic flaw detection, X-ray real-time imaging and spectral analysis to achieve simultaneous detection of internal defects and components of the hole wall cladding layer; The intelligent feedback control unit includes a control system that is interconnected with the multimodal detection module. The control system is interconnected with the laser irradiation power of the laser head, the powder feeding rate of the powder feeder, and the scanning speed of the detection probe through dynamic adjustment.

2. The online monitoring and feedback control system for cladding quality of the inner wall of an ultra-long deep hole according to claim 1 is characterized by: The frequency of the integrated ultrasonic flaw detection is 5 MHz, the resolution is 0.1 mm, the resolution of the X-ray real-time imaging is 10 μm, and the wavelength range of the spectral analysis is between 200-1100 nm.

3. The online monitoring and feedback control system for cladding quality of the inner wall of an ultra-long deep hole according to claim 1 is characterized by: The detection probe is coaxially installed with the laser head of the cladding instrument to achieve follow-up scanning.

4. The online monitoring and feedback control system for cladding quality of the inner wall of an ultra-long deep hole according to claim 1 is characterized by: It also includes a cladding defect database. The control system and the cladding defect database are mutually associated with a machine learning model. The control system uses the machine learning model to predict process parameters and adjust cladding and detection strategies.

Images