Intelligent detection method and system for detecting tipping angle of hot-metal bottle

Abstract

The invention discloses an intelligent detection method and system for detecting the tipping angle of a hot-metal bottle. The invention relates to the technical field of metallurgical engineering. The laser radar sensor is installed on the upper portion of the moving path of the molten iron tank and measures the distance between the laser radar sensor and a lower object in real time. Collecting height data in a period of time, wherein the height data comprises height data of a molten iron surface front edge A, a molten iron surface B and a molten iron rear edge C; calibrating the laser radar sensor, namely adjusting a scanning angle and setting scanning frequency and resolution parameters so as to ensure that the acquired data is accurate; by accurately measuring the height of the molten iron, dynamically judging the overflow critical position and combining real-time monitoring of the infrared camera, the risk of molten iron overflow can be found and warned in time, production safety accidents caused by molten iron overflow are effectively avoided, and the safety level of an operation site is greatly improved. Due to automatic tipping angle calculation and slagging-off track planning, the time for manual intervention and judgment is shortened, and slagging-off operation is more efficient and accurate.

Description

Technical Field

[0001] The invention relates to the technical field of metallurgical engineering, in particular to the tipping operation of a molten iron tank, and in particular to an intelligent detection method and system for detecting the tipping angle of a molten iron tank. Background Art

[0002] In the steel smelting process, molten iron tanks are used to hold and transport high-temperature molten iron. Tilting operation is a key link, especially during slag removal operation, the molten iron tank needs to be tilted to a certain angle so that the slag on the surface of the molten iron can be removed smoothly. This operation requirement not only requires precise control of the tilting angle, but also requires ensuring that the molten iron does not overflow during the tilting process, thereby avoiding production accidents and waste of resources. In order to meet this operation requirement, it is necessary to accurately measure and dynamically adjust the tilting angle of the molten iron tank. This requires the system to be able to obtain the height information of the molten iron in the molten iron tank in real time, and calculate the appropriate tilting angle based on the height information.

[0003] In the past, the determination of the tipping angle of the molten iron ladle mainly relied on manual operation or simple sensor detection. However, these traditional solutions have obvious defects and cannot meet the requirements of modern steelmaking processes for precise control and safety. Manual determination of the tipping angle often relies on the operator's experience and judgment, which leads to strong subjectivity in the determination results and makes it difficult to ensure accuracy.

[0004] Traditional sensor detection solutions can only provide simple location or distance information, and cannot accurately measure and dynamically adjust the height of molten iron. At the same time, simple sensor detection solutions often lack the ability to monitor and warn of the risk of molten iron overflow in real time, and cannot promptly detect and deal with potential safety hazards.

[0005] Therefore, an intelligent detection method and system for detecting the tipping angle of a molten iron ladle are proposed. Summary of the invention

[0006] In view of this, the embodiments of the present invention hope to provide an intelligent detection method and system for detecting the tilting angle of a molten iron tank, so as to solve or alleviate the technical problems existing in the prior art, namely, how to improve the effect of detecting the tilting angle of a molten iron tank, and provide a critical position determination mechanism for molten iron overflow, and at least provide a beneficial option for this;

[0007] The technical solution of the embodiment of the present invention is achieved as follows:

[0008] First, the intelligent detection method for the tilting angle of the molten iron tank:

[0009] 1. Overview:

[0010] The present invention aims to improve the accuracy and safety of the detection of the tipping angle of a molten iron tank. The height data of the molten iron tank during its movement is collected in real time by a laser radar sensor, including data of the front edge, the surface and the rear edge of the molten iron surface. Then, the collected data is low-pass filtered to obtain the accurate height of the molten iron. According to the height of the molten iron, the tipping angle of the molten iron tank is determined by a preset data table, and the critical judgment position of the molten iron overflow is obtained. At the same time, an infrared camera is combined to monitor in real time whether the molten iron area exceeds the critical overflow position to prevent the molten iron from overflowing. In addition, the slag removal trajectory is planned according to the molten iron height and the tipping angle, and the key point attributes in the trajectory are set. During the slag removal operation, the slag removal planning trajectory and the operation trajectory are displayed in real time through a 3D model to achieve visual monitoring and safety measures in abnormal situations.

[0011] (II) Technical solution:

[0012] 2.1 Step S1, LiDAR data collection:

[0013] The lidar sensor is installed on the upper part of the molten iron ladle's travel path to measure the distance to the lower objects in real time; it collects height data over a period of time, including the height data of the front edge A of the molten iron surface, the molten iron surface B, and the rear edge C of the molten iron.

[0014] 2.1.1 Step S100, sensor installation and calibration:

[0015] Calibrate the LiDAR sensor, including adjusting the scanning angle, setting the scanning frequency and resolution parameters, to ensure the collected data is accurate.

[0016] 2.1.2 Step S101, real-time distance measurement:

[0017] When the LiDAR sensor is working, it emits laser downward in real time and receives the reflected signal to measure the distance between the molten iron tank and the molten iron. The distance data of each measurement point is recorded with a timestamp.

[0018] 2.1.3 Step S102, data preprocessing:

[0019] Remove noise from the original distance data, and then use moving average filtering or low-pass filtering to reduce data fluctuations and errors.

[0020] 2.1.4 Step S103, height data extraction:

[0021] Based on the preprocessed data D, the Halcon algorithm, SIFT algorithm, SURF algorithm or generalized Hough transform algorithm are used to identify the feature points of the molten iron surface, and their vertical distances relative to the lidar sensor are calculated to extract the height data of the molten iron surface front A, molten iron surface B and molten iron rear edge C.

[0022] 2.1.5 Step S104, data storage and transmission:

[0023] The extracted height data is stored in a local or remote database for subsequent data analysis and processing; if necessary, the height data is transmitted in real time to a data processing and control system or other related systems for further use or display.

[0024] 2.2 Step S2, calculation of molten iron height:

[0025] The collected height data is analyzed to identify the characteristics of the front edge A, the molten iron surface B and the rear edge C of the molten iron surface. The data in the middle area of ​​the molten iron surface is low-pass filtered to improve the data accuracy; the height of the molten iron is calculated based on the filtered data.

[0026] 2.2.1 Step S200, height data feature recognition:

[0027] The collected height data is analyzed in detail, and the respective characteristics of the front edge A of the molten iron surface, the molten iron surface B and the rear edge C of the molten iron are identified using a peak detection algorithm or an edge recognition algorithm.

[0028] 2.2.2 Step S201, data filtering and smoothing:

[0029] For the height data of the middle area of ​​the molten iron surface, a low-pass filter is applied for smoothing. The low-pass filter can remove high-frequency noise and fluctuations in the data and retain the true height information of the molten iron surface.

[0030] 2.2.3 Step S202, outlier detection and processing:

[0031] In the filtered data, outlier detection of measurement errors is performed; for the detected outliers, they are replaced with the average value or interpolation of adjacent data.

[0032] 2.2.4 Step S203, calculation of molten iron height:

[0033] Based on the filtered and processed height data, the heights of the front edge A of the molten iron surface and the rear edge C of the molten iron are averaged to obtain the height of the molten iron.

[0034] 2.2.5 Step S204, data verification and checking:

[0035] Verify and check the calculated iron height, including comparison with expected values ​​or historical data, or independent verification through other measurement methods;

[0036] If any deviation or abnormality is found in the data, return to the previous steps in time to make corrections and adjustments to ensure that the final molten iron height data is accurate and reliable.

[0037] 2.3 Step S3, determination of tipping angle and overflow critical position:

[0038] According to the height of the molten iron, the tipping angle of the molten iron tank is determined through a preset data table. At the same time, the critical judgment position of the molten iron overflow is obtained according to the tipping angle. The real-time image taken by the infrared camera is read to analyze whether the molten iron area exceeds the critical judgment position of the overflow.

[0039] 2.3.1 Step S300, determining the tilting angle:

[0040] The filtered molten iron height data obtained in step S2 is used as the basis for calculating the tilting angle.

[0041] Based on a preset data table (recording the correspondence between different molten iron heights and the tilting angles of the molten iron tank), the tilting angle corresponding to the current molten iron height is matched through traversal search or interpolation method; based on the matching result, the current tilting angle of the molten iron tank is read out.

[0042] 2.3.2 Step S301, overflow critical position determination

[0043] According to the tipping angle, combined with the geometric dimensions of the molten iron ladle and the critical conditions for molten iron overflow, the critical judgment position for molten iron overflow is calculated or looked up in a table; at the same time, the real-time image inside the molten iron ladle taken by the infrared camera is read, and the position and shape of the molten iron area are analyzed and identified using image processing technology; if the position of the molten iron area exceeds the critical judgment position for overflow, it is determined that there is a risk of molten iron overflow; otherwise, it is determined to be in a safe state.

[0044] 2.3.3 Step S302, comprehensive determination and response:

[0045] If the tipping angle reaches the preset limit or there is a risk of molten iron overflowing, the corresponding warning or control measures will be triggered; if the result of the judgment is an unsafe state, a warning signal will be immediately issued to notify the operator to pay attention to safety; at the same time, according to the preset control strategy, the tipping angle of the molten iron tank will be automatically adjusted or other emergency measures will be taken to prevent molten iron overflow or tipping accidents.

[0046] 2.4 Step S4, slag removal trajectory planning

[0047] Determine the coordinates of the key points when slagging according to the height of the molten iron and the tilting angle. Call the preset slagging trajectory data table and generate a suitable slagging trajectory based on the current situation. Set the speed, type, position control accuracy of the key points in the trajectory and whether the Z coordinate is automatically adjusted.

[0048] 2.4.1 Step S400, determining key point coordinates:

[0049] According to the height and tilting angle of the molten iron and the process requirements of the slag removal operation, the coordinates of the key points that need to be reached when slag removal are calculated, including the starting point, the ending point and the turning point of the slag removal process; based on the preset slag removal trajectory data table (which records the recommended slag removal trajectory data under different molten iron heights and tilting angles), according to the current molten iron height and tilting angle, the most matching trajectory data is searched in the preset slag removal trajectory data table; if a completely matching trajectory cannot be found, the similar trajectory data is interpolated and adjusted according to the current situation to automatically generate a slag removal trajectory suitable for the current situation.

[0050] 2.4.2 Step S401, trajectory smoothing and optimization:

[0051] The generated scraping trajectory is smoothed to remove unnecessary fluctuations and turning points to make the trajectory smoother; according to the requirements and actual conditions of the scraping operation, an average speed is set for each key point in the trajectory.

[0052] 2.4.3 Step S402, type setting:

[0053] Set the type for each key point, including the starting point, end point and turning point, so that the control system can correctly identify and execute the corresponding actions; according to the accuracy requirements of the slag removal operation, set the position control accuracy for each key point in the trajectory.

[0054] 2.4.4 Step S403, Z coordinate automatic adjustment property setting:

[0055] Set whether the Z coordinate of the key points in the trajectory is automatically adjusted; if automatic adjustment is required, the adjustment range and conditions should be set to ensure that the scraper can flexibly adjust the Z coordinate according to actual conditions during operation.

[0056] 2.5 Step S5, slag removal operation execution

[0057] Start the slag removal operation, and call the corresponding slag removal trajectory to perform the slag removal operation based on the visual analysis of the slag distribution on the slag surface; during the slag removal operation, if a collision occurs, handle it according to the preset collision handling strategy; when removing slag at the edge, apply the preset slag removal strategy.

[0058] 2.5.1 Step S500, trajectory calling and adjustment:

[0059] According to the slag distribution, call the corresponding slag removal trajectory to carry out the slag removal operation; if the slag distribution does not meet the expectations, adjust the slag removal trajectory to adapt to the actual situation;

[0060] 2.5.2 Step S501, collision processing:

[0061] During the scrapping operation, the operating status of the scraper is monitored in real time to detect whether a collision occurs. If a collision occurs, the movement of the scraper is stopped immediately and handled according to the preset collision handling strategy, including retreating, adjusting the trajectory and / or alarming.

[0062] 2.6 Step S6, real-time display and monitoring of 3D model

[0063] The 3D model can display the slag removal planning trajectory and operation trajectory in real time. If any abnormal situation is found, the slag removal operation will be stopped immediately and corresponding safety measures will be taken.

[0064] 2.6.1 Step S600, 3D model creation and loading:

[0065] According to the actual size and shape of the ladle, slag scraper and working environment, a 3D model is built and visualized and loaded into the monitoring system; including the internal structure of the ladle, the moving parts of the slag scraper and obstacles in the working environment.

[0066] 2.6.2 Step S601, real-time display of scraping trajectory:

[0067] In the 3D model, the planned trajectory of the scraper is displayed as a dotted line or in different colors. The planned trajectory includes the moving path of the scraper, the position of key points and speed information.

[0068] Update the actual running track of the scraper in real time, represented by solid lines or dynamic icons in the 3D model;

[0069] The operating trajectory should be compared with the planned trajectory so that the operator can intuitively understand the operating status of the scraper.

[0070] (III) Mechanism for solving technical problems:

[0071] 3.1 Improve the detection effect of the tilting angle of the molten iron tank:

[0072] A laser radar sensor is used to collect high-precision data on the upper part of the molten iron ladle's path. The laser radar sensor can measure the distance to the lower object in real time to ensure the accuracy and real-time nature of the data. The system intelligently analyzes the collected height data to identify the features of the front edge, the molten iron surface, and the rear edge of the molten iron surface. The data accuracy and stability are further improved by low-pass filtering the data in the middle area of ​​the molten iron surface. Based on the filtered molten iron height data, the system accurately calculates the tilting angle of the molten iron ladle through a preset data table or algorithm. This process avoids the subjectivity and errors of manual judgment and improves the accuracy of detection.

[0073] 3.2 Provide a critical position determination mechanism for molten iron overflow:

[0074] The present invention not only pays attention to the tipping angle of the molten iron tank, but also dynamically determines the critical position of molten iron overflow according to the tipping angle. This mechanism can quickly calculate the critical position where molten iron may overflow according to the real-time tipping angle, providing an important reference for subsequent slag removal operations. In order to further ensure the safety of molten iron, the present invention also introduces an infrared camera for real-time monitoring. The infrared camera can capture real-time images inside the molten iron tank, and use image analysis technology to determine whether the molten iron area exceeds the critical position of overflow. Once the risk of molten iron overflow is detected, the system will immediately issue an alarm and stop the tipping operation. The system combines the data of the lidar sensor and the infrared camera for comprehensive judgment. When it is detected that the height of the molten iron is close to or exceeds the critical position of overflow, the system will automatically trigger the early warning mechanism to remind the operator to take timely measures to avoid the occurrence of molten iron overflow accidents.

[0075] Secondly, the intelligent detection system for the tilting angle of the molten iron tank:

[0076] The system is the hardware carrier of the above intelligent detection method, including:

[0077] LiDAR sensor that measures the distance between the molten iron tank and the molten iron in real time: installed on the upper part of the molten iron tank's path. By collecting height data changes over a period of time, the system can accurately identify the leading edge, middle area and trailing edge of the molten iron surface. LiDAR sensors have the characteristics of high precision, high reliability and strong real-time performance. They can work stably in complex industrial environments to ensure the accuracy and timeliness of data collection.

[0078] Infrared camera for real-time monitoring of the molten iron area in the molten iron tank: By taking real-time images of the molten iron tank and combining image analysis technology, the system can determine whether the molten iron area exceeds the preset overflow critical position. The infrared camera has night vision and high-temperature object recognition capabilities, and can work normally in low-light or high-temperature environments, providing clear images of the molten iron area, providing an important basis for system decision-making.

[0079] It also includes a processor connected to the laser radar sensor and the infrared camera, and a register coupled to the processor, wherein the register stores program instructions, and when the program instructions are executed by the processor, the processor executes the intelligent detection method as described above, wherein the processor receives the data transmitted by the laser radar sensor and the infrared camera, and performs intelligent analysis and processing. The system can automatically calculate the tipping angle of the molten iron ladle according to the data changes, and dynamically determine the critical position of the molten iron overflow. At the same time, the system can also automatically adjust the slag removal trajectory and operating parameters according to the analysis results to ensure the smooth progress of the slag removal operation.

[0080] Compared with the prior art, the present invention has the following beneficial effects:

[0081] 1. Significantly improve safety: By accurately measuring the height of molten iron and dynamically determining the critical overflow position, combined with real-time monitoring by infrared cameras, the present invention can timely detect and warn of the risk of molten iron overflow, effectively avoiding production safety accidents caused by molten iron overflow, and greatly improving the safety level of the work site. Automated calculation of the tipping angle and slag removal trajectory planning reduce the time for manual intervention and judgment, making slag removal operations more efficient and accurate. At the same time, the real-time display and monitoring functions of the 3D model allow operators to intuitively understand the operating status and quickly respond to abnormal situations, further improving overall operating efficiency.

[0082] 2. Enhanced operation accuracy: The high-precision data acquisition and intelligent data analysis technology of the laser radar ensures the accuracy of the molten iron height measurement, which makes the determination of the tipping angle and the planning of the slag removal trajectory more accurate, which helps to improve the slag removal quality and the utilization rate of the molten iron and reduce resource waste. The equipment in the present invention has high reliability and stability, reducing downtime and maintenance costs caused by equipment failure. At the same time, the automated monitoring and early warning mechanism helps to discover and solve potential problems in advance and extend the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0084] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0085] Figure 2 It is a schematic diagram of the system composition of the present invention;

[0086] Figure 3 This is a schematic diagram of data measured by a laser radar according to the second embodiment of the present invention;

[0087] Figure 4 It is a schematic diagram of the position of the edge of the molten iron ladle in the infrared camera when different angles are calibrated according to the second embodiment of the present invention;

[0088] Figure 5 for Figure 4 A schematic diagram of a digital format of location information;

[0089] Figure 6 This is a schematic diagram of key point positioning in Embodiment 2 of the present invention;

[0090] Figure 7 for Figure 6A schematic diagram of a digital format of location information;

[0091] Figure 8 Based on Figure 7 Schematic diagram of trajectory file definition of location information. DETAILED DESCRIPTION

[0092] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below;

[0093] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0094] Example 1: In modern steel mills, hot metal ladle is used to transport high-temperature hot metal. In order to ensure the safety and efficiency of the transportation process, this example will disclose an automatic control system based on laser radar, infrared camera and 3D model to monitor and control the tilting angle, hot metal height and slag removal of the hot metal ladle. Figure 1 As shown, it specifically includes the following steps S1 to S6.

[0095] In this embodiment, regarding step S1: laser radar data collection:

[0096] Sensor installation and calibration (S100): A high-precision LiDAR sensor was installed on the upper part of the ladle's travel path and strictly calibrated, including adjusting the scanning angle to 45 degrees to cover the entire ladle surface, setting the scanning frequency to 50 Hz to ensure real-time performance, and adjusting the resolution parameter to 0.1 mm to improve measurement accuracy.

[0097] Real-time distance measurement (S101): The LiDAR sensor continuously emits laser pulses downward and receives the reflected signals. The distance data of each measurement point is recorded with a time stamp accurate to milliseconds.

[0098] Data preprocessing (S102): The original distance data is smoothed by a moving average filtering algorithm to remove data fluctuations caused by environmental noise.

[0099] Height data extraction (S103): The preprocessed data is subjected to feature point recognition using the Halcon algorithm, and feature points of the front edge A, the front edge B, and the rear edge C of the molten iron surface are successfully recognized. The height data of these feature points are obtained by calculating the vertical distances of these feature points relative to the LiDAR sensor.

[0100] Data storage and transmission (S104): The extracted height data is stored in a local database in real time and simultaneously transmitted to a data processing and control system via a network for further analysis.

[0101] In this embodiment, regarding step S2: calculation of molten iron height:

[0102] Height data feature recognition (S200): The collected height data is analyzed in detail, and the respective features of the front edge A, the molten iron surface B and the rear edge C of the molten iron surface are accurately identified using a peak detection algorithm.

[0103] Data filtering and smoothing (S201): A low-pass filter is applied to the height data of the middle area of ​​the molten iron surface, which effectively removes high-frequency noise and fluctuations in the data and retains the true molten iron surface height information.

[0104] Outlier detection and processing (S202): In the filtered data, outliers caused by measurement errors are detected by setting a threshold value and replaced with the average value of adjacent data to ensure the accuracy of the data.

[0105] Calculation of molten iron height (S203): Based on the filtered and processed height data, the heights of the front edge A of the molten iron surface and the rear edge C of the molten iron are averaged to obtain the accurate molten iron height.

[0106] Data verification and calibration (S204): The calculated molten iron height is compared with the expected value and verified by independent measurement means to ensure the accuracy of the data.

[0107] In this embodiment, regarding step S3: determining the tipping angle and determining the overflow critical position

[0108] Determine the tilting angle (S300): According to the height of the molten iron, the corresponding tilting angle is matched in the preset data table by interpolation method. For example, when the height of the molten iron is 1.5 meters, the tilting angle should be 30 degrees according to the table.

[0109] Overflow critical position determination (S301): Based on the tipping angle and the geometric dimensions of the molten iron ladle, the critical position for molten iron overflow is calculated. At the same time, the real-time image of the molten iron ladle taken by the infrared camera is read, and the position and shape of the molten iron area are identified through image processing technology. By comparison, it is found that the position of the molten iron area does not exceed the overflow critical position, and it is determined to be in a safe state.

[0110] Comprehensive determination and response (S302): Since the tipping angle and the molten iron position are both within the safe range, no warning or control measures are triggered. The system continues to monitor the status of the molten iron ladle.

[0111] In this embodiment, regarding step S4: slag removal trajectory planning

[0112] Determination of key point coordinates (S400): Based on the molten iron height and tilting angle, combined with the process requirements of the slag removal operation, the key point coordinates that need to be reached during slag removal are calculated. By searching the preset slag removal trajectory data table, the most matching trajectory data is found, and appropriate interpolation adjustments are made to adapt to the current situation.

[0113] Trajectory smoothing and optimization (S401): The generated scraping trajectory is smoothed to remove unnecessary fluctuations and turning points. At the same time, a reasonable speed is set for each key point in the trajectory to ensure the smoothness and efficiency of the scraping operation.

[0114] Type setting (S402): The type (such as starting point, end point, turning point, etc.) is set for each key point, and the position control accuracy is set. This ensures that the control system can accurately identify and execute the corresponding action.

[0115] Z coordinate automatic adjustment attribute setting (S403): The Z coordinate automatic adjustment attribute of the key point in the trajectory is set. During the slag removal operation, the slag removal machine can flexibly adjust the Z coordinate according to the actual situation to ensure the slag removal effect.

[0116] In this embodiment, regarding step S5: slag removal operation is performed:

[0117] Trajectory call and adjustment (S500): According to the slag distribution, the corresponding slag removal trajectory is called for operation. During the operation, the slag removal trajectory is adjusted in real time through visual analysis to adapt to changes in the actual situation.

[0118] Collision handling (S501): During the scrapping operation, the system monitors the operating status of the scraper in real time. When a collision is detected, the scraper stops moving immediately, and performs operations such as backing up, adjusting the trajectory, and alarming according to the preset collision handling strategy, ensuring the safety of the operation.

[0119] In this embodiment, regarding step S6: real-time display and monitoring of 3D model

[0120] 3D model establishment and loading (S600): According to the actual size and shape of the molten iron ladle, slag scraper and working environment, an accurate 3D model is established and loaded into the monitoring system. The model includes detailed information such as the internal structure of the molten iron ladle, the moving parts of the slag scraper and obstacles in the working environment.

[0121] Real-time display of the scraper trajectory (S601): In the 3D model, the planned scraper trajectory is represented by a dotted line, and the actual operation trajectory of the scraper is represented by a solid line or a dynamic icon. By comparing the two, the operator can intuitively understand the operation status and deviation of the scraper.

[0122] Abnormal monitoring and response (implicit steps): During the monitoring process, if an abnormal situation is found (such as the slag remover deviates from the planned trajectory, molten iron overflows, etc.), the system will immediately issue a warning signal and stop the slag removal operation. At the same time, take corresponding safety measures (such as turning off the power supply, starting the emergency rescue procedure, etc.) to ensure the safety of personnel and equipment.

[0123] Embodiment 2: Based on Embodiment 1, this embodiment further provides a specific application example of the intelligent detection method for detecting the tilting angle of the molten iron tank:

[0124] A laser radar sensor is installed on the upper part of the path of the molten iron ladle to measure the distance to the lower molten iron surface in real time. By matching the changing characteristics of the height data over a period of time with the shape of the molten iron ladle, it is possible to accurately identify the data within the molten iron range, such as Figure 3 As shown, the data is processed by low-pass filtering to obtain accurate molten iron height data.

[0125] According to the measured molten iron height, the tilting angle of the molten iron tank corresponding to the current molten iron height is calculated by linear interpolation of the pre-calibrated angle-height data table. At the same time, in order to prevent the risk of molten iron overflow caused by height measurement error, the concept of "critical judgment position for molten iron overflow" as described in Example 1 is introduced. The molten iron area is monitored in real time by an infrared camera to see if it exceeds the judgment position (such as Figures 4-5 As shown in the figure, once the risk of molten iron overflow is detected, the tipping operation is stopped immediately.

[0126] In order to remove all the slag surface as much as possible, and combined with the visual analysis of the slag distribution on the slag surface, 21 key points are defined to generate the slag removal trajectory (such as Figures 6-7 These key points are calibrated in units of 1 degree, covering all important positions during the ladle tipping process. Based on these key points and combined with the empirical data of slag removal, a series of slag removal trajectories are generated as follows: Figure 8 As shown in the figure. The program will automatically call the corresponding slag removal trajectory to perform slag removal operations based on the slag distribution on the slag surface analyzed by the visual system. The collision handling problem of trajectory operation is also considered during the slag removal process. The 3D model displays the slag removal planning trajectory and operation trajectory in real time, so that the operator can intuitively monitor the slag removal process and perform manual intervention when necessary.

[0127] This technical solution is applicable to the slag removal operation of hot metal ladle in steel enterprises. In actual application, when the hot metal ladle is moving, the laser radar sensor will measure the height of the hot metal in real time and transmit the data to the control system. The control system calculates the tilting angle of the hot metal ladle based on the measured data and controls the tilting mechanism to perform the tilting operation. At the same time, the infrared camera monitors the changes in the hot metal area in real time, and stops the tilting operation immediately if the risk of hot metal overflow is found.

[0128] During the slag removal process, the operator can view the slag removal planning trajectory and operation trajectory in real time through the 3D model to monitor and adjust the slag removal process. According to the slag distribution on the slag surface, the program will automatically call the corresponding slag removal trajectory for slag removal operations, thereby ensuring the maximum slag removal effect.

[0129] Embodiment 3: Figure 2 As shown, this embodiment further discloses an intelligent detection system for detecting the tilting angle of a molten iron ladle, which is a hardware carrier of the intelligent detection method of the above-mentioned embodiment 1, and includes:

[0130] (I) LiDAR sensor: As one of the core components of the hardware system, the LiDAR sensor is installed on the upper part of the path of the molten iron ladle. Its main function is to measure the distance to the lower molten iron ladle and molten iron in real time by emitting laser and receiving the reflected signal. The sensor is equipped with a high-precision ranging module and data processing unit, which can collect height data changes over a period of time and accurately identify the front, middle and rear edges of the molten iron surface.

[0131] It is understandable that the LiDAR sensor has the characteristics of high precision, high reliability and strong real-time performance. Even in a complex and changeable industrial environment, it can work stably to ensure the accuracy and timeliness of data collection. This feature provides a solid foundation for the subsequent calculation of the tilting angle of the molten iron ladle and the planning of the slag removal trajectory.

[0132] (ii) Infrared camera:

[0133] The infrared camera is responsible for real-time monitoring of the molten iron area in the molten iron ladle. By capturing real-time images of the molten iron ladle and combining them with image analysis technology, the infrared camera can determine whether the molten iron area exceeds the preset overflow critical position. The infrared camera has night vision and high-temperature object recognition capabilities, which enables it to work normally in low-light or high-temperature environments. The images of the molten iron area captured by the camera are clear and accurate, providing an important visual basis for system decision-making. At the same time, the real-time monitoring function of the infrared camera can also promptly detect and warn of potential molten iron overflow risks, thereby ensuring production safety.

[0134] (III) Processor and registers:

[0135] The processor is the control center of the hardware system, connecting the lidar sensor and infrared camera, and receiving the data transmitted by them. The processor is integrated with a high-performance data processing unit and intelligent analysis algorithm, which can process and analyze the received data in real time. The register stores program instructions, and when these instructions are executed by the processor, they will drive the processor to execute the above-mentioned intelligent detection method. The processor can automatically calculate the tipping angle of the molten iron ladle according to the data changes, and dynamically determine the critical position of the molten iron overflow. At the same time, it can also automatically adjust the slag removal trajectory and operating parameters according to the analysis results to ensure the smooth progress of the slag removal operation.

[0136] (IV) Overall system collaboration:

[0137] The various components in the hardware system work together to complete various tasks in the slag removal process of the molten iron ladle. The lidar sensor and infrared camera are responsible for data collection and real-time monitoring, while the processor is responsible for data processing and intelligent analysis. Through this series of processes, the system can achieve precise control of the tilting angle of the molten iron ladle, real-time monitoring of the risk of molten iron overflow, and intelligent planning of the slag removal trajectory.

[0138] For those skilled in the art, it can be further appreciated that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0139] At the same time, those skilled in the art can understand that all or part of the processes in all the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0140] The above embodiments only express the implementation methods of the relevant practical applications of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An intelligent detection method for detecting the tipping angle of a molten iron ladle, characterized in that: The following steps are included: S1, the lidar collects height data for a period of time at the upper part of the ladle's path; S2, analyzing the collected height data, identifying the characteristics of the front edge A, the molten iron surface B and the rear edge C of the molten iron surface; performing low-pass filtering on the data in the middle area of ​​the molten iron surface; and calculating the height of the molten iron based on the filtered data; S3, according to the height of the molten iron, determine the tilting angle of the molten iron tank through a preset data table; at the same time, according to the tilting angle, obtain the critical judgment position of the molten iron overflow; read the real-time image taken by the infrared camera, and analyze whether the molten iron area exceeds the critical judgment position of the overflow; S4, determine the coordinates of the key points when slag removal according to the molten iron height and tilting angle; S5, start the slag removal operation, and call the corresponding slag removal trajectory to perform the slag removal operation based on the visual analysis of the slag distribution on the slag surface.

2. The intelligent detection method according to claim 1, characterized in that: In S1, the characteristic points of the molten iron surface are identified by the Halcon algorithm, SIFT algorithm, SURF algorithm or generalized Hough transform algorithm, and their vertical distances relative to the lidar sensor are calculated to extract the height data of the front edge A of the molten iron surface, the molten iron surface B and the rear edge C of the molten iron surface.

3. The intelligent detection method according to claim 1, characterized in that: The execution method of S2 includes: S200, using a peak detection algorithm or an edge recognition algorithm to identify the respective features of the front edge A, the molten iron surface B and the rear edge C of the molten iron surface from the collected height data; S201, applying a low-pass filter to smooth the height data of the middle area of ​​the molten iron surface; S202, performing outlier detection of measurement errors in the filtered data; replacing the detected outliers with the average value or interpolation of adjacent data; S203, based on the filtered and processed height data, average the heights of the front edge A of the molten iron surface and the rear edge C of the molten iron to obtain the height of the molten iron.

4. The intelligent detection method according to claim 1, characterized in that: The execution method of S3 includes: S300, matching the tilting angle corresponding to the current molten iron height by traversing and searching or interpolating based on a preset data table; and reading the current tilting angle of the molten iron ladle according to the matching result; S301, according to the tipping angle, combined with the geometric dimensions of the molten iron ladle and the critical conditions for molten iron overflow, the critical position for molten iron overflow is calculated or looked up in a table; at the same time, the real-time image of the molten iron ladle taken by the infrared camera is read to identify the position and shape of the molten iron area; if the position of the molten iron area exceeds the critical position for overflow, it is determined that there is a risk of molten iron overflow; otherwise, it is determined to be in a safe state; S302: If the tipping angle reaches a preset limit value or there is a risk of molten iron overflowing, corresponding warning or control measures are triggered; at the same time, the tipping angle of the molten iron tank is automatically adjusted according to the preset control strategy.

5. The intelligent detection method according to any one of claims 1 to 4, characterized in that: In said S4, the preset scraping trajectory data table is called, and a suitable scraping trajectory is generated in combination with the current situation; the speed, type, position control accuracy of key points in the trajectory and whether the Z coordinate is automatically adjusted are set.

6. The intelligent detection method according to claim 5, characterized in that: The execution steps of S4 include: S400, calculating the coordinates of key points that need to be reached when slagging according to the height and tilting angle of the molten iron, including the starting point, the ending point and the turning point of the slagging process; searching for the most matching trajectory data in the preset slagging trajectory data table according to the current molten iron height and tilting angle; S401, smoothing the generated scraping trajectory to remove fluctuations and inflection points; and setting an average speed for each key point in the trajectory; S402, setting the type for each key point, including the start point, the end point and the turning point; and setting the position control accuracy for each key point in the trajectory; S403, setting whether the Z coordinates of key points in the trajectory are automatically adjusted; if automatic adjustment is required, the adjustment range and conditions should be set to constrain the scraper to adjust the Z coordinates according to actual conditions during operation.

7. The intelligent detection method according to claim 5, characterized in that: The execution steps of S5 include: S500, according to the slag amount distribution, call the corresponding slag removal trajectory to perform the slag removal operation; if the slag amount distribution does not meet the expectation, adjust the slag removal trajectory to adapt to the actual situation; S501, during the scrapping operation, the operating status of the scraper is monitored in real time to detect whether a collision occurs; if a collision occurs, the movement of the scraper is stopped immediately and processed according to a preset collision handling strategy, including retreating, adjusting the trajectory and / or alarming.

8. The intelligent detection method according to claim 1, characterized in that: It also includes S6: The slag removal planning trajectory and operation trajectory are displayed in real time through a 3D model. If any abnormal situation is found, the slag removal operation will be stopped immediately and corresponding safety measures will be taken.

9. An intelligent detection system for detecting the tipping angle of a molten iron ladle, characterized in that: include: A LiDAR sensor that measures the distance between the ladle and the molten iron in real time; Infrared camera for real-time monitoring of the molten iron area in the molten iron ladle; A processor connected to the laser radar sensor and the infrared camera, and a register coupled to the processor, wherein program instructions are stored in the register, and when the program instructions are executed by the processor, the processor executes the intelligent detection method as described in any one of claims 1-8.

10. The intelligent detection system according to claim 9, characterized in that: The laser radar sensor is installed on the upper part of the travel path of the molten iron tank; by collecting height data changes over a period of time, the front edge, middle area and rear edge of the molten iron surface are identified.

Images