Online roller way type casting blank continuous weighing device and method

Abstract

The invention discloses an on-line roller way type casting blank continuous weighing device and method, and belongs to the technical field of metallurgy continuous casting. The casting blank continuous weighing device comprises a conveying roller way system, a weighing sensor system, a visual identification system and a central control system, the weighing sensor system is installed below a weighing roller way and used for weighing casting blanks conveyed to the weighing roller way, and the visual identification system is used for identifying the casting blanks conveyed to the weighing roller way. The visual identification system is used for acquiring the moving track of the casting blank in the conveying process through image acquisition and processing so as to judge whether a weighing starting or stopping signal needs to be sent or not; the visual identification system and the weighing sensor system are connected with the central control system. According to the invention, online continuous weighing of the casting blank is realized, a production line does not need to be stopped, the production efficiency and the weighing precision are obviously improved, full-automatic operation is realized, and the labor cost is reduced.

Description

Technical Field

[0001] This invention belongs to the field of metallurgical continuous casting technology, and in particular relates to an online roller conveyor type continuous casting billet weighing device and method. Background Technology

[0002] In the continuous casting process of steel, especially in production lines that produce rectangular billets, irregular-shaped billets, and square billets, it is necessary to weigh the cut billets to ensure product quality and manage production. Traditional weighing methods usually require stopping the production line and placing the object to be weighed on a static weighing device for measurement.

[0003] This intermittent weighing process has many technical drawbacks: Traditional roller conveyors generate mechanical vibrations and bumps during billet movement, and these dynamic disturbances severely affect the measurement accuracy of the weighing sensors, resulting in large fluctuations in weighing data and making it impossible to obtain accurate weight values. Therefore, the billet movement must be stopped for accurate weighing. Because the production process needs to be interrupted for weighing, it not only seriously affects the continuity of the production line and the overall production efficiency, but also takes a long time, resulting in a slow production cycle. During the shutdown weighing process, auxiliary equipment such as heating furnaces and insulation equipment need to be kept running, resulting in a large amount of energy waste. Frequent start-ups and shutdowns of the production line also lead to accelerated equipment wear, further reducing overall production efficiency. At the same time, this method relies on manual judgment of weighing timing, equipment operation, and data recording, which not only increases labor costs, but also makes it easy for the randomness of human operation and environmental interference factors to introduce measurement errors, making it difficult to guarantee the stability and consistency of weighing accuracy. This method is far from meeting the technical requirements of modern continuous production lines for high-efficiency, high-precision, and automated weighing.

[0004] Furthermore, traditional shutdown weighing methods suffer from the following efficiency losses: weighing operation time is 7-35 seconds, restart time is 1-2 seconds, and the cumulative time loss reaches 8-37 seconds per operation. Considering the high output value of continuous casting production lines, the economic loss from each shutdown weighing operation can reach hundreds of yuan, seriously affecting the economic benefits of enterprises. Currently, most steel plants rely on manual tracking and adjustment for the weighing process in continuous casting production, which is inefficient, labor-intensive, time-consuming, and lacks accuracy, far from meeting production needs.

[0005] While some existing online weighing technologies can solve the above problems to some extent, they still have technical defects such as difficulty in accurately controlling the start and end times of weighing, low weighing accuracy, and low system integration. Summary of the Invention

[0006] This invention provides an online roller conveyor type continuous weighing device and method for billets, which can solve the problems of low weighing accuracy, impact on production continuity, and high labor costs of traditional stop-and-weigh methods. The technical solution of this invention can realize online continuous and automated weighing of billets and effectively ensure its weighing accuracy, thus solving the problems of low accuracy in existing online weighing technologies.

[0007] To achieve the above objectives, the present invention provides the following solution: The first aspect of the present invention provides an online roller conveyor type continuous weighing device for cast billets, comprising: A conveyor roller system for conveying billets, comprising parallel multi-flow conveyor rollers, each of which includes a feed roller, a weighing roller, and a discharge roller arranged sequentially along the billet conveying direction. A weighing sensor system is installed below the weighing roller conveyor and is used to weigh the billet conveyed to the weighing roller conveyor. It includes several independent weighing units distributed at intervals along the billet conveying direction. Each weighing unit includes two weighing sensors located below the same weighing roller and close to the outer sides of its two ends, namely the first sensor and the second sensor. A visual recognition system is used to acquire the movement trajectory of the billet during the conveying process through image acquisition and processing, so as to determine whether it is necessary to send a weighing start or stop signal; The system includes a central control system, which is connected to both the vision recognition system and the weighing sensor system. The central control system receives vision recognition signals to control the start and stop of the weighing process and receives and processes the weighing signals collected by the weighing sensor system to obtain the billet weighing results.

[0008] According to any of the technical solutions described in the first aspect of the present invention, the feed roller, weighing roller and discharge roller in each flow conveyor roller table are respectively composed of a plurality of feed rollers, weighing rollers and discharge rollers distributed at intervals along the conveying direction, the rotation direction of each roller corresponds to the conveying direction of the billet, and each roller is driven by a motor. According to any of the technical solutions described in the first aspect of the present invention, each flow conveyor roller is installed and supported by a support frame, the support frame including a support base distributed below each weighing roller and extending along the length direction of the weighing roller, and two parallel and relatively spaced roller beams installed on the top of each support base and extending along the billet conveying direction, wherein the feed roller, weighing roller and discharge roller on the flow conveyor roller are respectively rotatably installed between the two roller beams at intervals.

[0009] According to any of the technical solutions described in the first aspect of the present invention, the weighing sensor is mounted on the underside of the support frame via a mounting base, and its top is in contact with the spherical surface of the support frame via a spherical contact pad.

[0010] According to any of the technical solutions described in the first aspect of the present invention, the mounting base is provided with a mounting groove for mounting and accommodating a weighing sensor. The weighing sensor is mounted on the bottom plate of the mounting groove by a support screw, and the mounting base together with the entire weighing device is fixedly mounted on the concrete foundation by the support screw.

[0011] According to any of the technical solutions described in the first aspect of the present invention, the weighing sensor system includes a three-stage adjustment mechanism for adjusting the installation height of the weighing sensor, wherein: Primary coarse adjustment mechanism: Four support screws are symmetrically arranged below each load cell and connected to the mounting base for coarse adjustment; Secondary adjustment mechanism: Equipped with precision gaskets of different thicknesses for adjustment; Three-stage fine-tuning mechanism: This three-stage fine-tuning mechanism uses a wedge-shaped adjustment mechanism for fine-tuning; The wedge adjustment mechanism includes a fixed wedge and a movable wedge that cooperate with each other through wedge surfaces. The fixed wedge is fixedly installed on the bottom of the load cell, and the movable wedge is connected to the mounting base through a support screw.

[0012] According to any of the technical solutions described in the first aspect of the present invention, the weighing sensor is connected to the central control system through a signal box, and the signal box is used to perform signal conditioning and A / D conversion on the data collected by the weighing sensor and transmit it to the central control system; The visual recognition system includes a first camera and a second camera respectively installed at the feeding end and the discharging end of the weighing roller conveyor. The first camera is used to acquire and process images of the billet at the feeding end of the weighing roller conveyor to determine whether the billet has completely entered the weighing area. The second camera is used to acquire and process images of the billet at the discharging end of the weighing roller conveyor to determine whether the billet has begun to leave the weighing area.

[0013] A second aspect of the present invention also provides an online roller conveyor continuous weighing method for cast billets, employing any of the online roller conveyor continuous weighing devices described in the first aspect of the present invention, comprising the following steps: The billet is conveyed by a conveyor roller, and the status of the billet on the conveyor roller is monitored in real time by a vision recognition system to identify the color characteristics and position information of the billet. When the visual recognition system detects that the tail end of the billet has completely entered the weighing area, it sends a weighing start signal to the central control system. The central control system then controls the weighing sensor system to start data acquisition, and the weighing sensor system transmits the acquired weight data to the central control system in real time. When the visual recognition system detects that the billet head begins to leave the weighing area, it sends a weighing end signal to the central control system, and the weighing sensor system automatically stops weighing. After receiving the weighing data sent by the weighing sensor system, the central control system processes the data in real time and calculates the final weighing result.

[0014] According to any of the technical solutions described in the second aspect of the present invention, after receiving the weighing data sent by the weighing sensor system, the central control system processes the data in real time and calculates the final weighing result, specifically including: Data preprocessing: The repetitive data is preprocessed, including filtering. Prediction and dynamic adjustment: Based on the casting speed, position and historical data of the billet, the system makes predictions and estimates the upcoming position and weight change trend of the billet; Data fusion and weighted processing: Data from different weighing sensors are fused using a weighted averaging technique; Output final weight data: The weighing data after multiple layers of processing will be sent to the central control system for display and processing, updating the weight information of the billet in real time, and outputting the final weight data.

[0015] According to any of the technical solutions described in the second aspect of the present invention, in the prediction and dynamic adjustment step, the window length and weight value of the data processing are automatically adjusted based on the speed and weight of the billet, wherein the window length calculation takes into account the billet passing speed and the lateral spacing between adjacent roller conveyor sensors, and the final window length is: L window = L base × k v × k stability ;in: Base window length L base :L base = ceil(S / (v×f s S is the sensor spacing between adjacent rollers, v is the billet casting speed, and f is the casting speed. s The sampling frequency; velocity correlation coefficient k v :k v = 1+μ×(vv ref ) / v ref μ is the adjustment coefficient, v ref This is the reference speed, i.e., the theoretical value; Stability coefficient k stability :k stability = 1 + 0.2 × σ v / v mean , σ v v is the standard deviation of velocity. mean This represents the average speed.

[0016] According to any of the technical solutions described in the second aspect of the present invention, the data fusion and weighting processing step specifically includes: (1) Internally fuse the data of two weighing sensors corresponding to the same weighing roller, and the weighting coefficients are allocated considering the sensor position and the center of gravity of the billet: w front = (L rear / L total ); w rear = (L front / L total ); in, w front , w rear These are the fusion weighting coefficients for the first sensor (4001) and the second sensor (4002) corresponding to the same weighing roller, respectively; L rear L front L represents the longitudinal distance L from the center of gravity of the billet to the second sensor (4002) and the first sensor (4001), respectively. total Let W be the longitudinal distance between the two weighing sensors, then the fused weight W of the two weighing sensors corresponding to the i-th weighing roller is... i = First sensor reading × w front +Second sensor reading × w rear ; (2) The sensor data between adjacent weighing rollers adopts a recursive fusion strategy, that is, the weights of each weighing roller are dynamically adjusted based on the billet coverage length. w i0 : w i0 = Coverage i / Σ(Coverage j Coverage i Σ(Coverage) represents the coverage ratio of the cast billet on weighing roller i. j () represents the sum of the coverage ratios of the billet on all weighing rollers; Then the weight of the cast billet W0 = Σ(W i × w i0 ).

[0017] According to any of the technical solutions described in the second aspect of the present invention, the filtering process in the data preprocessing includes three-stage filtering: hardware filtering, digital pre-filtering, and adaptive Kalman filtering, wherein: The adaptive Kalman filter employs the state equation x(k+1) = Fx(k) + Gu(k) + ω(k) and the observation equation z(k) = Hx(k) + v(k). For a multi-sensor system, its state vector x(k) contains the weight estimates and rates of change of each sensor; F, G, and H are the system matrix, control matrix, and observation matrix, respectively; z(k) is the observation vector; ω(k) and v(k) are the process noise and observation noise, respectively; u(k) represents the control input or external influence of the system at time k, which can be the sensor's adjustment signal or other external force; the process noise covariance Q is set as a diagonal matrix diag([σ ω² ,σ v² ]); Observation noise covariance R = σ r 2 ; According to any of the technical solutions described in the second aspect of the present invention, when fusing sensor data between adjacent weighing rollers, the weights corresponding to each weighing roller are assigned based on the weight of the billet. w i0 Adjustments are made to determine the final weight. w i = Base weight w i0 ×k w ; Where, k w k is the weight correlation coefficient. w =1+β×(WW ref ) / W ref β is the adjustment coefficient (taken as 0.05~0.15); W ref For reference weight.

[0018] Compared with the prior art, the present invention can achieve the following beneficial effects: (1) The present invention provides an online roller conveyor type continuous weighing device for billets. The device identifies the timing when the billet fully enters or leaves the weighing area through a visual recognition system, thereby accurately controlling the start and end timing of weighing and reducing weighing errors caused by improper timing control. This ensures that the billet can be continuously weighed online without stopping the production line, which significantly improves production efficiency. Furthermore, the system's reliability and fault tolerance are further improved by adopting a distributed weighing sensor design.

[0019] (2) This invention optimizes the installation structure of the conveyor roller and the weighing sensor, especially through the spherical contact structure between the top of the sensor and the support frame of the weighing roller, and the three-level adjustment mechanism between the bottom of the sensor and the mounting base. This not only reduces the impact of mechanical vibration and bumps on the weighing accuracy and achieves the accuracy of dynamic weighing, but also allows for coarse, medium and fine adjustment of the height of the weighing sensor as needed.

[0020] (3) The present invention further adopts multi-sensor data fusion technology to weight and fuse the data of multiple weighing sensors. Two weighing sensors are set below the same weighing roller, and their weight coefficients are determined based on the distance between the two sensors and the center of gravity of the billet. The sensor data between adjacent weighing rollers adopts a recursive fusion strategy, that is, the weight of each weighing roller is dynamically adjusted based on the coverage length of the billet, which is conducive to improving the detection accuracy of the billet weight.

[0021] (4) The present invention further adopts the Kalman filter algorithm to filter the weight signal in real time, which can effectively suppress vibration and noise interference, which is conducive to further improving the detection accuracy of billet weight, and the data processing delay is less than 10ms, which can meet the real-time control requirements.

[0022] In summary, this invention enables fully automated operation, reduces manual intervention and labor costs, significantly improves weighing accuracy and production efficiency, and ensures continuous movement of the billet throughout the weighing process without affecting the production cycle. Furthermore, this invention is applicable to weighing billets of different specifications and temperatures, demonstrating good versatility and providing strong support for the digital transformation of the steel industry. Attached Figure Description

[0023] The dimensions and scales in the accompanying drawings do not represent the actual dimensions and scales of the product. The drawings are for illustrative purposes only, and some non-essential elements or features have been omitted for clarity.

[0024] Figure 1 This is a flowchart of the online roller conveyor continuous weighing method for cast billets according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the overall structure of the online roller conveyor continuous weighing device for billets according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the longitudinal installation structure of the weighing roller conveyor according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the horizontal mounting structure of the weighing sensor according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the longitudinal installation structure of the weighing sensor according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the installation structure of the weighing sensor and the wedge adjustment mechanism according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the wedge adjustment mechanism in the case of no weighing in an embodiment of the present invention; Figure 8 This is a schematic diagram of the state of the wedge adjustment mechanism during weighing in an embodiment of the present invention.

[0025] The components are as follows: 101, roller beam; 102, support base; 103, concrete foundation; 2, feed roller conveyor; 3, weighing roller conveyor; 4, weighing sensor; 4001, first sensor; 4002, second sensor; 401, spherical contact pad; 402, mounting base; 403, support screw; 404, wedge adjustment mechanism; 4041, fixed wedge; 4042, movable wedge; 405, gasket; 5, first camera; 6, second camera; 7, signal box; 8, central control system; 9, weighing roller; 10, discharge roller conveyor; 11, billet; 12, motor. Detailed Implementation

[0026] To further understand the present invention, it will be described in detail below with reference to the accompanying drawings and embodiments. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this disclosure. In the following detailed description, numerous specific details are set forth to provide a comprehensive understanding of the embodiments of this disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of this disclosure.

[0027] The structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0028] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated devices, elements, or components to having a specific orientation, or to be constructed and operated in a specific orientation. Furthermore, some of the above terms may be used to indicate other meanings besides orientation or positional relationship; for example, the term "upper" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application according to the specific circumstances.

[0029] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein.

[0030] Furthermore, the terms "comprising," "including," etc., used in this application indicate the presence of the stated features, steps, operations, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components. The terms "installed," "set up," "equipped with," "connected," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral structure; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, elements, or components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0031] It should also be understood that, for clarity, certain features of this disclosure may be described herein in the context of individual embodiments, but may also be provided in combination with each other in individual embodiments. That is, unless obviously incompatible or specifically excluded, each individual embodiment is considered to be combinable with any other embodiment, and such combination is considered to represent another different embodiment. Conversely, for brevity, various features of this disclosure described in the context of individual embodiments may also be provided individually or in any sub-combination. Finally, while a particular embodiment may be described as part of a series of steps or part of a more general structure, each step or substructure may also be considered an independent embodiment in itself.

[0032] like Figure 2 , Figure 3 As shown, this embodiment of the invention provides an online roller conveyor type continuous weighing device for cast billets, including a conveyor roller system, a weighing sensor system, a vision recognition system, and a central control system 8, wherein: The conveying roller system is used to convey the billet, and includes multiple conveying rollers arranged in parallel. Each conveying roller includes a feed roller 2, a weighing roller 3 and a discharge roller 10 arranged sequentially along the billet conveying direction (transverse). The weighing sensor system is installed below the weighing roller conveyor 3 and is used to weigh the billets conveyed to the weighing roller conveyor 3. The visual recognition system is used to acquire and process images to obtain the movement trajectory of the billet during the conveying process, thereby determining whether a weighing start or stop signal needs to be sent. The visual recognition system and the weighing sensor system are both connected to the central control system 8. The central control system 8 is used to receive weighing signals and visual recognition signals, and to control the start and stop of the weighing process.

[0033] In this embodiment of the invention, each feed roller 2, weighing roller 3 and discharge roller 10 is composed of multiple feed rollers, weighing rollers 9 and discharge rollers (collectively referred to as conveying rollers) that are spaced apart along the conveying direction. The rotation direction of each conveying roller corresponds to the conveying direction of the billet, and each conveying roller is driven by a motor 12 with adjustable speed to ensure that the billet 11 is conveyed smoothly.

[0034] The number of each conveying roller and the spacing between adjacent conveying rollers can be determined according to the length of the billet 11 to be conveyed. For example, the number of conveying rollers is 12 to 16, and the spacing between adjacent conveying rollers is 1 to 1.5 m. Furthermore, in this embodiment of the invention, each conveying roller is preferably made of 45# steel with a surface hardness of HRC45 to 50, a diameter of 200 mm, and a length that can be customized according to the width of the billet.

[0035] In some embodiments, conveying rollers distributed along the same flow path are supported by a support frame, which includes a support base 102 and roller beams 101. The support base 102 includes multiple spaced support seats located in the area where the weighing roller conveyor 3 is located, corresponding to each weighing roller 9 (each located below the weighing roller and extending along the length direction of the weighing roller, i.e., extending longitudinally), and is fixedly installed on a concrete foundation 103. The top of the support base 102 is provided with two parallel, spaced roller beams 101 extending along the conveying direction of the billet 11. Both ends of each conveying roller are rotatably mounted between the two roller beams 101, and one end of the feed roller, weighing roller 9, and discharge roller are coaxially fixed to an output shaft and driven to rotate by a motor 12. Specifically, in this embodiment of the invention, the motor 12 is a variable frequency speed control motor with a speed range of 0~100 rpm.

[0036] In some embodiments, the weighing sensor system includes a plurality of independent weighing units spaced apart along the billet conveying direction, which detect weight changes on corresponding weighing rollers 9. In a preferred embodiment, each weighing unit includes two weighing sensors 4 located below the same weighing roller 9: a first sensor 4001 (or a front sensor, for ease of expression)... Figure 2The first weighing sensor 4002 (or rear sensor) and the second weighing sensor 4002 are symmetrically located below and near the outer sides of the same weighing roller to ensure uniform force distribution on the roller conveyor. All the weighing sensors 4 constitute a distributed weighing detection system. More preferably, a laser tracker is used for three-dimensional coordinate measurement to establish a spatial position database of the roller conveyor and sensors, facilitating subsequent data processing.

[0037] Specifically, the height difference between the two sensors corresponding to the same weighing roller 9 is controlled within 0.05mm, and their signals are differentially amplified and fused to effectively eliminate the influence of off-center loading and improve measurement accuracy. Furthermore, the sensor spacing S between adjacent rollers is controlled at 1~2m, and the specific spacing S is determined based on the minimum length Lmin of the billet: S = Lmin / n, where n is the minimum number of sensors (≥3) that the billet must cover in the transverse direction.

[0038] Specifically, in this embodiment of the invention, the length of the support base 102 is greater than the distance between the two roller beams 101, that is, both ends of the support base 102 extend outwards from the two roller beams 101 by a certain length. The first sensor 4001 and the second sensor 4002 are installed below the support base 102 and close to both ends of the support base 102, respectively. The longitudinal horizontal distance between them and the corresponding ends (front end or tail end) of the support base 102 is 200~300mm. The weighing sensor 4 in this embodiment of the invention adopts a high-precision strain gauge weighing sensor with a range of 0~7.5 tons, an accuracy class of C3, a nonlinearity ≤0.02%FS, and a repeatability ≤0.01%FS.

[0039] like Figure 4 As shown, in some embodiments, each load cell 4 is provided with a mounting base 402 at its installation position. The mounting base 402 is located below the support base 102 (fixedly connected to the support base 102) and has a mounting groove for placing the load cell 4. The load cell 4 is fixedly installed on the bottom plate of the mounting groove by a support screw 403, and its top is in contact with the spherical surface of the support base 102 through a spherical contact pad 401 to ensure that the load is transmitted vertically, with a maximum allowable angle deviation of ±3°.

[0040] Specifically, in this embodiment of the invention, the top of the weighing sensor 4 is machined with an arc-shaped groove that matches the spherical contact pad 401. The spherical contact pad 401 is directly and movably supported in the arc-shaped groove. The mounting base 402 is machined with a rectangular mounting groove. The weighing sensor 4 is installed in the rectangular mounting groove, which can effectively protect the weighing sensor 4 on the one hand, and limit the spherical contact pad 401 on the other hand to prevent the spherical contact pad 401 from slipping off the sensor.

[0041] Furthermore, both the load cell 4 and the mounting base 402 are fixedly installed on the concrete foundation 103 by support screws 403. That is, the load cell 4 and the support base 102 are fixedly supported on the concrete foundation 103 together by the support screws 403. Preferably, the concrete foundation 103 is made of C30 concrete, which has a stiffness 3 to 5 times greater than that of the sensor. Each sensor is preferably fixed with 4 screws, and the pre-tightening force is controlled at a torque of 200 to 400 N·m. More preferably, it is equipped with triple anti-loosening measures: double nuts, spring washers, and thread-locking agent.

[0042] like Figure 5 As shown, in some further preferred embodiments, the weighing sensor system includes a three-stage adjustment mechanism: (1) a primary coarse adjustment mechanism: four support screws 403 are provided under each sensor for coarse adjustment; (2) a secondary intermediate adjustment mechanism: precision shims 405 of different specifications (e.g., 0.1mm, 0.2mm, 0.5mm) are provided for intermediate adjustment; and (3) a tertiary fine adjustment mechanism: i.e., a wedge adjustment mechanism 404. The three-stage adjustment mechanism ensures the accuracy of the sensor and protects it from continuous high-precision operation, thus extending its service life.

[0043] Specifically, such as Figure 6 As shown, the wedge adjustment mechanism 404 of this embodiment includes a fixed wedge 4041 and a movable wedge 4042. The fixed wedge 4041 is fixedly installed on the bottom of the weighing sensor 4, and the movable wedge 4042 is connected to the mounting base 402 and the concrete foundation 103 through a support screw 403. The top surface of the movable wedge 4042 and the fixed wedge 4041 are machined into wedge-shaped surfaces that cooperate with each other. More preferably, the inclination angle of the wedge-shaped surface is 3°±0.1°.

[0044] Combination Figure 7 , Figure 8 As shown, when no weighing is performed, the sensor is positioned at H1. When a billet is being weighed, the movable wedge 4042 moves forward under the influence of the force in the direction of motion. At this time, the bolt rotates, causing the sensor height to rise, resulting in higher accuracy. The maximum rotation angle of the bolt is 360°, at which point the sensor height is at its maximum. H2 = H1 + h, where h is the height the sensor rises when the bolt rotates 360°. H is preferably 0.02 mm. When the billet leaves the weighing roller, the movable wedge 4042 is subjected to a reaction force and returns to the unweighed state. The height adjustment calculation formula is: Where P is the screw pitch, specifically 1.25 mm in this embodiment; α is the wedge angle, i.e., the inclination angle of the wedge surface; The adjustment accuracy of the wedge-shaped adjustment mechanism 404 can reach 0.02mm, which is the screw rotation angle.

[0045] As a further preferred embodiment, the weighing sensor 4 is connected to the central control system 8 through a signal box 7. The signal box 7 is used to perform signal conditioning and A / D conversion on the data collected by the weighing sensor 4 and transmit it to the central control system 8.

[0046] Specifically, the signal box 7 incorporates a high-precision signal conditioning circuit and a 24-bit A / D conversion module, capable of amplifying, filtering, and digitizing the analog signals from the weighing sensor. As a preferred embodiment, the signal box 7 includes an anti-vibration filtering algorithm (an existing algorithm, not detailed here), effectively filtering out mechanical vibrations and bumps generated during roller conveyor operation, ensuring the stability and accuracy of the weighing data. More preferably, the signal box 7 adopts an industrial-grade protective design with an IP65 protection rating, enabling stable operation in harsh environments. Multiple signal boxes 7 can be configured as needed, forming a distributed signal processing system.

[0047] In some embodiments, the visual recognition system includes a first camera 5 and a second camera 6 respectively installed at the feed end and discharge end of the weighing roller conveyor 3, for real-time monitoring of the position of the billet on the weighing roller conveyor. The first camera 5 is used to acquire and process images of the billet at the feed end of the weighing roller conveyor 3 to determine whether the billet has completely entered the weighing area, thereby sending a weighing start signal to the central control system 8. The second camera 6 is used to acquire and process images of the billet at the discharge end of the weighing roller conveyor 3 to determine whether the billet has begun to leave the weighing area, thereby sending a weighing stop signal to the central control system 8.

[0048] Specifically, in this embodiment of the invention, both the first camera 5 and the second camera 6 are industrial-grade CCD cameras with a resolution of 3088×2064, a frame rate of 30fps, and are equipped with high-temperature filters, with an operating temperature range of -20℃ to +70℃. As a preferred installation method, the first camera 5 is installed 3 meters above the feeding end of the weighing roller conveyor 3, with a viewing angle of 15°~30°, preferably 15°; the second camera 6 is installed 3 meters above the discharging end of the weighing roller conveyor 3, with a viewing angle of 15°~30°, preferably 15°. The cameras are directly connected to the central control system 8 via Ethernet to transmit real-time image data.

[0049] As a further optimization, the first camera 5 and the second camera 6 are equipped with color recognition capabilities (the color recognition algorithm can be directly adopted from existing technologies, which will not be elaborated here), enabling them to identify castings of specific colors, such as red high-temperature castings. The cameras have built-in image processing chips that support real-time image processing with a processing latency of less than 50ms; and the lenses feature a zoom design with a focal length range of 8~50mm, which can be adjusted according to site conditions.

[0050] In some embodiments, the central control system 8 employs an industrial control computer, which controls the operation and shutdown of the weighing sensor system based on the recognition results of the visual recognition system, and processes the data collected by the weighing sensor system in real time. Furthermore, the central control system 8 integrates an image processing module, a data acquisition module, a communication module, and a human-machine interface module. The central control system 8 is connected to the signal box 7 via a Profibus-DP bus with a communication rate of 12Mbps; and to the camera via a gigabit Ethernet connection with a communication rate of 1000Mbps.

[0051] Signal transmission architecture: The analog signal from the weighing sensor 4 → signal box 7 (signal conditioning, A / D conversion) → central control system 8 (data processing, control decision); Digital image signals from the first camera 5 and the second camera 6 → Central control system 8 (image processing, location recognition); The advantages of this design architecture are: the signal box 7 undertakes signal conditioning and preliminary digital processing functions, which effectively improves signal quality and reduces noise interference during transmission; the camera is directly connected to the central control system 8, which reduces the transmission delay of image data and improves the real-time performance of visual recognition; the distributed signal processing architecture improves the reliability and maintainability of the system.

[0052] This embodiment also provides an online roller conveyor continuous weighing method for cast billets, combined with... Figure 1 As shown, using any of the above-mentioned continuous weighing devices, the specific steps include: S1, System initialization phase; Start the visual recognition system and weighing sensor system, and establish a communication connection with the central control system 8.

[0053] Specifically, this includes: the first camera 5 and the second camera 6 starting to work, performing image acquisition and processing system initialization; the weighing sensor 4 performing zero-point calibration to ensure measurement accuracy; the signal box 7 performing self-test to verify that the signal conditioning circuit and A / D conversion module are working properly; and the central control system 8 establishing data communication links with each subsystem and setting data acquisition parameters.

[0054] S2, Billet Inspection and Tracking Stage; The billet is conveyed by a conveyor roller, and the billet status on the conveyor roller is monitored in real time by a vision recognition system, which identifies the color characteristics and position information of the billet.

[0055] The rotational speed of the weighing rollers on the weighing roller conveyor 3 is set according to the production cycle requirements, usually 20~60 rpm. The billet 11 moves stably on the roller conveyor, and the preferred moving speed is 3.5 m / min.

[0056] The first camera 5 and the second camera 6 in the visual recognition system acquire the position information of the casting billet, and calculate the position coordinates of the casting billet in real time through image processing algorithms (specifically including but not limited to edge detection algorithms, contour detection algorithms, etc.). Furthermore, the image processing includes but is not limited to steps such as image enhancement, edge detection, contour extraction, and feature matching.

[0057] Specifically, the first camera 5 uses a color recognition algorithm to identify the outline features of the high-temperature red billet 11 through infrared imaging and visible light imaging functions; then the system establishes a billet movement trajectory model and calculates the billet's movement speed and position coordinates in real time.

[0058] S3, Weighing Start Judgment Stage When the first camera 5 located at the feeding end detects that the tail end of the billet 11 has completely landed on the weighing roller 3, the image processing algorithm determines the tail end boundary of the billet 11. After confirming that the tail end has completely entered the weighing area, the vision recognition system sends a weighing start signal to the central control system 8.

[0059] As a preferred implementation, the criterion for determining whether the tail end of the billet 11 has completely entered the weighing area is: the boundary of the tail end of the billet 11 exceeds the boundary line of the feed end of the weighing roller 3 by at least 50mm, so as to ensure that the billet 11 is completely free from the influence of the feed roller 2.

[0060] As a further optimization of this embodiment of the invention, the first camera 5 located at the feeding end identifies the red high-temperature billet through color recognition to ensure that the tail end of the billet completely enters the weighing area. Specifically, the color recognition adopts the HSV color space, and the red threshold range is set as follows: hue H value 160~180, saturation S value 100~255, and brightness V value 100~255.

[0061] S4, Data Acquisition Start-up Phase Upon receiving the weighing start signal, the central control system 8 immediately activates the weighing sensor system to begin data acquisition. The billet 11 continues to move normally along the weighing roller conveyor 3, maintaining its speed within the casting speed range. Simultaneously, the timestamp of the weighing start moment is recorded to provide a time reference for subsequent data processing.

[0062] S5, Continuous Weighing Data Acquisition Stage The weighing sensor system continuously collects weight data, which is then conditioned and converted by an A / D converter via signal box 7 before being transmitted to the central control system 8 for real-time processing and storage. As a further optimization, the sampling frequency of the weighing sensor system is 100Hz to ensure the continuity and accuracy of data acquisition; in this embodiment, the data acquisition accuracy is 0.1kg, and the weighing range is 0~20 tons.

[0063] The signal box 7 processes the collected weight data by amplifying, filtering and digitizing the original weighing signal, especially by using a bandpass filter to filter out low-frequency vibrations (1~5Hz) and high-frequency turbulence interference (above 50Hz) generated by the operation of the roller conveyor, so as to retain the effective weighing signal frequency band (5~50Hz).

[0064] Specifically, data from multiple weighing sensors 4 are fused and processed by signal box 7, and a Kalman filter algorithm is used to reduce the impact of local bumps on the overall weighing result to calculate the total weight. The central control system 8 monitors the stability of the data in real time and removes abnormal data points through a sliding window algorithm and an outlier detection algorithm; the processed weight data is stored in time series.

[0065] In this embodiment, the length of weighing roller conveyor 3 is calculated as follows: The roller conveyor length L is related to the key parameters of the weighing process in the following way: L = L cast +v × t + L0; in: L: Total length of weighing roller conveyor (m) refers to the total length of the same weighing roller 9 extending along the billet conveying direction; L cast : Length of cast billet (m); v: Casting speed (m / s); t: Total weighing time (s); L0: Safety margin length (m); The detailed calculation process for the safety margin length L0 is as follows: L0 = L a + L b + L c in: L a = n × d (n is the number of buffer rollers, d is the roller spacing); L b = v × t b (t) b (This refers to the system response time, typically taken as 0.1~0.2s). L c = 0.1 × Lcast (The safety factor is usually taken as 10% of the billet length). Specifically in this embodiment: (1) L a calculate: Roller spacing d = 1.0m; number of buffer roller conveyors n = 1; then L a = 1 × 1.0 = 1.0m; (2) L b calculate: System response time t b = 0.15s, billet casting speed v = 3.5m / min = 0.058m / s; then L b = 0.058 ×0.15 = 0.009m ≈ 0.01m; (3) L c calculate: billet length L cast = 12.0m, then L c = 0.1 × 12.0 = 1.2m; Therefore: L0 = 1.0 + 0.01 + 1.2 = 2.21m.

[0066] Basic calculation principle: From the moment the billet fully enters the weighing roller conveyor at the tail end to the moment the billet head contacts the end of the weighing roller conveyor, the length of the roller conveyor is L. Considering the system response time, roller conveyor buffering requirements, and measurement accuracy requirements, the design of the safety margin L0 must comprehensively consider multiple factors such as mechanical structure, control accuracy, and process safety.

[0067] Actual design parameters: Casting speed v: 3.5 m / min, Casting length L cast The weighing time is ≤ 7s; the safety margin L0 is 2.21, therefore the roller conveyor length L = 12.0 + 0.058 × 7 + 2.21 = 14.61 m. This embodiment uses L = 15m, which facilitates standardized design and is applicable to most working conditions.

[0068] S6. Weighing Completion Judgment Stage When the second camera 6 located at the discharge end detects that the head of the billet 11 contacts the end of the weighing roller conveyor 3, the system automatically stops weighing. Specifically, a position detection algorithm or a contour detection algorithm can be used for detection. In this embodiment of the invention, the head of the billet 11 is preferably identified accurately using a contour recognition algorithm to ensure the accuracy of the timing when weighing ends.

[0069] The specific criteria for determining the end of weighing are as follows: when the boundary of the billet head reaches the boundary line of the weighing roller conveyor discharge end, the vision recognition system sends a weighing end signal to the central control system 8 to ensure that the weighing process covers the entire length of the billet.

[0070] S7. Data Processing and Result Output Stage After synchronous acquisition, all weighing sensors 4 transmit analog signals to signal box 7. Signal box 7 conditions and converts the signals to A / D, then transmits them to central control system 8 via PROFIBUS-DP bus. The first camera 5 and the second camera 6 transmit image data directly to central control system 8 via Ethernet. Central control system 8 processes the data in real time, including signal filtering, data fusion, anomaly detection, and result calculation, and calculates the final weighing result (including billet weight, weighing time, weighing accuracy, etc.). This result can be displayed through a human-machine interface, stored in a database, and further transmitted to the upper-level system via network.

[0071] In some embodiments, it is further preferred to introduce a dynamic measurement window (i.e., a sliding window) and a weighted fusion algorithm when processing the collected weight data: the sliding window technique is used to balance casting speed and accuracy; as the billet moves, the data acquisition frequency and processing time need to be precisely controlled, and by setting the dynamic window length, it can be ensured that the data used in each calculation does not exceed the necessary window range. Simultaneously, the readings from different sensors are weighted and averaged based on the billet's position, speed, and sensor accuracy, thereby improving the accuracy of the measurement results. For example, sensors closer to the weighing area are given higher weights than those farther away.

[0072] Specifically, in this embodiment of the invention, the central control system 8 processes the collected weight data, including the following processing steps: S71, Data Preprocessing The data preprocessing includes filtering, specifically: using Kalman filtering to denoise the original data and eliminate environmental interference.

[0073] Furthermore, in this embodiment of the invention, the data preprocessing preferably includes three-stage filtering, the specific process of which is as follows: (1) First stage: Hardware filtering Analog low-pass filter with a cutoff frequency of 50Hz; Differential amplifier circuit, common-mode rejection ratio >120dB.

[0074] (2) Second stage: Digital pre-filtering To eliminate high-frequency random noise, a moving average filter is used. N is the window length, preferably 5; To remove impulse interference, median filtering is used. The data window of length 5 is sorted, and the median x(n) is taken. .

[0075] (3) Third stage: Adaptive Kalman filter The Kalman filter employs the state equation x(k+1) = Fx(k) + Gu(k) + ω(k) and the observation equation z(k) = Hx(k) + v(k). For a multi-sensor system, its state vector contains the weight estimates and rates of change of each sensor. The process noise covariance Q is set as a diagonal matrix diag([σ ω² , σ v² ]).

[0076] State-space model: State equation: x(k+1) = Fx(k) + Gu(k) + ω(k); The observation equation is z(k) = Hx(k) + v(k); State vector: x(k)=[W(k), dW / dt(k)] T ; Where W(k) is the weight of the billet, dW / dt(k) is the rate of change of weight, and ω(k) and v(k) are the process noise and observation noise, respectively. System matrix: ; Control matrix: ; Observation matrix: ; Noise covariance adaptive adjustment: Process noise covariance: Q = diag[σ ω 2 , σ v 2 ]; Observation noise covariance: R = σ r 2 ; Dynamic adjustment strategy: - High-speed drawing (v>4.5m / min): σ ω 2 = 0.01, σ v 2 = 0.001, σ r 2 = 0.05; - Low-speed drawing (v ≤ 4.5m / min): σ ω 2 = 0.1, σ v 2= 0.01, σ r 2 = 0.1; New sequence test: New information: ; In Kalman filtering, innovation refers to the difference between actual and predicted observations, representing the deviation of the system estimate from the observed values. It measures the inconsistency between the current prediction and observation, and is thus used to update the Kalman gain to correct the estimation of the system state. Indicates at time k The observation error.

[0077] New covariance: ; P Let represent the state estimation error covariance matrix, and let represent the uncertainty of the state estimation. This represents the covariance of the one-step prediction error.

[0078] Anomaly detection: Exception handling is triggered when the time is right.

[0079] The adaptive parameter tuning algorithm optimizes the Q and R parameters through grid search, within the Q range of 10. -4 ~10 0 R range 10 -3 ~10 1 Internal search selects the optimal parameter combination based on the mean squared error of the training data. Specifically for dual-sensor configurations on roller conveyors, correlation analysis between sensors is added to optimize the covariance matrix structure.

[0080] S72, Forecasting and Dynamic Adjustment Based on the casting speed, position, and historical data of the billet, the system makes predictions, estimating the billet's upcoming location and weight change trends. It automatically adjusts the window length and weight values ​​for data processing according to the billet's speed and weight. Fast-moving billets are calculated using a shorter processing window, while slower-moving billets use a longer window.

[0081] The window length calculation takes into account the billet throughput speed and the lateral spacing between adjacent roller conveyor sensors. Basic window length L base = ceil(S / (v×f s Where S is the sensor spacing between adjacent rollers (1~2m), v is the billet casting speed, and f s The sampling frequency.

[0082] In a typical configuration, the window length is 64–256 sampling points; more preferably, when v > 4.5 m / min, the window length is set to 64–128 sampling points; and when v ≤ 4.5 m / min, the window length is set to 128–256 sampling points. Since the sensor spacing between adjacent roller conveyors is 1–2 m, the sequential passing of the billet through each sensor introduces a time delay. Therefore, the algorithm employs timestamp alignment technology to spatially register the sensor data according to the billet position, achieving synchronous fusion processing.

[0083] Velocity correlation coefficient: k v = 1+μ×(vv ref ) / v ref ; Where μ is the adjustment coefficient (ranging from 0.1 to 0.3), v ref This is the reference speed, i.e., the theoretical value; Final window length: L window = L base × k v × k stability ; Stability coefficient: k stability = 1 + 0.2 × σ v / v mean ; Where: σ v v is the standard deviation of velocity. mean This represents the average speed.

[0084] S73, Data Fusion and Weighted Processing Data from different sensors is fused using a weighted averaging technique to ensure that each sensor's contribution in the calculation matches its location and accuracy. Simultaneously, the accuracy of the sensor data is ensured by comparing it in real time with the location information provided by the vision system. If inconsistencies are found, the system will adaptively correct them.

[0085] First, the data from the two sensors corresponding to the same weighing roller are internally fused, and the weighting coefficients are assigned taking into account the sensor position and the center of gravity of the billet: w front = (L rear / L total ); w rear = (L front / L total ); in, w front , w rearThese are the fusion weighting coefficients for the first sensor 4001 and the second sensor 4002 corresponding to the same weighing roller, respectively; L rear L front L represents the longitudinal distance L from the center of gravity of the billet to the second sensor 4002 and the first sensor 4001, respectively. total Let W be the longitudinal spacing between the two sensors, i.e., the weights of the first and second sensors are dynamically adjusted according to the position of the billet's center of gravity. Then, the fused weight W of the two weighing sensors corresponding to the i-th weighing roller is... i = First sensor reading × w front +Second sensor reading × w rear .

[0086] Example: Assuming the billet's center of gravity is 600mm from the front sensor and 400mm from the rear sensor, then: w front = 400 / (600+400) = 0.4; w rear = 600 / (600+400) = 0.6; The fused weight is calculated as: Front sensor reading × 0.4 + Rear sensor reading × 0.6.

[0087] Then, the sensor data between adjacent weighing rollers are fused using a recursive strategy, that is, the weights of each weighing roller are dynamically adjusted based on the billet coverage length: w i0 = Coverage i / Σ(Coverage j Coverage i Σ(Coverage) represents the coverage ratio of the cast billet on weighing roller i. j Let Σ(W) represent the sum of the coverage ratios of the billet on all weighing rollers; then the weight of the billet W0 = Σ(W i × w i0 ).

[0088] for example: (1) Time T1: The billet has just entered the weighing zone; - Weighing roller 1 covers 30%, its weight = 0.3 / 0.3 = 1.0; - Weighing rollers 2-4 are not covered, their weight = 0; (2) Time T2: The billet continues to advance; - Weighing roller 1 covers 100%, its weight = 1.0 / 2.5 = 0.4; - Weighing roller 2 covers 100%, its weight = 1.0 / 2.5 = 0.4; - Weighing roller 3 covers 50%, its weight = 0.5 / 2.5 = 0.2; - Weighing roller 4 is not covered, its weight = 0.

[0089] As a further preferred implementation, the weight of each weighing roller is assigned based on the weight of the cast billet. w i0 (i.e., the basic weights) are further optimized and adjusted. For heavy billets (≥10 tons), the weights of the intermediate sensors are increased and the weights of the edge sensors are reduced; while for light billets (<10 tons), the weights of each sensor are relatively balanced.

[0090] Specifically, in this embodiment of the invention, the weight correlation coefficient is: k w =1+β×(WW ref ) / W ref ; Where β is the adjustment coefficient (taken from 0.05 to 0.15); W ref The reference weight is the billet weight W0 predicted earlier using the basic weight.

[0091] Then: final weight w i = Base weight w i0 × k w ; The corrected weight of the cast billet is: W = Σ(W i × w i ).

[0092] S74, Output final weight data The weighing data, after being processed through multiple layers, will be sent to the central control system for display and processing, updating the weight information of the billet in real time, and outputting the final weight data.

[0093] In summary, this invention can precisely control the weighing timing based on real-time feedback from the visual recognition system, achieving continuous online weighing of cast billets to realize accurate weighing and improve production efficiency. Specifically, the first camera 5 is responsible for identifying the start of weighing, using an edge detection algorithm to identify the tail end of the cast billet; the second camera 6 is responsible for identifying the end of weighing, using a contour recognition algorithm to identify the head end of the cast billet. The detection accuracy of both cameras is better than ±5mm to ensure the accuracy of the weighing data.

[0094] Compared with existing technologies, the present invention can achieve the following technical effects: Weighing accuracy: The weighing accuracy reaches ±0.5%, meeting the requirements of industrial production. Compared with traditional static weighing, the accuracy can be improved by 20%.

[0095] Production efficiency: It can achieve continuous weighing without stopping the machine, increasing production efficiency by 35% and annual production capacity by about 15%.

[0096] Automation level: Fully automated operation, reducing operators by 60% and lowering labor costs.

[0097] Adaptability: Applicable to casting billets of different specifications, with cross-sectional dimensions from 150×150mm to 300×300mm and lengths of 6-12 meters.

Claims

1. An online roller conveyor type continuous weighing device for cast billets, characterized in that, include: The conveying roller system is used to convey the billet (11), and includes parallel multi-flow conveying rollers. Each flow conveying roller includes a feed roller (2), a weighing roller (3) and a discharge roller (10) arranged sequentially along the billet conveying direction. The weighing sensor system is installed below the weighing roller (3) and is used to weigh the billet (11) conveyed to the weighing roller (3). It includes several independent weighing units distributed at intervals along the billet conveying direction. Each weighing unit includes two weighing sensors (4) located below the same weighing roller (9) and close to the outer sides of its two ends, namely the first sensor (4001) and the second sensor (4002). A visual recognition system is used to acquire the movement trajectory of the billet during the conveying process through image acquisition and processing, so as to determine whether it is necessary to send a weighing start or stop signal; The system includes a central control system (8), which is connected to a visual recognition system and a weighing sensor system. The central control system (8) is used to receive visual recognition signals to control the start and stop of the weighing process, and to receive and process the weighing signals collected by the weighing sensor system to obtain the billet weighing results.

2. The online roller conveyor type continuous weighing device for cast billets according to claim 1, characterized in that, Each flow conveyor roller is installed and supported by a support frame, which includes a support base (102) distributed below each weighing roller (9) and extending along the length of the weighing roller (9), and two parallel roller beams (101) installed on the top of each support base (102) and extending along the conveying direction of the billet (11). The feed roller, weighing roller (9) and discharge roller on the flow conveyor roller are respectively rotatably installed between the two roller beams (101).

3. The online roller conveyor type continuous weighing device for cast billets according to claim 2, characterized in that, The weighing sensors (4) are all mounted on the bottom of the support frame via mounting bases (402), and their tops are in contact with the spherical surface of the support frame via spherical contact pads (401). The mounting base (402) is machined with a mounting groove for mounting and accommodating the weighing sensor (4). The weighing sensor (4) is mounted on the bottom plate of the mounting groove by a support screw (403), and the mounting base (402) together with the entire weighing device is fixedly installed on the concrete foundation (103) by the support screw (403).

4. The online roller conveyor type continuous weighing device for cast billets according to claim 3, characterized in that, The weighing sensor system includes a three-stage adjustment mechanism, which adjusts the installation height of the weighing sensor (4). Primary coarse adjustment mechanism: Four support screws (403) are symmetrically arranged below each load cell and connected to the mounting base (402) for coarse adjustment; Secondary adjustment mechanism: Equipped with precision gaskets (405) of different thicknesses for adjustment; Three-stage fine-tuning mechanism: This three-stage fine-tuning mechanism employs a wedge-shaped adjustment mechanism (404) for fine-tuning; The wedge adjustment mechanism (404) includes a fixed wedge (4041) and a movable wedge (4042) that cooperate with each other through wedge surfaces. The fixed wedge (4041) is fixedly installed on the bottom of the weighing sensor (4), and the movable wedge (4042) is connected to the mounting base (402) through a support screw (403).

5. The online roller conveyor type continuous weighing device for cast billets according to any one of claims 1-4, characterized in that, The weighing sensor (4) is connected to the central control system (8) through the signal box (7). The signal box (7) is used to perform signal conditioning and A / D conversion on the data collected by the weighing sensor (4) and transmit it to the central control system (8). The visual recognition system includes a first camera (5) and a second camera (6) installed at the feeding end and the discharging end of the weighing roller conveyor (3), respectively. The first camera (5) is used to collect and process images of the billet at the feeding end of the weighing roller conveyor (3) to determine whether the billet has completely entered the weighing area. The second camera (6) is used to collect and process images of the billet at the discharging end of the weighing roller conveyor (3) to determine whether the billet has started to leave the weighing area.

6. A method for continuous weighing of online roller conveyor billets, characterized in that, The online roller conveyor type continuous weighing device for cast billets according to any one of claims 1-5 includes the following steps: The billet (11) is conveyed by the conveyor rollers, and the status of the billet (11) on the conveyor rollers is monitored in real time by the vision recognition system to identify the color characteristics and position information of the billet; When the visual recognition system detects that the tail end of the billet (11) has completely entered the weighing area, it sends a weighing start signal to the central control system (8). The central control system (8) controls the weighing sensor system to start data acquisition, and the weighing sensor system transmits the collected weight data to the central control system (8) in real time. When the visual recognition system detects that the head of the billet (11) begins to leave the weighing area, it sends a weighing end signal to the central control system (8), and the weighing sensor system automatically stops weighing. After receiving the weighing data sent by the weighing sensor system, the central control system (8) processes the data in real time and calculates the final weighing result.

7. The online roller conveyor continuous weighing method for cast billets according to claim 6, characterized in that, After receiving the weighing data sent by the weighing sensor system, the central control system (8) processes the data in real time and calculates the final weighing result, specifically including: Data preprocessing: The repetitive data is preprocessed, including filtering. Prediction and dynamic adjustment: Based on the casting speed, position and historical data of the billet, the system makes predictions and estimates the upcoming position and weight change trend of the billet; Data fusion and weighted processing: Data from different weighing sensors are fused using a weighted averaging technique; Output final weight data: The weighing data after multiple layers of processing will be sent to the central control system for display and processing, updating the weight information of the billet in real time, and outputting the final weight data.

8. The online roller conveyor continuous weighing method for cast billets according to claim 7, characterized in that, In the prediction and dynamic adjustment step, the window length and weight value of the data processing are automatically adjusted based on the billet speed and weight. The window length calculation takes into account the billet's passing speed and the lateral spacing between adjacent roller conveyor sensors. The final window length is: L window =L base × k v × k stability ; in: Base window length L base :L base = ceil(S / (v×f s S is the sensor spacing between adjacent rollers, v is the billet casting speed, and f is the casting speed. s The sampling frequency; velocity correlation coefficient k v :k v = 1+μ×(vv ref ) / v ref μ is the adjustment coefficient, v ref This is the reference speed, i.e., the theoretical value; Stability coefficient k stability :k stability = 1 + 0.2 × σ v / v mean , σ v v is the standard deviation of velocity. mean This represents the average speed.

9. The online roller conveyor continuous weighing method for cast billets according to claim 7, characterized in that, The data fusion and weighting processing specifically includes: (1) Internally fuse the data of two weighing sensors corresponding to the same weighing roller, and the weighting coefficients are allocated considering the sensor position and the center of gravity of the billet: w front = (L rear / L total ); w rear = (L front / L total ); in, w front , w rear These are the fusion weighting coefficients for the first sensor (4001) and the second sensor (4002) corresponding to the same weighing roller, respectively; L rear L front L represents the longitudinal distance L from the center of gravity of the billet to the second sensor (4002) and the first sensor (4001), respectively. total Let W be the longitudinal distance between the two weighing sensors, then the fused weight W of the two weighing sensors corresponding to the i-th weighing roller is... i = First sensor reading × w front +Second sensor reading × w rear ; (2) The sensor data between adjacent weighing rollers adopts a recursive fusion strategy, that is, the weights of each weighing roller are dynamically adjusted based on the billet coverage length. w i0 : w i0 = Coverage i / Σ(Coverage j Coverage i Σ(Coverage) represents the coverage ratio of the cast billet on weighing roller i. j () represents the sum of the coverage ratios of the billet on all weighing rollers; Then the weight of the cast billet W0 = Σ(W i × w i0 ).

10. The online roller conveyor continuous weighing method for cast billets according to claim 9, characterized in that, The filtering process in the data preprocessing includes three levels of filtering: hardware filtering, digital pre-filtering, and adaptive Kalman filtering, wherein: The adaptive Kalman filter employs the state equation x(k+1) = Fx(k) + Gu(k) + ω(k) and the observation equation z(k) = Hx(k) + v(k). For a multi-sensor system, its state vector x(k) contains the weight estimates and rates of change of each sensor; F, G, and H are the system matrix, control matrix, and observation matrix, respectively; z(k) is the observation vector; ω(k) and v(k) are the process noise and observation noise, respectively; u(k) represents the control input or external influence of the system at time k; the process noise covariance Q is set as a diagonal matrix diag([σ ω² , σ v² ]); Observation noise covariance R = σ r 2 ; When fusing sensor data between adjacent weighing rollers, the weights of each weighing roller are assigned based on the weight of the cast billet. w i0 Adjustments are made to determine the final weight. w i = Base weight w i0 × k w ; Where, k w k is the weight correlation coefficient. w =1+β×(WW ref ) / W ref β is the adjustment coefficient; W ref For reference weight.

Images