A heavy special-shaped variable thickness steel pipe laser adaptive cutting method and system

Abstract

The application discloses a heavy special-shaped variable-thickness steel pipe laser adaptive cutting method and system, relates to the technical field of heavy special-shaped workpiece cutting machining, and comprises the following steps: identifying the geometric shape, surface defects and material texture features of a workpiece and acquiring thickness distribution information of the workpiece according to a collected surface image of the workpiece; acquiring thickness data of different positions of the workpiece based on the thickness distribution information; acquiring an optimal cutting path based on the geometric shape, surface defects, material texture features and thickness data; executing a laser cutting task based on the optimal cutting path, and automatically adjusting laser power, pulse frequency and cutting speed according to thickness changes; and when vibration is detected, compensating for the vibration by means of reverse excitation or dynamic damping adjustment. The application solves the key technical problems in heavy special-shaped workpiece cutting and has a wide industrial application prospect and extremely high popularization value.

Description

Technical Field

[0001] This invention relates to the field of heavy-duty irregular workpiece cutting and processing technology, and more specifically, to a laser adaptive cutting method and system for heavy-duty irregular-shaped variable-thickness steel pipes. Background Technology

[0002] Cutting technology has always faced significant challenges in the machining of heavy, irregularly shaped workpieces, especially for complex workpieces such as steel pipes with varying thicknesses. Traditional machining methods struggle to simultaneously meet the requirements of high efficiency, high precision, and stability. These workpieces often exhibit characteristics such as large mass, complex geometry, and significant thickness variations, and existing technologies have revealed numerous shortcomings in practical applications.

[0003] Traditional cutting methods mainly rely on two approaches: (1) Workpiece rotation scheme: This method clamps and fixes the workpiece on a rotating mechanism, allowing the workpiece to rotate in conjunction with the laser to complete the cutting. Although this scheme is suitable for small and medium-sized workpieces with regular shapes, it shows obvious limitations in heavy and irregularly shaped workpieces. First, the weight of large workpieces may reach several tons or even higher, and the center of gravity is difficult to control during rotation. Slight imbalance will cause severe machine tool vibration, which will lead to processing errors and equipment damage. Second, the complex geometry makes the rotation clamping process time-consuming and labor-intensive, and improper workpiece fixing may also lead to accidental detachment, posing a high operational risk. (2) Laser multi-axis movement scheme: In this technical scheme, the workpiece remains stationary, while the laser moves and adjusts through a multi-axis linkage system to complete the cutting. Although this method can solve the center of gravity problem caused by workpiece rotation, the flexibility and response speed of existing lasers are limited. Especially when dealing with steel pipes of varying thickness, it is difficult to achieve real-time dynamic adjustment of laser power and cutting trajectory, which can easily lead to overcutting or incomplete cutting. Furthermore, due to the limited range of laser movement, it is difficult to cover the cutting area of ​​some complex workpieces, which further limits the application scope in actual production.

[0004] Some studies have attempted to improve upon traditional technologies, such as: (1) Adaptive control technology: By adding a thickness detection module, the system can adjust the laser power according to the thickness change of the workpiece. However, this type of technology is often based on offline detection data and cannot achieve real-time adjustment, and is still insufficient in terms of processing speed and accuracy. (2) High-rigidity machine tool design: In order to solve the problem of machine tool vibration, some solutions improve stability by increasing the rigidity and mass of the machine tool, but this also brings problems of bulky equipment and high cost, and cannot fundamentally solve the dynamic imbalance caused by the shift of the center of gravity. (3) Local clamping and vibration reduction technology: Vibration reduction clamping devices are used to reduce vibration when fixing workpieces, but for the complex geometric characteristics of irregular workpieces, the adaptability of this device is poor and the actual effect is limited.

[0005] Comprehensive analysis shows that although the existing technical solutions have solved some problems to a certain extent, the following technical bottlenecks still exist: (1) Unstable center of gravity: The center of gravity shift caused by the rotation of heavy workpieces cannot be completely eliminated, and even if the rigidity of the machine tool is strengthened, the problem of processing vibration cannot be effectively avoided. (2) Poor adaptability to thickness changes: When dealing with workpieces of varying thickness, the existing laser cutting technology has a slow response speed in adjusting the laser power and trajectory, resulting in low processing accuracy and even workpiece damage. (3) Difficulty in covering complex workpieces: The laser has a limited range of movement and flexibility, and it is difficult to complete high-quality cutting in some areas when facing irregularly shaped workpieces. (4) Mismatch between efficiency and cost: While improving processing accuracy, the existing improvement solutions often sacrifice processing efficiency, and the high equipment cost is difficult to meet the needs of large-scale industrial production. Summary of the Invention

[0006] To address the aforementioned problems, the present invention aims to provide an adaptive laser cutting technology for variable thickness steel pipes used in heavy, irregularly shaped workpieces. By combining multi-degree-of-freedom rotation of the laser, adaptive thickness detection, and center of gravity correction technology, it thoroughly solves the problems of unstable center of gravity, low cutting accuracy, and poor thickness adaptability in the processing of heavy, irregularly shaped workpieces, providing a comprehensive solution for the efficient cutting of variable thickness steel pipes and similar complex workpieces.

[0007] To achieve the above technical objectives, this application provides a laser adaptive cutting method for heavy-duty irregularly shaped variable thickness steel pipes, comprising the following steps:

[0008] Based on the collected surface images of the workpiece, the geometric shape, surface defects and material texture features of the workpiece are identified, and the thickness distribution information of the workpiece is obtained.

[0009] Based on thickness distribution information, thickness data at different locations on the workpiece are obtained;

[0010] The optimal cutting path is obtained based on geometric shape, surface defects, material texture features, and thickness data.

[0011] Based on the optimal cutting path, the laser cutting task is executed, and the laser power, pulse frequency and cutting speed are automatically adjusted according to the thickness change. At the same time, when vibration is detected, the vibration is compensated through reverse excitation or dynamic damping adjustment.

[0012] Preferably, when acquiring surface images of a workpiece, the spectrum, intensity, and angle of the light source are dynamically adjusted to acquire surface images of workpieces with different materials, colors, and surface roughness. In this case, a combination of multi-band light sources is used to enhance the contrast of texture features and obtain material texture features.

[0013] Preferably, when acquiring surface images, the image acquisition frame rate is set according to the cutting speed and accuracy requirements.

[0014] Preferably, when obtaining the thickness distribution information of the workpiece, a pattern is projected onto the workpiece surface to obtain the deformation pattern of the workpiece at different angles. Using the principle of triangulation, the geometric relationship between the deformation pattern acquisition point and the pattern projection point, as well as the degree of pattern deformation, is calculated to obtain the three-dimensional coordinates of each point on the workpiece surface, thereby generating the thickness distribution information of the workpiece.

[0015] Preferably, when acquiring thickness data at different locations of the workpiece, based on the thickness distribution information, a laser is used to excite ultrasonic waves to propagate inside the workpiece, and the thickness at different locations of the workpiece is measured by receiving and analyzing the ultrasonic echo signals.

[0016] Preferably, when obtaining the optimal cutting path, based on geometric shape, surface defects, material texture features and thickness data, a digital twin model of the cutting process is established to pre-simulate and optimize the cutting path, with the goal of ensuring cutting efficiency and accuracy, in order to obtain the optimal cutting path.

[0017] Preferably, when performing a laser cutting task, the laser power and cutting speed are automatically adjusted using a fuzzy control algorithm based on the real-time thickness, material properties, and cutting process requirements of the workpiece. The fuzzy control algorithm is used to establish a fuzzy control rule base based on the real-time thickness, material properties, and preset cutting process rules of the workpiece; to perform inference in the fuzzy control rule base based on the fuzzified input to obtain the fuzzy control output; and to convert the fuzzy output into a control quantity through defuzzification processing.

[0018] Preferably, during the laser cutting process, when encountering workpiece surface defects, sudden thickness changes, or minor deviations during cutting, the cutting path is dynamically adjusted based on real-time feedback of three-dimensional topographic data and cutting force sensor signals to bypass defect areas or adjust the cutting direction. Specifically, for small defects that do not affect the overall structural strength, the cutting path is finely adjusted to allow the laser beam to avoid the defect area; for larger defects, a completely new cutting path is planned; and for sudden thickness changes, the cutting speed and laser power are adjusted according to the magnitude and location of the change, combined with the laser cutting capability, while the cutting path is replanned.

[0019] Preferably, when planning the cutting path, a path planning method combining genetic algorithm and neural network is used based on the three-dimensional model of the workpiece and the cutting process requirements. In the genetic algorithm, the cutting path is encoded as chromosomes, the fitness value of each chromosome is calculated, and the selection operation adopts roulette wheel selection, so that the probability of each chromosome being selected is proportional to its fitness value. Partial matching crossover is used to randomly select partial gene segments of two chromosomes for exchange and to handle gene conflict problems. The neural network is used to predict the optimal cutting path and parameters under different conditions by learning the complex relationship between the workpiece shape, thickness, material and cutting equipment performance and the optimal cutting parameters.

[0020] This invention discloses a heavy-duty irregular-shaped variable-thickness steel pipe laser adaptive cutting system, used to implement the aforementioned heavy-duty irregular-shaped variable-thickness steel pipe laser adaptive cutting method, comprising:

[0021] The data acquisition and analysis module is used to identify the geometric shape, surface defects and material texture features of the workpiece based on the acquired surface image of the workpiece, and to obtain the thickness distribution information of the workpiece.

[0022] The thickness detection module is used to acquire thickness data at different locations on the workpiece based on thickness distribution information.

[0023] The path planning module is used to obtain the optimal cutting path based on geometry, surface defects, material texture features, and thickness data.

[0024] The cutting task execution module is used to execute laser cutting tasks based on the optimal cutting path and automatically adjust the laser power, pulse frequency and cutting speed according to the thickness change;

[0025] The vibration compensation module is used to compensate for vibration by reverse excitation or dynamic damping adjustment when vibration is detected.

[0026] The quality assessment module is used to evaluate the cutting quality by acquiring cutting temperature, cutting force, and smoke concentration during laser cutting tasks.

[0027] The fault diagnosis module is used to quickly locate the cause of a fault after a fault is detected in the equipment by using diagnostic methods based on fault tree analysis (FTA) and neural networks.

[0028] The present invention discloses the following technical effects:

[0029] This invention allows for flexible selection of laser source type based on workpiece material and cutting requirements. Common equipment may only be compatible with a single or a few types of laser sources, making it difficult to meet diverse processing needs.

[0030] The multi-degree-of-freedom laser head designed in this invention integrates a high-precision motor drive system, combined with a built-in attitude sensor and feedback control system, which can accurately adjust the angle and position of the laser head to ensure that the laser beam is always in the optimal cutting path.

[0031] The beam transmission system of this invention, consisting of a high-precision reflector and an optical fiber assembly, can better ensure that the beam quality is not significantly affected during transmission.

[0032] The laser source, beam transmission system, multi-degree-of-freedom laser head, attitude sensor, and feedback control system mentioned in this invention form an efficient collaborative working mechanism.

[0033] This invention relates to a strategy and method for making the cutting process more intelligent by using real-time workpiece information, monitoring data with attitude sensors, and adjusting parameters such as laser head attitude and laser source power in real time through a feedback control system. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram of the multi-degree-of-freedom fixture described in this invention;

[0036] Figure 2 This is a schematic diagram of the laser clamping and cutting motion described in this invention;

[0037] Figure 3 This is a schematic diagram of the laser cutting process described in this invention;

[0038] Figure 4 This is a schematic diagram illustrating the working principle of machine vision as described in this invention;

[0039] Figure 5 This is a schematic diagram of the workpiece information recognition process based on deep learning as described in this invention;

[0040] Figure 6 This is a schematic diagram of the thickness detection and feedback control operation described in this invention;

[0041] Figure 7 This is a schematic diagram of the workflow of the path planning algorithm described in this invention;

[0042] Figure 8 This is a schematic diagram illustrating the actual processing and virtual model operation described in this invention;

[0043] Figure 9This is a schematic diagram illustrating the working principle of the vibration compensation mechanism described in this invention;

[0044] Figure 10 This is a flowchart of the multi-sensor information acquisition process described in this invention;

[0045] Figure 11 This is a flowchart illustrating the cutting parameters and path adjustment process described in this invention;

[0046] Figure 12 The present invention relates to an adaptive laser cutting device for variable thickness steel pipes used for heavy-duty irregular workpieces, comprising: 1. a multi-degree-of-freedom laser fixture; 2. a gantry rail; 3. a laser; 4. a workpiece; 5. an industrial camera; 6. a strip light source; 7. an industrial lens; 8. a workpiece; 9. a ring light source; 61. a honeycomb panel; 62. a connecting rib; 63. a high-precision motor; and 64. an industrial camera. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0048] like Figure 1-12 As shown, this invention provides an innovative heavy-duty irregular workpiece cutting solution that integrates multiple cutting-edge technologies, mainly including advanced machine vision technology, intelligent adaptive laser control technology, high-precision thickness detection technology, intelligent path planning algorithm, and efficient vibration compensation mechanism. It is committed to overcoming the long-standing problems of unstable precision, poor cutting quality, and low processing efficiency in the field of heavy-duty and irregular workpiece cutting, and provides efficient, accurate, and stable cutting solutions for related industrial production.

[0049] The adaptive laser cutting system of the present invention consists of multiple closely coordinated core modules, including a high-performance laser cutting device, an advanced machine vision system, a precise thickness detection and feedback control system, an intelligent adaptive path planning and control algorithm, and an efficient vibration compensation mechanism. The modules work together to achieve high-quality cutting of heavy and irregularly shaped workpieces.

[0050] like Figure 1As shown, the multi-degree-of-freedom fixture can hold an industrial camera 64 or a laser. Through programming, the high-precision motor 63 is controlled to move, positioning the fixture end (holding the industrial camera 64 or laser, etc.) in a suitable spatial position, thereby achieving image acquisition and cutting. Further explanation: the honeycomb plate 61 is fixed in a suitable position on the machine tool, and the connecting rib plate 62 is connected to the honeycomb plate 61. The high-precision motor 63 actuates, causing the mechanism to move and position the fixture end in a suitable working state.

[0051] like Figure 2 As shown, the laser 3 is held by a multi-degree-of-freedom fixture 1, which can move on a gantry rail 2, with the workpiece 4 located directly below the laser. Further, this laser integrates a high-precision motor drive system, capable of rapidly and accurately adjusting its angle and position in space according to the complex shape and thickness variations of the workpiece. Through a built-in attitude sensor and feedback control system, it ensures that the laser beam is always perpendicular to the workpiece surface or travels along the theoretically optimal cutting path, effectively avoiding cutting deviations caused by workpiece instability or irregular shapes, thus guaranteeing cutting accuracy. For example, when cutting large, irregularly shaped steel structures, the laser can be adjusted in real time to ensure the laser beam acts stably on the workpiece surface, improving cutting quality.

[0052] like Figure 3 As shown, the core of a laser cutting device is a high-power laser source. The type of laser source is selected based on the workpiece material and cutting requirements. For example, fiber lasers can be used for metal workpieces, with output power in the kilowatts or even higher, to meet the cutting needs of thick plates. After the laser beam is emitted from the laser source, it is transmitted through a beam transmission system. This system includes a series of high-precision mirrors and fiber optic components. The mirrors are used to adjust the beam direction, while the fibers are responsible for efficiently transmitting the beam and ensuring that the beam quality is not significantly affected during transmission.

[0053] like Figure 3 As shown, the high-precision motor drive system of the multi-degree-of-freedom laser consists of multiple servo motors working in tandem. These servo motors control the laser's linear motion in the X, Y, and Z axes, as well as its rotational motion around the X, Y, and Z axes, respectively, enabling precise attitude adjustment of the laser in three-dimensional space. The built-in attitude sensor employs a high-precision inertial measurement unit (IMU), which can monitor the laser's acceleration and angular velocity information in real time, thereby accurately acquiring the laser's attitude.

[0054] The feedback control system transmits data collected by the attitude sensor to the control system. Based on the received workpiece data (such as CAD model data, real-time measured workpiece contour and thickness data), the control system calculates the ideal position and angle of the laser using a preset control algorithm (such as a model predictive control algorithm). The control system then sends control commands to the motor drive system based on the calculated control values, driving the servo motors to adjust the laser to the target position and angle, ensuring the laser beam acts on the workpiece surface in the best possible way.

[0055] like Figure 4 As shown, the machine vision system, as one of the core technologies, utilizes a high-resolution, wide-field-of-view industrial camera 5, along with multispectral bar light sources 6 and ring light sources 9 for illumination, to acquire real-time images of the workpiece surface 8 from multiple angles. Using deep learning image processing algorithms, the system can automatically identify the workpiece's geometric shape, surface defects, material texture, and other features. Simultaneously, combined with structured light 3D measurement technology, it accurately obtains the workpiece's thickness distribution information. Furthermore, the control system can dynamically adjust the spectrum, intensity, and angle of the light source according to the existing working conditions to ensure clear and accurate image data is acquired on workpieces of different materials, colors, and surface roughnesses, providing a reliable basis for subsequent cutting control.

[0056] like Figure 4 As shown, multispectral illumination technology integrates various light sources of different wavelengths, such as visible light (400-700nm) and near-infrared light (700-2500nm). The system automatically selects an appropriate combination of light sources for workpieces of different materials. Furthermore, the system's decision-making is based on the assessment of data related to different materials. For example, for metal workpieces with strong surface reflectivity, the proportion of near-infrared light can be increased to reduce the impact of reflection on image acquisition; for non-metallic workpieces with complex surface textures, a multi-band light source combination can be used to enhance the contrast of texture features.

[0057] To further explain, the industrial camera is equipped with a high-resolution image sensor and a wide-angle lens, enabling it to acquire images of the workpiece surface with a large field of view. The camera's frame rate is set according to the cutting speed and precision requirements. During high-speed cutting, the frame rate can be increased to ensure real-time image quality; during high-precision cutting, the frame rate can be appropriately reduced to improve image quality.

[0058] like Figure 5As shown, the deep learning image processing algorithm is built on a convolutional neural network (CNN) architecture. During the training phase, a large amount of image data containing different workpiece shapes, defects, and material textures is used. The network automatically extracts features from the images through components such as convolutional layers, pooling layers, and fully connected layers. Structured light 3D measurement technology projects specific structured light patterns, such as Gray code patterns or sinusoidal fringe patterns, onto the workpiece surface. When the pattern is projected onto the workpiece surface, it deforms due to changes in the workpiece's height. An industrial camera captures the deformed pattern from different angles. Using the principle of triangulation, the geometric relationship between the camera and the projector, as well as the degree of pattern deformation, is calculated to accurately determine the 3D coordinates of each point on the workpiece surface, thereby obtaining the workpiece's thickness distribution information.

[0059] like Figure 6 As shown, the thickness detection and feedback control system is equipped with a high-precision laser ultrasonic thickness detection device to solve the problem of uneven thickness in irregularly shaped workpieces. It utilizes a laser to excite ultrasonic waves that propagate inside the workpiece, and by receiving and analyzing the ultrasonic echo signals, it accurately measures the thickness at different locations on the workpiece. The detection data is transmitted to the control unit in real time. The control unit uses an adaptive control algorithm to automatically adjust the laser power, pulse frequency, and cutting speed according to thickness changes. For example, when cutting pressure vessel plates with varying thicknesses, the system can dynamically adjust the laser parameters based on thickness changes to ensure consistent cutting quality and avoid cutting defects.

[0060] To further explain, the working principle of the laser ultrasonic thickness measuring device is based on the thermoelastic excitation effect. A laser emitter emits short pulses of laser light, focusing them onto a very small area on the workpiece surface. This area rapidly heats up and expands under the influence of the laser energy, generating ultrasonic waves. These ultrasonic waves propagate within the workpiece, and are reflected and refracted when they encounter interfaces between different media (such as interfaces between areas of different thicknesses). An ultrasonic receiver is installed in a suitable location to receive the reflected echo signals and convert them into electrical signals.

[0061] To further explain, the signal processing unit amplifies, filters, and digitizes the electrical signal received from the ultrasonic receiver. By accurately measuring the propagation time of the echo signal and combining it with the known propagation speed of ultrasound in the workpiece material, the formula is used... (where d is thickness, v is sound velocity, and t is propagation time) The workpiece thickness is calculated. The adaptive control algorithm employs a model predictive control (MPC) strategy. This algorithm first establishes a predictive model based on the workpiece material, initial thickness, and preset cutting quality targets. During the cutting process, the algorithm uses real-time measured thickness data and the predictive model to predict the optimal adjustment values ​​for laser power, pulse frequency, and cutting speed over a future period to ensure consistent cutting quality.

[0062] like Figure 7As shown, the adaptive path planning and control algorithm, based on deep learning and intelligent optimization algorithms, performs in-depth analysis of the acquired workpiece geometry, surface features, and thickness data to calculate the globally optimal cutting path. Further, the algorithm considers not only the static geometry of the workpiece but also dynamic factors during processing, such as the heat effect of cutting and minor workpiece deformation, dynamically adjusting the cutting path. By establishing a digital twin model of the cutting process, the cutting path is pre-simulated and optimized, ensuring that the laser cutting head always moves along the optimal path, improving cutting efficiency and accuracy.

[0063] To further explain, the deep learning algorithm first extracts features from the workpiece's geometry, surface characteristics, and thickness. A convolutional neural network is used to process the workpiece's two-dimensional image data, extracting features such as edges and textures. For thickness data, a specialized deep neural network structure is used for feature learning. These feature data are then input into an intelligent optimization algorithm, such as Particle Swarm Optimization (PSO) or simulated annealing. During processing, sensors monitor dynamic factors in real time, such as the temperature distribution in the heat-affected zone and minor workpiece deformations. When changes in these dynamic factors are detected, the optimization algorithm is restarted to dynamically adjust the cutting path. For example, if the temperature in the heat-affected zone is found to be too high, potentially causing workpiece deformation, the algorithm will adjust the cutting path to avoid the overheated area, or adjust the cutting speed and laser power to reduce the heat impact. Figure 8 As shown, the actual processing process corresponds one-to-one with the virtual model processing process, which is beneficial for monitoring and controlling the actual processing situation. The digital twin model constructs a model in virtual space that is completely identical to the actual cutting process by collecting real-time equipment operation data (such as laser power, cutting speed, laser position, etc.) and processing data (such as cutting depth, cutting quality inspection data, etc.). Through simulation of the digital twin model, the cutting results under different cutting paths and parameter settings can be predicted, providing a reference for path planning and parameter adjustment.

[0064] like Figure 9 As shown, the vibration compensation mechanism addresses vibration issues generated during the machining of heavy workpieces. The system is equipped with high-precision vibration sensors to monitor the vibration status of the machine tool, workpiece, and laser in real time. Employing active vibration control technology, when vibration is detected, the system rapidly adjusts the laser's trajectory, laser power, and cutting speed. Through reverse excitation or dynamic damping adjustment, it effectively compensates for the impact of vibration on cutting quality. Simultaneously, the machine tool's structural design and dynamic performance are optimized to improve its vibration resistance and ensure the stability of the cutting process.

[0065] To further explain, high-precision vibration sensors, employing piezoelectric vibration or accelerometer sensors, are installed in critical parts of the machine tool, such as the worktable, spindle, bed, laser, and workpiece. These sensors can monitor the amplitude, frequency, and direction of vibration in real time. Active vibration control technology utilizes electromagnetic or piezoelectric actuators. When the vibration sensor detects a vibration signal, the control system sends a control signal to the actuator based on the characteristics of the vibration. For example, electromagnetic actuators counteract the vibration by generating an electromagnetic force opposite to the direction of vibration; piezoelectric actuators compensate for vibration by utilizing the inverse piezoelectric effect of piezoelectric materials to generate a displacement opposite to the direction of vibration.

[0066] To further explain, the machine vision system plays a crucial role in the entire cutting process, providing precise data support for cutting control through image acquisition, processing, and analysis. Industrial cameras and multispectral light sources are used to acquire images of the workpiece surface under varying lighting conditions. Optical image stabilization and autofocus technologies ensure image clarity and stability. The acquired raw images undergo preprocessing operations such as filtering, noise reduction, and grayscale transformation to remove noise interference and enhance image contrast. Image enhancement algorithms are then applied to highlight the workpiece's edges and feature information, providing high-quality image data for subsequent shape and thickness recognition.

[0067] The geometric shape and thickness recognition process employs edge detection, contour extraction, and shape matching algorithms to identify the geometric shape and contour features of the workpiece. Multi-view image fusion technology is combined to acquire the workpiece's three-dimensional shape information. Using the principle of structured light measurement, the thickness distribution of the workpiece is calculated based on the deformation of the structured light pattern projected onto its surface. For complex, irregularly shaped workpieces, a deep learning-based semantic segmentation algorithm is used to accurately identify each part of the workpiece and areas of thickness variation, providing a precise basis for cutting path planning and parameter adjustment.

[0068] To further explain, in edge detection, the Canny edge detection algorithm is used. This algorithm extracts edges through the following steps: first, Gaussian filtering is applied to the image for noise reduction; then, the gradient magnitude and direction of the image are calculated; next, non-maximum suppression is performed to refine the edges; finally, double threshold detection and edge connection are used to obtain the final edge image. In contour extraction, a contour finding algorithm is used to extract the contour of the workpiece based on the edge image. For deep learning-based semantic segmentation algorithms, taking the U-Net network as an example, its network structure consists of an encoder and a decoder. The encoder gradually extracts image features through convolutional layers and pooling layers, while the decoder restores the low-resolution feature map to a segmentation result of the same size as the original image through upsampling and convolution operations.

[0069] Real-time feedback and control transmit the identified geometric shape and thickness data to the control system in real time. Based on this data and the cutting process requirements, the control system automatically calculates and adjusts various laser cutting parameters, such as laser power, cutting speed, and focal point position. During the cutting process, the machine vision system continuously monitors the workpiece status and provides real-time feedback data. The control system dynamically adjusts the cutting parameters based on this feedback information to ensure the accuracy and stability of the cutting process. Assuming the relationship between laser power P and cutting speed v, calculated using empirical formulas or machine learning models based on the workpiece's geometric shape and thickness data, is as follows:

[0070]

[0071] Where k1, k2, and k3 are coefficients obtained through fitting experimental data, and d is the workpiece thickness. The control system calculates the required laser power P based on the real-time monitored workpiece thickness d and the preset cutting speed v, and sends control commands to adjust the parameters of the laser cutting device.

[0072] The adaptive control feedback mechanism of this invention enables dynamic adjustment and optimization of the cutting process through multi-source data fusion and intelligent algorithms. Based on the real-time thickness, material properties, and cutting process requirements of the workpiece, the system automatically adjusts the laser power and cutting speed using a fuzzy control algorithm. For areas with greater thickness or difficult-to-cut materials, the laser power is appropriately increased and the cutting speed is reduced to ensure cutting depth and quality; for thinner areas, the laser power is reduced and the cutting speed is increased to avoid overcutting. Simultaneously, considering heat accumulation and the heat-affected zone during the cutting process, the laser power and cutting speed are dynamically adjusted to reduce thermal deformation and thermal impact. The fuzzy control algorithm first establishes a fuzzy control rule base based on the real-time thickness of the workpiece, material properties (such as the hardness and thermal conductivity of metals), and preset cutting process rules. For example, if the workpiece is thick and made of a high-hardness metal, the rule base may include rules to increase laser power and decrease cutting speed. During the actual cutting process, the real-time thickness d and material information (represented by parameters such as hardness H) of the workpiece are acquired through sensors, and this precise data is then fuzzified. Thickness data is divided into fuzzy sets such as "thin," "medium," and "thick," while material hardness information is divided into fuzzy sets such as "soft," "medium," and "hard." For example, for thickness d, the fuzzification function can be defined as:

[0073]

[0074] in, (The threshold is set according to the actual situation) Similarly, the material hardness... The system performs fuzzification processing on the input. Then, based on the fuzzified input, it infers from the fuzzy control rule base to obtain fuzzy control outputs, such as "increase power" or "decrease speed." Finally, through defuzzification, the fuzzy outputs are converted into precise control quantities, such as specific increases in laser power and decreases in cutting speed, thereby achieving precise adjustment of laser power and cutting speed. Simultaneously, the system monitors heat accumulation and the heat-affected zone (HAZ) during the cutting process using temperature sensors. If the HAZ temperature is too high, indicating significant heat accumulation, the system will appropriately reduce laser power or increase the cutting speed to minimize thermal deformation and HAZ.

[0075] The dynamic adjustment of the cutting path is achieved through an adaptive path planning algorithm that dynamically adjusts the cutting path based on real-time feedback data, combined with real-time shape changes and cutting status of the workpiece. When encountering workpiece surface defects, sudden thickness changes, or minor deviations during the cutting process, the algorithm replans the cutting path based on real-time feedback of 3D topographic data and cutting force sensor signals, bypassing defect areas or adjusting the cutting direction to ensure cutting quality. By real-time monitoring and prediction of thermal deformation and stress distribution during the cutting process, the cutting path is adjusted in advance to reduce deformation and stress concentration. During operation, the adaptive path planning algorithm continuously receives real-time feedback data from the machine vision system, thickness detection system, and various sensors during the cutting process.

[0076] To further explain, when encountering surface defects on the workpiece, such as cracks or pinholes, the algorithm first analyzes the location, size, and shape of the defect to determine its impact on cutting quality. If the defect is small and does not affect the overall structural strength, the algorithm may fine-tune the cutting path to ensure the laser beam avoids the defect area. If the defect is large, a completely new cutting path is planned to ensure the quality of the cut workpiece. For cases of sudden thickness changes, the algorithm adjusts the cutting speed and laser power based on the magnitude and location of the change, combined with the laser cutting capability, and simultaneously replans the cutting path to ensure stable, high-quality cutting in areas of varying thickness. For example, when a sudden increase in workpiece thickness is detected, the laser power is appropriately increased and the cutting speed is decreased, and the cutting path is adjusted so that the laser beam acts on the workpiece at a more suitable angle and trajectory.

[0077] The laser angle and position adjustment utilizes vibration and attitude sensors to monitor the vibration, tilt, and other conditions of the machine tool and workpiece in real time. When an anomaly is detected, the system automatically adjusts the laser angle and position via a high-precision servo control system. Employing an intelligent control algorithm, the optimal laser adjustment is calculated based on vibration and tilt data to ensure the laser beam is always perpendicular to the workpiece surface or along the optimal cutting path, compensating for errors caused by workpiece imbalance or vibration.

[0078] To further explain, after receiving sensor data, the high-precision servo control system activates an intelligent control algorithm. Based on vibration and tilt data, the intelligent control algorithm uses mathematical models and algorithms to calculate the required adjustment angle and position of the laser. For example, an adaptive PID control algorithm is used to dynamically adjust the parameters of the PID controller according to the current vibration and tilt conditions, achieving precise control of the laser. After calculating the optimal adjustment amount, the servo control system sends control commands to the laser's drive motor, which then precisely adjusts the laser's angle and position. During the adjustment process, the system continuously provides feedback on the laser's actual position and angle information to ensure accuracy. Through this closed-loop control, the laser beam is guaranteed to always be perpendicular to the workpiece surface or irradiate along the optimal cutting path, effectively compensating for errors caused by workpiece imbalance or vibration, and improving cutting accuracy.

[0079] Workpiece scanning and geometric information acquisition utilizes LiDAR and industrial cameras to perform omnidirectional scanning of the workpiece, obtaining high-precision point cloud data. Point cloud processing algorithms extract feature information such as the workpiece's outline, surface defects, and cracks. Combined with laser interferometry technology, the thickness at different locations on the workpiece is accurately measured, generating a 3D digital model of the workpiece. During the scanning process, the workpiece's clamping position and orientation are automatically identified, providing accurate geometric data for subsequent path planning and cutting control. The LiDAR, by emitting a laser beam and receiving reflected light, measures the distance information of various points on the workpiece surface based on the Time-of-Flight (ToF) principle.

[0080] The path planning and dynamic adjustment of cutting parameters, based on the workpiece's 3D model and cutting process requirements, employs a path planning method combining genetic algorithms and neural networks to automatically generate the optimal cutting path. During path planning, the shape, thickness, material of the workpiece, and the performance of the cutting equipment are fully considered to optimize the cutting sequence and direction. Based on real-time acquired thickness data and cutting status, cutting parameters such as laser power, cutting speed, and focal point position are dynamically adjusted to ensure consistent and stable cutting quality.

[0081] To further explain, in genetic algorithms, the cutting path is encoded as chromosomes. For example, using integer encoding, each gene represents a point traversed by the cutting path. The initial population is composed of a certain number of randomly generated chromosomes. The fitness value of each chromosome (i.e., the cutting path scheme) is calculated. The fitness function can be determined comprehensively based on factors such as cutting path length, cutting time, and cutting quality. For example, the fitness function can be defined as:

[0082]

[0083] Where L is the cutting path length, T is the cutting time, and Q is the cutting quality assessment value (which can be obtained by calculating the surface roughness, perpendicularity, etc.). The weighting coefficients are adjusted according to actual needs. The selection operation uses a roulette wheel selection method, where the probability of each chromosome being selected is proportional to its fitness value. The crossover operation uses partially matched crossover (PMX), randomly selecting partial gene segments from two chromosomes for exchange and handling gene conflicts. The mutation operation randomly changes the gene values ​​in the chromosomes with a certain probability. The neural network is used to learn the complex relationship between workpiece shape, thickness, material, cutting equipment performance, and optimal cutting parameters. The neural network is trained with a large amount of sample data to accurately predict the optimal cutting path and parameters under different conditions. During the cutting process, the workpiece thickness data d and cutting status information (such as cutting temperature T, cutting force F, etc.) are collected in real time. Based on this real-time data, combined with preset cutting process rules and models, the cutting parameters are dynamically adjusted. For example, when the cutting temperature is too high, the cutting speed v is adjusted using the following formula:

[0084]

[0085] in, The initial cutting speed, This is the normal cutting temperature. This is an adjustment coefficient. When the workpiece thickness changes, the laser power P is adjusted according to the formula:

[0086]

[0087] in, The initial laser power, For preset thickness, This is a coefficient related to the material of the workpiece.

[0088] The laser features automatic adjustment and vibration compensation. Equipped with a high-precision automatic adjustment mechanism, the laser's angle, position, and focal length are automatically adjusted based on the workpiece's real-time status and the cutting path. Magnetic levitation drive technology enhances the laser's response speed and positioning accuracy. Vibration sensors monitor the machine tool and workpiece vibrations in real time, employing a combination of active and passive vibration damping to effectively compensate for the impact of vibration on cutting accuracy. For example, when cutting large ship components, the system can adjust the laser in real time to ensure cutting accuracy is unaffected by vibration. The automatic laser adjustment mechanism consists of a motor, guide rails, and a transmission device.

[0089] A real-time monitoring and feedback system for the cutting process is implemented, with multiple sensors installed in the cutting area to collect data such as cutting temperature, cutting force, and smoke concentration in real time. Through data analysis and machine learning algorithms, a status monitoring model for the cutting process is established to evaluate cutting quality and equipment operating status in real time. When an anomaly is detected, the system automatically issues an alarm and adjusts cutting parameters or suspends cutting according to preset strategies to avoid scrap and equipment damage. Simultaneously, the data from the cutting process is stored and analyzed to provide a basis for subsequent process optimization and equipment improvement.

[0090] To further explain, a thermocouple sensor is used to measure the cutting temperature T. The temperature is calculated based on the Seebeck effect by measuring the thermoelectric potential. A strain gauge sensor is used to convert changes in force into changes in resistance, thereby measuring the cutting force F. A smoke concentration sensor utilizes optical principles to measure the smoke concentration C based on the scattering or absorption characteristics of light. A support vector machine (SVM) algorithm is used to establish a cutting quality assessment model.

[0091] The system features automation and control, achieving fully automated operation. Operators only need to input basic workpiece information and processing requirements, and the system automatically completes the entire process from scanning and path planning to cutting. Employing artificial intelligence technology, the system can intelligently adjust cutting parameters and path planning strategies based on historical data and real-time feedback, continuously optimizing the cutting process. It also possesses fault diagnosis and self-repair capabilities, automatically detecting equipment faults and guiding operators to perform maintenance or automatically repairing the equipment through remote monitoring and intelligent diagnostic technology, improving equipment reliability and stability. Automated operation is achieved through a human-machine interface (HMI). Operators input the workpiece's material M and dimensions on the HMI. The system receives the shape description S and processing requirements (such as cutting accuracy A, surface quality Q, etc.). After receiving this information, the system automatically starts the scanning program, using LiDAR and an industrial camera to scan the workpiece and acquire geometric information. Based on the acquired information, the system automatically performs path planning and sets cutting parameters.

[0092] To further explain, path planning employs a combination of genetic algorithms and neural networks, as described above. Cutting parameters are set based on the workpiece material and processing requirements, obtained by querying a process database or predicting using a machine learning model. For example, for a given material M and cutting precision A, the prediction formula for laser power P is: Here, g represents the functional relationship obtained through training. During the cutting process, the system utilizes deep learning algorithms, such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), to intelligently adjust cutting parameters and path planning strategies based on historical cutting data and real-time feedback on cutting status information. For example, RNNs process time-series data to learn the dynamic changes during the cutting process, predict future cutting states, and thus adjust parameters in advance. The system possesses fault diagnosis and self-repair capabilities. By installing sensors on key parts of the equipment, the operating status of the equipment is monitored in real time, such as motor speed n and temperature. The power of the laser source wait.

[0093] To further explain, when a device malfunction is detected, diagnostic methods based on fault tree analysis (FTA) and neural networks are used to quickly pinpoint the cause of the malfunction. For example, if the motor temperature is too high... And the rotation speed is abnormal. or The system uses fault tree analysis to determine if the problem is related to motor overheating or overload, and then uses neural networks to further pinpoint the specific cause. For simple faults, the system can automatically repair them, such as by adjusting parameters or restarting relevant components. For complex faults, the system sends fault information to operators via a remote monitoring system and provides maintenance guidance to help operators quickly repair the equipment.

[0094] This invention employs a processing mode where the workpiece is fixed and the laser rotates, thus avoiding the center of gravity shift problem caused by workpiece rotation. The laser achieves spatial positioning through a multi-degree-of-freedom rotation mechanism and is equipped with a dynamic center of gravity correction system and a high-efficiency vibration absorption device to ensure the stability and accuracy of the cutting process.

[0095] This invention introduces an advanced real-time thickness detection system, combined with laser power adaptive adjustment technology, to achieve dynamic response to workpieces with varying thicknesses. Workpiece thickness information is acquired through sensors, and a highly efficient feedback algorithm is used to adjust laser cutting parameters in real time, ensuring consistency in cutting depth and width and avoiding overcutting and undercutting phenomena common in traditional technologies.

[0096] The laser mentioned in this invention employs a multi-degree-of-freedom rotation mechanism, enabling flexible adjustment of angle and position to achieve comprehensive coverage of irregularly shaped workpieces. Whether it's complex curved surfaces, edge regions, or special structures, high-quality cutting can be achieved through the adaptive movement of the laser, greatly improving the adaptability and processing flexibility of the equipment.

[0097] To balance processing efficiency and cost, this invention employs a modular structure in its design, reducing manufacturing and maintenance costs by simplifying mechanical components. Simultaneously, it optimizes laser cutting path planning and control algorithms, significantly improving processing efficiency. Furthermore, many innovative functions within the device are optimized and integrated based on existing mature technologies, further reducing the economic burden of overall equipment development and application.

[0098] The design of this invention is highly versatile, particularly suitable for machining heavy, irregularly shaped workpieces in the oil pipeline, shipbuilding, and aerospace industries. Its high adaptability and efficiency can meet the diverse needs of different industries for machining complex workpieces, bringing significant technological advancements and economic benefits to the industrial manufacturing sector.

[0099] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] In the description of this invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0101] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A laser adaptive cutting method for heavy-duty irregularly shaped steel pipes with varying thickness, characterized in that, Includes the following steps: Based on the collected surface images of the workpiece, the geometric shape, surface defects, and material texture features of the workpiece are identified, and the thickness distribution information of the workpiece is obtained. Based on the thickness distribution information, thickness data at different locations of the workpiece are obtained; Based on the geometry, surface defects, material texture features, and thickness data, a globally optimal cutting path is generated using an intelligent algorithm. Based on the optimal cutting path, the laser cutting task is executed, and the laser power, pulse frequency and cutting speed are automatically adjusted according to the thickness change. At the same time, when vibration is detected, the vibration is compensated by reverse excitation. During laser cutting, when encountering workpiece surface defects, sudden thickness changes, or minor deviations in the cutting process, the cutting path is dynamically adjusted based on real-time feedback of 3D topographic data and cutting force sensor signals. This allows the cutting path to bypass defect areas or adjust the cutting direction. Specifically, for small defects that do not affect the overall structural strength, the cutting path is fine-tuned to ensure the laser beam avoids the defect area. For larger defects, a completely new cutting path is planned. For sudden thickness changes, the cutting speed and laser power are adjusted based on the magnitude and location of the change, combined with the laser cutting capability, while the cutting path is also replanned. When planning the cutting path, based on the 3D model of the workpiece and the cutting process requirements, a path planning method combining genetic algorithms and neural networks is used to plan the cutting path. In the genetic algorithm, the cutting path is encoded as chromosomes, and the fitness value of each chromosome is calculated. The selection operation adopts the roulette wheel selection method, so that the probability of each chromosome being selected is proportional to its fitness value. Partial matching crossover is used to randomly select partial gene segments of two chromosomes for exchange and to handle gene conflict problems. The neural network is used to predict the optimal cutting path and parameters under different conditions by learning the complex relationship between the workpiece shape, thickness, material, and cutting equipment performance and the optimal cutting parameters. The fitness value is expressed as: ， In the formula, L is the cutting path length, T is the cutting time, and Q is the cutting quality evaluation value. w1, w2, and w3 are weighting coefficients, which can be adjusted according to actual needs.

2. The laser adaptive cutting method for heavy-duty irregularly shaped variable thickness steel pipes according to claim 1, characterized in that: When acquiring surface images of a workpiece, the spectrum, intensity, and angle of the light source are dynamically adjusted to acquire surface images of workpieces with different materials, colors, and surface roughness. In this process, a multi-band light source combination is used to enhance the contrast of texture features and obtain the material texture features.

3. The laser adaptive cutting method for heavy-duty irregularly shaped variable thickness steel pipes according to claim 2, characterized in that: When acquiring surface images, the image acquisition frame rate is set according to the cutting speed and accuracy requirements.

4. The laser adaptive cutting method for heavy-duty irregularly shaped variable thickness steel pipes according to claim 3, characterized in that: When acquiring the thickness distribution information of a workpiece, a pattern is projected onto the workpiece surface to obtain the deformation pattern of the workpiece at different angles. Using the principle of triangulation, the geometric relationship between the acquisition point of the deformation pattern and the projection point of the pattern, as well as the degree of pattern deformation, is calculated to obtain the three-dimensional coordinates of each point on the workpiece surface, thereby generating the thickness distribution information of the workpiece.

5. The laser adaptive cutting method for heavy-duty irregularly shaped variable thickness steel pipes according to claim 4, characterized in that: When acquiring thickness data at different locations of the workpiece, based on the thickness distribution information, laser-excited ultrasonic waves propagate inside the workpiece, and the thickness at different locations of the workpiece is measured by receiving and analyzing the ultrasonic echo signals.

6. The laser adaptive cutting method for heavy-duty irregularly shaped variable thickness steel pipes according to claim 5, characterized in that: When obtaining the optimal cutting path, based on the geometry, surface defects, material texture features, and thickness data, a digital twin model of the cutting process is established to pre-simulate and optimize the cutting path, with the goal of ensuring cutting efficiency and accuracy, to obtain the optimal cutting path.

7. The laser adaptive cutting method for heavy-duty irregularly shaped variable thickness steel pipes according to claim 6, characterized in that: When performing laser cutting tasks, the laser power and cutting speed are automatically adjusted using a fuzzy control algorithm based on the real-time thickness, material properties, and cutting process requirements of the workpiece. The fuzzy control algorithm is used to establish a fuzzy control rule base based on the real-time thickness, material properties, and preset cutting process rules of the workpiece; to perform inference in the fuzzy control rule base based on the fuzzified input to obtain the fuzzy control output; and to convert the fuzzy output into a control quantity through defuzzification processing.

8. A heavy-duty irregular-shaped variable-thickness steel pipe laser adaptive cutting system, used to implement the heavy-duty irregular-shaped variable-thickness steel pipe laser adaptive cutting method as described in claim 1, characterized in that, include: The data acquisition and analysis module is used to identify the geometric shape, surface defects and material texture features of the workpiece based on the acquired surface image of the workpiece, and to obtain the thickness distribution information of the workpiece. A thickness detection module is used to acquire thickness data at different locations of the workpiece based on the thickness distribution information. The path planning module is used to generate a globally optimal cutting path based on the geometry, surface defects, material texture features, and thickness data using an intelligent algorithm. The cutting task execution module is used to execute laser cutting tasks based on the optimal cutting path, and automatically adjust the laser power, pulse frequency and cutting speed according to the thickness change; The vibration compensation module is used to compensate for vibration by reverse excitation or dynamic damping adjustment when vibration is detected. The quality assessment module is used to evaluate the cutting quality by acquiring cutting temperature, cutting force, and smoke concentration during laser cutting tasks. The fault diagnosis module is used to quickly locate the cause of a fault after a fault is detected in the equipment by using diagnostic methods based on fault tree analysis (FTA) and neural networks.

Images