Rolling method for improving grain size of large-specification gear steel

Abstract

The invention discloses a rolling method for improving the grain size of large-specification gear steel. The rolling method comprises the steps that firstly, a steel billet is fed into a heating furnace; secondly, the heated steel is conveyed to a subsequent machining station from the heating furnace through a furnace discharging roller way; thirdly, the heated steel billet is rolled through a rolling mill; fourthly, after rolling is completed, cooling treatment is conducted through a multi-section closed type water pipe independent cooling system; 5, after the steel cooling procedure is completed, a linear array camera and an area array camera are installed above the roller way, and a multi-view visual inspection system is constructed in cooperation with a multi-angle annular light source and a linear laser scanning device; 6, dynamically adjusting a control strategy by adopting a reinforcement learning algorithm; the method has the beneficial effects that based on an analysis algorithm, temperature data collected by the thermal imager are analyzed, a temperature abnormal area and a potential stress concentration point are identified, a temperature stress mathematical model is established, and heating and rolling processes are adjusted in time.

Description

Technical Field

[0001] The invention relates to the field of gear rolling, and in particular to a rolling method for improving the grain size of large-size gear steel. Background Art

[0002] In the rolling production of large-gauge gear steel (75-80mm), with the high-end equipment manufacturing industry's continuously increasing requirements for gear material performance, traditional rolling technology faces severe challenges. Existing processes suffer from multiple technical bottlenecks, directly restricting improvements in product quality and production efficiency. Due to the large rolling gauge and large cross-sectional dimensions of the steel, significant heat loss occurs during the rolling process. As a result, the controlled rolling temperature of the steel entering the final stand rolling mill can only reach 920°C, far below the 960°C required to ensure grain size. This can easily cause mixed crystals in the rolled material, seriously affecting the material's mechanical properties and service life. Large-gauge steel suffers from severe temperature losses during roller conveying, rolling deformation, and cooling. Existing processes struggle to effectively control the temperature field throughout the entire production process, resulting in uneven temperatures across the steel, increasing the difficulty of process control and the risk of product quality fluctuations. The lack of technology to identify abnormal temperature areas and potential stress concentration points in the steel being processed prevents timely detection and resolution of problems, hindering further improvement in product quality. Summary of the Invention

[0003] The purpose of the present invention is to solve the above-mentioned problems and therefore propose a rolling method for increasing the grain size of large-sized gear steel.

[0004] The object of the present invention can be achieved by the following technical solution: A rolling method for increasing the grain size of large-sized gear steel, comprising:

[0005] Step 1: The billet is fed into the heating furnace, heated according to the temperature rise curve, and discharged from the furnace when the set tapping conditions are met;

[0006] Step 2: The heated steel is transported from the heating furnace to the subsequent processing station by the furnace roller;

[0007] Step 3: Install infrared thermal imagers at the entrance and exit of the rolling mill to monitor the surface temperature of the steel in real time, identify abnormal temperature areas and potential stress concentration points, and then roll the heated steel billet through the rolling mill to form a gear-shaped billet.

[0008] Step 4: After rolling is completed, cooling is carried out through a multi-section closed water pipe independent cooling system;

[0009] Step 5: After the steel cooling process is completed, a linear array camera and an area array camera are installed above the roller. Together with a multi-angle ring light source and a line laser scanning device, a multi-view visual inspection system is constructed. In addition to visual inspection, array eddy current sensors and phased array ultrasonic probes are deployed to inspect the surface quality of the rolled steel.

[0010] Step 6: Based on the surface quality inspection results and cooling parameter optimization historical data, the control strategy is dynamically adjusted using the reinforcement learning algorithm.

[0011] Furthermore, the heating curve is as follows: a heating rate of 5°C / min from room temperature to 800°C, a heating rate of 3°C / min from 800-1230°C, and a soaking period maintained at 1230°C for 140 minutes.

[0012] Furthermore, the tapping conditions are: the soaking period reaches 140 minutes and the tapping temperature is within the range of 1220-1230°C.

[0013] Furthermore, the method of identifying the temperature abnormality area and the potential stress concentration point is as follows:

[0014] Data preprocessing: Filter and denoise the raw temperature image data collected by the thermal imager to remove abnormal data points caused by environmental interference or equipment errors. At the same time, grayscale calibration is performed on the image to ensure an accurate mapping relationship between temperature and grayscale values.

[0015] Temperature feature extraction: Using a threshold segmentation algorithm, we set a threshold based on the normal temperature range of the gear steel rolling process, segmenting the temperature image into different regions. This allows us to quickly identify abnormal temperature areas above or below the normal range. Using an edge detection algorithm, we extract boundaries within the temperature image where the temperature gradient changes significantly. This means areas with significant temperature differences are formed where the temperature difference between adjacent pixels in the temperature image exceeds the set threshold.

[0016] Stress concentration point identification: Based on the coupling principle of thermodynamics and material mechanics, a temperature stress mathematical model is established. Using the finite element analysis method, temperature data is used as input conditions to simulate the stress distribution inside the steel. Combined with the machine learning algorithm, a stress concentration point identification model is constructed by training temperature data samples of known stress concentration points. This model can identify potential stress concentration points based on the temperature distribution characteristics.

[0017] Furthermore, the temperature stress mathematical model is established as follows:

[0018] The temperature field distribution of gear steel during rolling is described by the Fourier heat conduction equation, that is, ,in Represents the heat conduction term, which reflects the heat conduction phenomenon caused by the temperature gradient inside the material. is the thermal conductivity of the material, is the temperature gradient, is the divergence operator, represents the internal heat source term, that is, the rate at which the material generates heat itself, is the density of the material; is the constant pressure specific heat capacity of the material, Indicates temperature Over time This equation fully reflects the relationship between heat flow, internal heat source, material thermal physical parameters and temperature changes over time during heat conduction;

[0019] Combined with the equilibrium equation in elasticity ,in, is the stress tensor, is the volume force, combined with the geometric equation , is the strain tensor, For the displacement vector, a basic equation system for multi-physics field coupling is constructed;

[0020] Introducing the coefficient of thermal expansion , through the thermoelastic constitutive equation Relate temperature changes to stress and strain, where is the elastic stiffness matrix, is the unit tensor, is the temperature variation, realizing the bidirectional coupling between temperature field and stress field.

[0021] Furthermore, each section of the multi-section closed water pipe independent cooling system is equipped with an independent water flow and pressure regulating device, which can adjust the cooling intensity in real time according to the identification results of temperature abnormality areas and potential stress concentration points.

[0022] Furthermore, the infrared thermal imager at the entrance is used to monitor the initial temperature state of the steel entering the rolling mill, and the infrared thermal imager at the exit is used to monitor the temperature change of the steel after rolling and deformation.

[0023] Furthermore, the reinforcement learning algorithm dynamically adjusts the control strategy as follows: if the same type of surface defects appear continuously, the system automatically lowers the temperature threshold of the corresponding cooling section and starts enhanced cooling in advance.

[0024] Furthermore, the speed of the furnace-discharging roller is 1.2 m / s.

[0025] Furthermore, the reinforcement learning algorithm dynamically adjusts the control strategy and also includes adaptively adjusting the collaborative working mode of the multi-segment cooling system.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] High-precision infrared thermal imagers are installed at the entrance and exit of the blooming mill. Based on analytical algorithms, they analyze the temperature data collected by the thermal imagers, identify temperature anomalies and potential stress concentration points, and establish a temperature-stress mathematical model. This allows for real-time monitoring of steel temperature conditions and prompt adjustments to heating and rolling processes. Through intelligent algorithms and model analysis, temperature anomalies and stress concentration issues can be detected in advance, preventing unqualified grain size and quality defects caused by temperature and stress issues.

[0028] Array eddy current sensors and phased array ultrasonic probes are deployed to detect defects. Mobile Rockwell and Brinell hardness testers are installed at the end of the production line for hardness testing. Eddy current sensors and ultrasonic probes can detect surface, near-surface, and internal defects in steel, respectively. Hardness testing determines whether the steel's microstructure and performance meet standards. This multi-faceted approach ensures product quality and prevents defects from affecting the grain size and performance of gear steel.

[0029] Dynamically adjust cooling parameters based on test results, and dynamically adjust control strategies based on reinforcement learning algorithms, such as adjusting temperature thresholds and cooling modes. Accurately adjust the cooling process for different quality issues to avoid residual stress concentration and surface defects caused by uneven cooling, optimize cooling uniformity, and ensure stable grain size of large-size gear steel. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0031] Figure 1 The present invention is a flow chart of a rolling method for increasing the grain size of large-size gear steel. DETAILED DESCRIPTION

[0032] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0033] See also Figure 1 As shown, a rolling method for increasing the grain size of large-size gear steel comprises:

[0034] Step 1: The billet is fed into the heating furnace, heated according to the temperature rise curve, and discharged from the furnace when the set tapping conditions are met;

[0035] The heating furnace heating curve is as follows: the heating rate from room temperature to 800℃ is 5℃ / min, the heating rate from 800-1230℃ is 3℃ / min, and the soaking period is maintained at 1230℃ for 140min.

[0036] The tapping conditions are as follows: when the soaking period reaches 140 minutes and the tapping temperature is within the range of 1220-1230℃, the tapping conditions are met. At the same time, all water tanks and roller cooling water must be closed 10 minutes before tapping. This can promote the full diffusion of elements in the steel, improve the uniformity of the internal structure of the steel, and lay the foundation for increasing the grain size in subsequent rolling. Turning off the cooling water can reduce temperature loss during tapping and ensure that the steel enters the rolling process at the appropriate temperature.

[0037] Step 2: The heated steel is transported from the heating furnace to the subsequent processing station by the furnace roller;

[0038] The speed of the furnace roller was changed from 0.8m / s to 1.2m / s, the conveying time was shortened to 45 seconds, and the surface temperature loss was ≤30℃;

[0039] Step 3: Install infrared thermal imagers at the entrance and exit of the rolling mill to monitor the surface temperature of the steel in real time, identify abnormal temperature areas and potential stress concentration points, and then roll the heated steel billet through the rolling mill to form a gear-shaped billet.

[0040] The infrared thermal imager at the entrance is used to monitor the initial temperature of the steel entering the rolling mill. It is used to determine whether the steel has reached the starting rolling temperature based on the initial temperature. If the temperature does not meet the standard, the personnel can adjust the heating process in time to avoid excessive rolling force due to low temperature that may damage the equipment, or excessive temperature that may affect the steel's microstructure and properties. The infrared thermal imager at the exit is used to monitor the temperature changes of the steel after rolling and deformation. It is used to evaluate the temperature uniformity and temperature drop, providing a basis for adjusting the subsequent cooling process parameters, ensuring that the steel enters the next process within the appropriate temperature range, thereby ensuring the stability and quality of the gear steel's fine grain size.

[0041] Identify areas of temperature anomalies and potential stress concentration points as follows:

[0042] Data preprocessing: Filter and denoise the raw temperature image data collected by the thermal imager to remove abnormal data points caused by environmental interference or equipment errors. At the same time, grayscale calibration is performed on the image to ensure an accurate mapping relationship between temperature and grayscale values.

[0043] Temperature feature extraction: Using a threshold segmentation algorithm, we set a threshold based on the normal temperature range of the gear steel rolling process, segmenting the temperature image into different regions. This allows us to quickly identify abnormal temperature areas above or below the normal range. Using an edge detection algorithm, we extract boundaries in the temperature image where the temperature gradient changes significantly. This means that in the temperature image, areas where the temperature difference between adjacent pixels exceeds the set threshold form significant temperature drop regions. These boundaries often correspond to the edges of abnormal temperature regions.

[0044] Stress Concentration Point Identification: Based on the coupling principles of thermodynamics and material mechanics, a temperature stress mathematical model is established. Using finite element analysis, temperature data is used as input to simulate the stress distribution within the steel. Combined with a machine learning algorithm, a stress concentration point identification model is constructed by training on a large number of temperature data samples of known stress concentration points. This model can identify potential stress concentration points based on temperature distribution characteristics, such as areas of sudden temperature changes and areas of abnormal temperature gradients. These areas are more prone to stress concentration due to uneven deformation during rolling.

[0045] The mathematical model of temperature stress is established as follows:

[0046] The basic equation is determined and the Fourier heat conduction equation is used to describe the temperature field distribution of gear steel during the rolling process, that is, ,in Represents the heat conduction term, which reflects the heat conduction phenomenon caused by the temperature gradient inside the material. is the thermal conductivity of the material, is the temperature gradient, is the divergence operator, represents the internal heat source term, that is, the rate at which heat is generated within the material itself, such as the thermal effect caused by plastic deformation during rolling. is the density of the material; is the constant pressure specific heat capacity of the material, Indicates temperature Over time This equation fully reflects the relationship between heat flow, internal heat source, material thermal physical parameters and temperature changes over time during heat conduction;

[0047] Combined with the equilibrium equation in elasticity ( is the stress tensor, is the body force) and the geometric equations ( is the strain tensor, is the displacement vector), building a basic equation system for multi-physics field coupling;

[0048] Introducing the coefficient of thermal expansion , through the thermoelastic constitutive equation Relate temperature changes to stress and strain, where is the elastic stiffness matrix, is the unit tensor, is the temperature variation, realizing the bidirectional coupling between temperature field and stress field;

[0049] In practical application, the Fourier heat conduction equation is used to calculate the temperature field distribution of gear steel during the rolling process, and the temperature T and temperature change at each time and position are obtained. , then according to the displacement through the geometric equation Calculate strain , then and Substitute into the thermoelastic constitutive equation and combine with the elastic stiffness matrix Calculate stress , and finally the stress Substitute into the equilibrium equation and check whether it satisfies Through repeated iterative calculations, the bidirectional coupling of temperature and stress fields is achieved to accurately simulate the changes in temperature and stress during the rolling process of large-sized gear steel, providing a theoretical basis for rolling methods to improve grain size.

[0050] Step 4: After rolling is completed, cooling is carried out through a multi-section closed water pipe independent cooling system;

[0051] Each section is equipped with independent water flow and pressure regulating devices, which can adjust the cooling intensity in real time according to the identification results of temperature anomaly areas and stress concentration points;

[0052] Specifically, based on the identification results of temperature anomaly areas and stress concentration points, cooling intensity adjustment rules are set. If image analysis shows that the temperature in a certain area is higher than the target temperature range, the system automatically increases the water flow in the corresponding cooling section by 5-8m³ / h for every 1°C increase, thereby improving the cooling rate.

[0053] If the temperature is lower than the target temperature range, the system reduces the water flow rate by 3-5 m³ / h for every 1°C decrease to avoid cracks in the steel caused by overcooling. For areas with abnormal temperature gradients or stress concentrations, the cooling intensity of this area and its adjacent cooling sections is enhanced to make the cooling distribution more in line with the actual needs of the steel. For example, when a temperature anomaly is detected at the edge of the steel, the system automatically increases the water flow in the edge section and its two adjacent sections, and adjusts the water spray angle so that the cooling water evenly covers the temperature anomaly area. The water spray angle of each cooling section can be electrically adjusted within the range of 0-90° in 1° steps to achieve precise cooling distribution control. In addition, by establishing a cooling intensity-temperature-time relationship database and combining it with real-time temperature data, the working sequence of each cooling section is dynamically optimized to achieve coordinated adjustment of cooling intensity and distribution, ensuring the stability and quality of the grain size of large-size gear steel.

[0054] Step 5: After the steel cooling process is completed, a linear array camera and an area array camera are installed above the roller. Together with a multi-angle ring light source and a line laser scanning device, a multi-view visual inspection system is constructed. An image acquisition card is used to acquire real-time images of the steel surface. An edge detection algorithm is used to identify the contours of surface cracks and folds. Threshold segmentation and morphological processing are combined to accurately extract defect areas. At the same time, structured light 3D reconstruction technology is used to calculate the flatness and roughness of the steel surface. A flatness error threshold of ±0.1 mm and a roughness Ra upper limit of 1.6 μm are set as quality judgment criteria.

[0055] When visual inspection reveals areas of thickened iron oxide scale caused by local overheating on the steel surface, it indicates that the previous cooling process was insufficient in cooling the area, and secondary cooling treatment is performed. The control system automatically increases the water flow in the corresponding cooling section of the area based on the defect area and severity, and increases the water pump pressure by 0.05-0.1MPa and extends the cooling time by 5-10s according to the rule of increasing the water flow by 2-3m³ / h for every 10cm² defect area. If ultrasonic testing finds areas of residual stress concentration caused by uneven cooling, the system immediately reduces the water flow in the adjacent cooling section by 3-5m³ / h, decreases the water spray angle by 5-10°, and adjusts the cooling sequence to make the area enter the secondary slow cooling stage to relieve stress concentration.

[0056] Based on visual inspection, array eddy current sensors and phased array ultrasonic probes are deployed. Eddy current sensors can detect tiny cracks and material unevenness on the surface and near the surface (depth 0-5mm) of steel. By detecting changes in coil impedance and combining it with a neural network algorithm, they can identify the type and size of defects.

[0057] Phased array ultrasonic probes are used to detect internal holes (5-50mm deep) and inclusion defects. Wavelet transform and pattern recognition techniques are used to locate and quantitatively analyze defects using the time and amplitude characteristics of ultrasonic echo signals. Mobile Rockwell and Brinell hardness testers are deployed at the end of the production line. Industrial robots automatically clamp steel samples for multi-point hardness testing (at least three test points per meter). The measured hardness values ​​are compared with the 28-32HRC range required by process standards to determine whether the steel's microstructure and performance meet the standards.

[0058] Step 6: Based on the surface quality test results and cooling parameter optimization historical data, a reinforcement learning algorithm is used to dynamically adjust the control strategy. If the same type of surface defects (such as cracks) appear continuously, the system automatically reduces the temperature threshold of the corresponding cooling section by 5-10°C and starts enhanced cooling in advance. At the same time, based on the fluctuations in microstructure and performance feedback from hardness testing, the collaborative working mode of the multi-section cooling system is adaptively adjusted, such as switching from "sequential cooling" to "staggered cooling", to optimize cooling uniformity and ensure the stability of the grain size of large-size gear steel.

[0059] The grain size of the products produced under the above process was tested. A Φ75mm gear steel sample was taken after rolling, etched with a 4% nitric acid alcohol solution, and observed under a 100x optical microscope. The austenite grain size reached level 7.5, meeting the requirements of GB / T6394-2017, with no mixed crystal phenomenon.

[0060] Mechanical performance test: All indicators are better than the industry standards, the comparison table is as follows:

[0061]

[0062] The present invention solves the problem of mixed crystals caused by insufficient rolling temperature control during the rolling process of gear steel by optimizing the heating process, increasing the speed of the furnace roller, and modifying the water pipe cooling method. At the same time, the introduction of an intelligent temperature control system solves the problem of small cracks easily appearing on the steel surface during high-speed rolling, thereby improving product quality and production efficiency.

[0063] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A rolling method for increasing the grain size of large-size gear steel, characterized in that: include: Step 1: The billet is fed into the heating furnace, heated according to the temperature rise curve, and discharged from the furnace when the set tapping conditions are met; Step 2: The heated steel is transported from the heating furnace to the subsequent processing station by the furnace roller; Step 3: Install infrared thermal imagers at the entrance and exit of the rolling mill to monitor the surface temperature of the steel in real time, identify abnormal temperature areas and potential stress concentration points, and then roll the heated steel billet through the rolling mill to form a gear-shaped billet. Step 4: After rolling is completed, cooling is carried out through a multi-section closed water pipe independent cooling system; Step 5: After the steel cooling process is completed, a linear array camera and an area array camera are installed above the roller. Together with a multi-angle ring light source and a line laser scanning device, a multi-view visual inspection system is constructed. In addition to visual inspection, array eddy current sensors and phased array ultrasonic probes are deployed to inspect the surface quality of the rolled steel. Step 6: Based on the surface quality inspection results and cooling parameter optimization historical data, the reinforcement learning algorithm is used to dynamically adjust the control strategy.

2. A rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: The heating curve is as follows: a heating rate of 5°C / min from room temperature to 800°C, a heating rate of 3°C / min from 800 to 1230°C, and a soaking period of 1230°C for 140 minutes.

3. The rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: The tapping conditions are: the soaking period reaches 140 minutes and the tapping temperature is within the range of 1220-1230°C.

4. The rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: The method for identifying temperature anomaly areas and potential stress concentration points is as follows: Data preprocessing: Filter and denoise the raw temperature image data collected by the thermal imager to remove abnormal data points caused by environmental interference or equipment errors. At the same time, grayscale calibration is performed on the image to ensure an accurate mapping relationship between temperature and grayscale values. Temperature feature extraction: Using a threshold segmentation algorithm, we set a threshold based on the normal temperature range of the gear steel rolling process, segmenting the temperature image into different regions. This allows us to quickly identify abnormal temperature areas above or below the normal range. Using an edge detection algorithm, we extract boundaries within the temperature image where the temperature gradient changes significantly. This means areas with significant temperature differences are formed where the temperature difference between adjacent pixels in the temperature image exceeds the set threshold. Stress concentration point identification: Based on the coupling principle of thermodynamics and material mechanics, a temperature stress mathematical model is established. Using the finite element analysis method, temperature data is used as input conditions to simulate the stress distribution inside the steel. Combined with the machine learning algorithm, a stress concentration point identification model is constructed by training temperature data samples of known stress concentration points. This model can identify potential stress concentration points based on the temperature distribution characteristics.

5. A rolling method for increasing the grain size of large-sized gear steel according to claim 4, characterized in that: The mathematical model of temperature stress is established as follows: The temperature field distribution of gear steel during rolling is described by the Fourier heat conduction equation, that is, ,in Represents the heat conduction term, which reflects the heat conduction phenomenon caused by the temperature gradient inside the material. is the thermal conductivity of the material, is the temperature gradient, is the divergence operator, represents the internal heat source term, that is, the rate at which the material generates heat itself, is the density of the material; is the constant pressure specific heat capacity of the material, Indicates temperature Over time This equation fully reflects the relationship between heat flow, internal heat source, material thermal physical parameters and temperature changes over time during heat conduction; Combined with the equilibrium equation in elasticity ,in, is the stress tensor, is the volume force, combined with the geometric equation , is the strain tensor, For the displacement vector, a basic equation system for multi-physics field coupling is constructed; Introducing the coefficient of thermal expansion , through the thermoelastic constitutive equation Relate temperature changes to stress and strain, where is the elastic stiffness matrix, is the unit tensor, is the temperature variation, realizing the bidirectional coupling between temperature field and stress field.

6. The rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: Each section of the multi-section closed water pipe independent cooling system is equipped with an independent water flow and pressure regulating device, which can adjust the cooling intensity in real time according to the identification results of temperature abnormality areas and potential stress concentration points.

7. The rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: The infrared thermal imager at the entrance is used to monitor the initial temperature state of the steel entering the rolling mill, and the infrared thermal imager at the exit is used to monitor the temperature change of the steel after rolling and deformation.

8. The rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: The reinforcement learning algorithm dynamically adjusts the control strategy as follows: if the same type of surface defects appear continuously, the system automatically lowers the temperature threshold of the corresponding cooling section and starts enhanced cooling in advance.

9. The rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: The speed of the furnace roller is 1.2 m / s.

10. The rolling method for increasing the grain size of large-sized gear steel according to claim 1, characterized in that: The reinforcement learning algorithm dynamically adjusts the control strategy and also includes adaptively adjusting the collaborative working mode of the multi-segment cooling system.

Images