Intelligent monitoring system for high-strength pellet production

Abstract

The invention belongs to the technical field of balling regulation and control in high-strength pellet production, and discloses an intelligent monitoring system for high-strength pellet production, which comprises a balling image acquisition module, a balling stage identification module, a balling disc rotating speed regulation and control module, a balling disc angle regulation and control module and a parameter dynamic regulation and control module. According to the method, whether the pelletizing stage of the target pellet production process is in the nucleation stage, the growth stage or the granulation stage is recognized based on the main body proportion green pellet diameter, stage recognition fuzziness is avoided, corresponding parameter control can be carried out for different stages, the pellet quality stability is improved, and the adaptability of the system is enhanced. According to the method, the pelletizing disc rotating speed regulation and control target value and the pelletizing disc angle regulation and control target value are dynamically constructed, then relevant parameter regulation and control are carried out, the production requirements can be accurately matched, the production efficiency is improved, the cost is reduced, and waste and equipment losses are reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of pelletizing control in high-strength pellet production and relates to an intelligent monitoring system for high-strength pellet production. Background Art

[0002] High-strength pellets are an iron-containing raw material with important application value in the metallurgical industry. The production process of high-strength pellets refers to the process of using a specific process to make iron-containing raw materials such as iron concentrate into spherical materials with a certain particle size, shape and high strength. It generally includes raw material preparation, batching, mixing, pelletizing, drying, roasting and other links.

[0003] The pelletizing stage is a critical step in the high-strength pelletizing process. This process directly impacts the initial strength of green pellets, and an efficient pelletizing process can increase green pellet yield. The pelletizing disk is a key piece of equipment used to transform powdered materials into spherical particles during the pelletizing process. Widely used in industries such as metallurgy and mineral processing, it plays a decisive role in pellet quality and production efficiency. Proper parameter settings for the disk optimize the pelletizing process, ensuring stable pellet quality, improving production efficiency, and reducing equipment wear and tear. Therefore, research on parameter monitoring and control during the pelletizing stage of high-strength pelletizing production is of great significance.

[0004] There are also technical solutions for monitoring and controlling parameters of the pelletizing process in the prior art. For example, a Chinese invention patent application with publication number CN105087910A is for a pelletizing control method and device, which includes obtaining the qualified raw ball flow rate WI1 and the unqualified raw ball flow rate WI2; calculating the pelletizing rate rb of the pelletizing ore based on WI1 and WI2; and adjusting the given disc watering amount FI_Water, the given disc rotation speed SI_TURN, and the given disc inclination angle SI_ANGLE according to the preset strategy based on the said pelletizing rate rb.

[0005] In addition, a Chinese invention patent application with publication number CN119287155A is for a method for improving the ball-forming performance of laboratory vanadium-titanium pellets. The method comprises using a pelletizing disk and sieve commonly used in the laboratory to screen out mother balls with a particle size of 10 to 12.5 mm as qualified vanadium-titanium pellets. The pellets obtained by this method are uniform in size, and their raw and cooked compressive strength, drop strength performance and yield are superior to those of conventional pelletizing methods. The performance of the pellets fully meets the requirements of experimental research and can accurately control the experimental objectives.

[0006] Although the above two schemes have proposed some solutions for monitoring and controlling the parameters of the pelletizing process, there are still certain limitations. For example, the adjustment of the given disc water spraying amount, given disc speed, and given disc inclination angle according to the preset strategy mentioned in Scheme 1 can improve the quality of the pelletizing stage to a certain extent, but its dynamic adjustment process has low adaptability and cannot accurately perform dynamic analysis and control on the relevant parameters of the actual pelletizing process, thereby reducing the production efficiency and quality of the pelletizing process.

[0007] Option 2 mentions obtaining qualified green balls through multiple screenings. Although this method ensures that the corresponding particle size and related process parameters of the green balls obtained are close to the required quality, it sacrifices the continuity of the production process, requires multiple screening and analysis, lacks adaptive ball-forming stage analysis, and reduces the efficiency of ball-making. Summary of the Invention

[0008] In view of this, in order to solve the problems of mismatch in dynamic parameter control and low pelletizing efficiency proposed in the above background technology, an intelligent monitoring system for high-intensity pellet production is proposed.

[0009] The purpose of the present invention can be achieved through the following technical solutions: An intelligent monitoring system for high-intensity pellet production, including: a pelletizing image acquisition module, which is used to use an image acquisition device to collect real-time time-series images of each production process of the target pellet based on a preset acquisition frequency.

[0010] The pelletizing stage identification module is used to extract scale features based on the time-series images of the production process to obtain the main proportion of raw ball diameters, and then identify the pelletizing stage of the target pellet production process and obtain the corresponding suitable pelletizing disk rotation speed and suitable pelletizing disk angle. The pelletizing stage includes the nucleation stage, the growth stage and the pelletizing stage.

[0011] The pelletizing disk speed control module is used to process the production time series images to generate the apparent defects of the raw balls and the degree of deviation of the waterfall area shape, and at the same time use the online pressure monitoring equipment to obtain the degree of deviation of the compressive strength of the raw balls, and combine it with the appropriate speed of the pelletizing disk to construct the target value of the pelletizing disk speed control.

[0012] The ball-making disk angle control module is used to analyze the centrifugal motion vector of the raw balls in the production process time series image through the optical flow method, evaluate the degree of deviation of the raw balls' centrifugal ejection direction, and combine it with the appropriate angle of the ball-making disk to construct the target value of the ball-making disk angle control.

[0013] The parameter dynamic control module is used to control the relevant parameters of the target turntable according to the pelletizing disk speed control target value and the pelletizing disk angle control target value.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention avoids stage identification ambiguity by identifying whether the target pellet production process is in the nucleation stage, growth stage or whole-grain stage based on the main body proportion of raw pellet diameter, and can perform corresponding parameter control for different stages, thereby improving the stability of pellet quality and enhancing the adaptability of the system.

[0015] (2) The present invention dynamically constructs the target value for controlling the rotation speed of the pelletizing disk and the target value for controlling the angle of the pelletizing disk, and then controls the relevant parameters, which can accurately match production needs, improve production efficiency, reduce costs, and reduce waste and equipment loss.

[0016] (3) The present invention comprehensively identifies the demand for speed control of the pelletizing disk by analyzing the surface defects of the raw balls, the degree of deviation of the shape of the waterfall area, and the degree of deviation of the compressive strength of the raw balls. It can accurately locate production problems and adjust the speed in time according to different problems, thereby ensuring efficient and stable pellet production.

[0017] (4) The present invention evaluates the degree of deviation of the centrifugal ejection direction of the raw balls and then identifies the need for angle control of the pelletizing disk, thereby avoiding the problems of scattering, collision and breakage of the raw balls due to the deviation of the ejection direction, ensuring the integrity and quality of the pellets, and making the material distribution in the pelletizing disk more uniform, thereby improving the pelletizing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 This is a schematic diagram of the connection of various modules of the system of the present invention.

[0020] Figure 2 A schematic diagram of the angle of the pelletizing disk corresponding to an embodiment is provided.

[0021] Figure 3 A schematic diagram of the sequence of ball-forming stages corresponding to an embodiment is provided.

[0022] Figure numerals: 1 - pelletizing disk, 2 - pelletizing disk angle. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] See also Figure 1 As shown, the present invention provides an intelligent monitoring system for high-intensity pellet production, including a pelletizing image acquisition module, a pelletizing stage identification module, a pelletizing disk speed control module, a pelletizing disk angle control module and a parameter dynamic control module, wherein the balling image acquisition module is connected to the balling stage identification module, the balling stage identification module is respectively connected to the balling disk speed control module and the balling disk angle control module, and the balling disk speed control module and the balling disk angle control module are both connected to the parameter dynamic control module.

[0025] The pelletizing image acquisition module is used to use an image acquisition device to acquire real-time sequential images of each production process of the target pellet based on a preset acquisition frequency.

[0026] It's important to explain that the core task of this module is to visually monitor the entire green ball production process within the ball-forming tray using an image acquisition device (such as an industrial camera). The captured image sequences (time-series images) are then used to analyze key parameters such as green ball size distribution, surface defects, and motion trajectory.

[0027] The ball forming stage identification module is used to extract scale features based on the time-series images of the production process to obtain the main proportion of raw ball diameters, and then identify the ball forming stage of the target pellet production process and obtain the corresponding suitable ball forming disk rotation speed and suitable ball forming disk angle. The ball forming stage includes the nucleation stage, the growth stage and the pelletizing stage.

[0028] In a preferred embodiment of the present invention, the specific analysis method of the main body proportion of the raw ball diameter is as follows: extract the time-series images of each production process of the target pellet, use image processing software to obtain the diameter of each raw ball corresponding to each production process time-series image, match each raw ball diameter with a pre-set raw ball diameter-balling stage comparison relationship, obtain the balling stage of each raw ball, and statistically obtain the number of raw balls corresponding to each balling stage.

[0029] In one embodiment, see Figure 3 As shown, the relationship between the raw ball diameter and the ball formation stage is as follows: nucleation stage (raw ball diameter <3mm), growth stage (3mm≤raw ball diameter≤10mm), and grain formation stage (raw ball diameter >10mm).

[0030] Compare the number of raw balls in each ball-forming stage, sum up the number of raw balls in other ball-forming stages except the ball-forming stage corresponding to the maximum number of raw balls to obtain the total non-maximum raw ball amount, compare the maximum number of raw balls with the total non-maximum raw ball amount, if the maximum number of raw balls is greater than or equal to the total non-maximum raw ball amount, calculate the mean of the raw ball diameters in the ball-forming stage corresponding to the maximum number of raw balls to obtain the raw ball diameter corresponding to the main proportion of the time series image of each production process.

[0031] If the maximum number of raw balls is less than the total number of non-maximum raw balls, the raw ball diameters of each ball-forming stage are averaged to obtain the raw ball diameters that account for the main proportion of the time series images of each production process.

[0032] The main proportion of green ball diameter in the target pellet production process is obtained by calculating the mean of the main proportion of green ball diameter in the time series images of each production process.

[0033] It should be noted that the above process dynamically determines the diameter of the majority of raw balls by statistically analyzing the distribution of raw balls. Its core logic is to determine the dominant state of the current production stage based on quantitative dominance. This method can dynamically adapt to production fluctuations and accurately reflect the characteristics of the production stage, ensuring that the majority diameter accurately reflects the core characteristics of the current production stage, providing a scientific basis for identifying the ball formation stage and adjusting ball-making parameters.

[0034] In a feasible embodiment, data analysis is performed on the above process, and the results are as follows.

[0035] Table 1 Corresponding original data of an example of analysis of the diameter of a main body ball

[0036] stage quantity Average green ball diameter Nucleation period 20 2 Growth period 60 6 Whole grain stage 20 13

[0037] According to the above original data, the maximum number of green balls is 60, the total number of non-maximum green balls is 40, and the maximum number of green balls is greater than the total number of non-maximum green balls. Therefore, the diameter of the main green balls is 6, and the corresponding ball formation stage is the growth period.

[0038] In a preferred embodiment of the present invention, the specific process of identifying the ball-forming stage of the target pellet production process is as follows: matching the raw ball diameter of the main proportion of the target pellet production process with the pre-set raw ball diameter-ball-forming stage comparison relationship, thereby taking the ball-forming stage into which the raw ball diameter of the main proportion of the target pellet production process falls as the ball-forming stage of the target pellet production process.

[0039] Specifically, if the raw ball diameter of the main body is within the raw ball diameter range corresponding to the nucleation period, the pelletizing stage of the target pellet production process is identified as the nucleation period.

[0040] If the main proportion of raw ball diameters falls within the range of raw ball diameters corresponding to the growing stage, the pelletizing stage of the target pellet production process is identified as the growing stage.

[0041] If the main proportion of raw ball diameter belongs to the raw ball diameter range corresponding to the whole pellet stage, then the pelletizing stage of the target pellet production process is identified as the whole pellet stage.

[0042] It should be noted that the present invention avoids ambiguity in stage identification by identifying whether the target pellet production process is in the nucleation stage, growth stage or particle size stage based on the main proportion of raw pellet diameter, and can perform corresponding parameter control for different stages, thereby improving the stability of pellet quality and enhancing the adaptability of the system.

[0043] The pelletizing disk speed control module is used to process the production time series images to generate the apparent defects of the raw balls and the degree of deviation of the waterfall area shape, and at the same time use the online pressure monitoring equipment to obtain the degree of deviation of the compressive strength of the raw balls, and combine it with the appropriate speed of the pelletizing disk to construct the pelletizing disk speed control target value.

[0044] In a preferred embodiment of the present invention, the specific method of generating the apparent defect situation of the raw balls is as follows: using image processing software to obtain the apparent defect area and apparent surface area of each raw ball in the time-series images of each production process, and then performing a ratio calculation to obtain the ratio of the apparent defect area of each raw ball in the time-series images of each production process.

[0045] It should be noted that the production process time sequence image is an image of the interior of the pelletizing disk at a certain moment in the target green pellet production process, and the image contains several green pellets.

[0046] The average of the apparent defect area ratio of each green ball in the time series images of each production process is calculated to obtain the green ball apparent defect evaluation index corresponding to the target pellet production process.

[0047] The green ball surface defect evaluation index is used to evaluate the severity of green ball surface defects.

[0048] It's important to explain that as green balls move faster within the ball-forming disc, collision frequency and intensity increase, which can easily lead to surface defects such as cracks and pits. When the green ball surface defect evaluation index is high, the module will reduce the rotational speed (for example, by 2 rpm) to minimize collisions and mitigate defects. Rotational speed is a key parameter influencing green ball surface defects, and the two are negatively correlated. By monitoring the defect area ratio in real time and dynamically adjusting the rotational speed, the defect rate can be effectively reduced, ensuring green ball quality.

[0049] In a preferred embodiment of the present invention, the specific analysis method of the degree of deviation of the waterfall area shape is as follows: using high-definition image processing software to obtain the ejection point and landing point of each raw ball corresponding to the time-series image of each production process, and then obtain the length of the waterfall area corresponding to each raw ball.

[0050] The deviation between the waterfall area length of each raw ball in the time series image of each production process and the preset appropriate waterfall area length is calculated, and then normalized and averaged, and the waterfall area shape deviation index of the target pellet production process is obtained by analysis.

[0051] In a feasible embodiment, the waterfall shape deviation index of the target pellet production process is analyzed as follows: using the formula The waterfall shape deviation index Γ of the target pellet production process is obtained by analysis, where i represents the number of the production process time series image, i = 1, 2...I, I represents the number of the production process time series images, j represents the number of the raw ball, j = 1, 2...J, J represents the number of the raw balls, L ij It represents the length of the waterfall area corresponding to the jth raw ball in the time series image of the i-th production process, and L0 represents the preset appropriate waterfall area length.

[0052] The waterfall area shape deviation index is used to evaluate the degree of waterfall area shape deviation.

[0053] It should be explained that the correlation mechanism between the rotation speed of the ball making disk and the deviation degree of the waterfall area shape is as follows: 1. The rotation speed directly affects the shape of the waterfall area: the centrifugal force of the ball increases, the ejection speed increases, and the length of the waterfall area L ij If the desired length L0 is exceeded, the waterfall deviation index Γ will be negative, triggering control (e.g., reducing the rotation speed by 1-2 rpm). If the centrifugal force is insufficient, the ball trajectory will be abnormal, shortening the waterfall length, and the shape may become an irregular parabola or clumping. If the waterfall deviation index Γ is positive, the rotation speed will need to be increased by 0.5-1 rpm.

[0054] 2. Too high or too low a rotational speed will cause the waterfall length to deviate from the preset value, triggering regulation. By calculating the shape deviation index in real time and dynamically adjusting the rotational speed, the material projection trajectory can be optimized to ensure the quality of the raw balls.

[0055] In a preferred embodiment of the present invention, the specific analysis method of the deviation degree of the green ball compressive strength is as follows: the compressive strength of each tested green ball is obtained by using an online pressure monitoring device, and the difference and mean analysis of the pre-set expected compressive strength and the compressive strength of each tested green ball is performed to obtain the green ball compressive strength deviation index of the target pellet production process.

[0056] Exemplary, a method for analyzing the deviation index of the compressive strength of green balls: using online pressure monitoring equipment to obtain the compressive strength of each tested green ball, performing difference calculation between a preset expected compressive strength and the compressive strength of each tested green ball to obtain the compressive strength deviation of each tested green ball, and then performing ratio calculation with the preset expected compressive strength to obtain the green ball compressive strength deviation index of each tested green ball, and performing average calculation on the green ball compressive strength deviation index of each tested green ball to obtain the green ball compressive strength deviation index of the target pellet production process.

[0057] The green ball compressive strength deviation index is used to evaluate the degree of deviation of the green ball compressive strength.

[0058] It needs to be explained that if the rotation speed is too low, the probability of green balls sticking together increases, the structure becomes loose, and the compressive strength decreases. Therefore, the rotation speed needs to be increased by 0.5-1rpm to enhance the compactness of the green balls.

[0059] In a preferred embodiment of the present invention, the specific analysis method for constructing the target value of the pelletizing disk speed control is as follows: extract the green ball apparent defect evaluation index, waterfall area shape deviation index and green ball compressive strength deviation index of the target pellet production process, multiply them with the preset reference unit speed correction amount respectively, and then sum them to obtain the pelletizing disk speed control amount.

[0060] It should be noted that the reference unit speed correction is determined based on multiple factors. The production process determines the base speed. Raw ball quality indicators such as defects and compressive strength deviation are key, and speed adjustment is based on these factors to ensure quality. Equipment and raw material characteristics also have an impact, with larger disks and coarser-grained raw materials requiring different speeds. Furthermore, corrections are determined based on historical production data, experimental research, and online monitoring feedback to ensure the disk speed aligns with production needs and stabilizes raw ball quality.

[0061] The pelletizing stage of the target pelletizing production process is matched with the pre-set pelletizing stage-pelletizing disk suitable parameter comparison relationship to obtain the suitable speed of the pelletizing disk in the current pelletizing stage.

[0062] The speed control value of the pelletizing disk is calculated by summing the speed control amount of the pelletizing disk and the appropriate speed of the pelletizing disk to obtain the speed control target value of the pelletizing disk.

[0063] It should be noted that the present invention analyzes the surface defects of the raw balls, the degree of deviation of the waterfall area shape and the degree of deviation of the compressive strength of the raw balls, comprehensively identifies the demand for speed control of the pelletizing disk, can accurately locate production problems, and adjust the speed in time according to different problems, thereby ensuring efficient and stable pellet production.

[0064] See also Figure 2As shown, the ball-making disk angle control module is used to analyze the centrifugal motion vector of the raw balls in the production process time series image through the optical flow method, evaluate the degree of deviation of the raw balls' centrifugal projection direction, and combine it with the appropriate angle of the ball-making disk to construct the target value of the ball-making disk angle control.

[0065] In a preferred embodiment of the present invention, the specific evaluation method of the deviation degree of the centrifugal ejection direction of the green ball is as follows: the trajectory of each green ball in the time series image of each production process of the target pellet is tracked by the optical flow method to obtain the instantaneous velocity vector of each pellet

[0066] It should be noted that the optical flow method is a method that uses the information about the change in pixel intensity over time in an image sequence to calculate the motion of an object. During the production process of target pellets, the optical flow method is applied to each time-series image to track the position changes of each raw ball at different times. Based on these position changes, the instantaneous velocity vector of each raw ball on a two-dimensional plane (set as the xy plane) can be calculated. represents the instantaneous velocity vector of the j-th pellet, v j,x is the instantaneous velocity component of the pellet in the x direction, v j,y is the instantaneous velocity component in the y direction.

[0067] The friction coefficient between the material and the disk surface and the radius of the ball-making disk are obtained, and the current angle and speed of the ball-making disk are obtained in real time, and then the theoretical centrifugal projection direction and the corresponding angle are analyzed based on the theory of object motion.

[0068] Based on the instantaneous velocity vector analysis of each pellet, the corresponding centrifugal projection direction angle of each pellet is analyzed, and then the deviation analysis is performed on the angle corresponding to the theoretical centrifugal projection direction, and then the deviation index of the centrifugal projection direction of each raw ball is obtained after normalization, and then the centrifugal projection direction deviation index of the raw ball in the target pellet production process is obtained by averaging calculation.

[0069] In a feasible embodiment, the specific calculation method of the green ball centrifugal projection direction deviation index in the target pellet production process is as follows: using the formula The green ball centrifugal ejection direction deviation index Δφ of the target pellet production process is constructed, where θ0 represents the angle corresponding to the theoretical centrifugal ejection direction, Where μ represents the preset friction coefficient between the material and the disk surface, R represents the radius of the ball-making disk, α represents the current angle of the ball-making disk, g represents the acceleration of gravity, and v0 represents the current speed of the ball-making disk.

[0070] It is necessary to further explain the specific construction logic of the above formula: 1. Theoretical modeling: Determine the ideal projectile direction θ0, in the formula The physical meaning is: the theoretical projectile angle when the centrifugal force and friction force are balanced.

[0071] Centrifugal force component μ×v0 2 ×cosα: Determined by the angle α and the friction coefficient μ, it reflects the centrifugal tendency of the material on the disc surface.

[0072] Gravitational component: g is used as a reference to balance the effect of centrifugal force on the direction of projection.

[0073] Geometric meaning: θ0 is the angle between the projectile direction of the ball and the tangent of the disk surface caused by the balance of centrifugal force and friction under ideal conditions.

[0074] 2. Positive deviation (Δφ>0): The actual projection direction is steeper than the theoretical direction, indicating that the centrifugal force is too strong (the angle is too large).

[0075] Negative deviation (Δφ<0): The actual projection direction is flat, indicating insufficient friction (angle is too small).

[0076] A feasible embodiment is to perform data simulation calculation based on the raw ball centrifugal projection direction deviation index analysis formula to obtain the corresponding simulation calculation results. Some simulation results can be referred to Table 1, where μ = 0.5, R = 1m, α = π / 4, g = 9.81m / s 2 , and J=5 is preset, and for the convenience of calculation, the v of the data simulation process j,x =v j,y ,

[0077] Table 2. Simulation results of deviation index of centrifugal projection of some green balls

[0078]

[0079] The simulation results above show the following: 1. θ0 is the angle corresponding to the theoretical centrifugal projection direction, calculated based on the friction coefficient between the material and the disk surface, the disk radius, angle, gravitational acceleration, and disk speed. As v0 (disk speed) increases, θ0 also increases. This is because increasing speed increases the centrifugal force acting on the material, thereby changing the theoretical projection angle.

[0080] 2. Δφ is the green ball centrifugal ejection direction deviation index, reflecting the degree of deviation of the actual ejection direction from the theoretical ejection direction. The results show that when v0 is small, the Δφ value is large, indicating that at lower rotational speeds, the actual ejection direction deviates significantly from the theoretical direction. As v0 increases, the Δφ value decreases, meaning that at higher rotational speeds, the actual ejection direction approaches the theoretical direction. This index is of great significance for controlling green ball ejection direction and improving pellet production quality during target pellet production. The index can be used to adjust the operating parameters of the pelletizing disk.

[0081] The green ball centrifugal projection direction deviation index is used to evaluate the degree of green ball centrifugal projection direction deviation in a target pellet production process.

[0082] In a preferred embodiment of the present invention, the specific method of constructing the target value of the pelletizing disk angle control is as follows: extract the deviation index of the centrifugal ejection direction of the raw balls in the target pellet production process, and then multiply it by the preset unit correction value of the pelletizing disk angle to obtain the pelletizing disk angle control value.

[0083] The target value of the angle control of the ball-making disk is obtained by performing a difference calculation between the suitable angle of the ball-making disk and the angle control value of the ball-making disk.

[0084] It should be noted that the present invention evaluates the degree of deviation in the centrifugal ejection direction of the raw balls and then identifies the need for angle control of the pelletizing disk, thereby avoiding problems such as scattering, collision and breakage of the raw balls due to the deviation in the ejection direction, ensuring the integrity and quality of the pellets, and making the material distribution in the pelletizing disk more uniform, thereby improving the pelletizing efficiency.

[0085] The parameter dynamic control module is used to control the relevant parameters of the target turntable according to the pelletizing disk speed control target value and the pelletizing disk angle control target value.

[0086] In a preferred embodiment of the present invention, the specific method of regulating the relevant parameters of the target turntable is as follows: extracting the target value for controlling the speed of the ball-making disk and the target value for controlling the angle of the ball-making disk, and then comparing them with the pre-set allowable range of the speed of the ball-making disk and the allowable range of the angle of the ball-making disk, respectively.

[0087] It's important to note that the pelletizing disk's allowable speed range is the speed range required for normal equipment operation and guaranteed pellet quality. It's typically 10-14 rpm, but this varies depending on various factors. Equipment performance limits the upper speed limit to prevent component overload and malfunction. Material properties significantly influence this, for example, high speeds are not suitable for materials with fine particle size or high moisture content, as they can easily be thrown off the pellets. Furthermore, to meet pellet quality requirements, inappropriate speeds can lead to uneven pellet size and poor strength. Taking all of these factors into account, a reasonable speed range ensures efficient and stable equipment operation and high-quality pellet production. The allowable angle range for the pelletizing disk refers to the appropriate angle between the disk and the horizontal plane, typically between 40° and 45°. This angle directly affects the material's residence time: a larger angle results in a shorter residence time, while a smaller angle results in a longer residence time. The appropriate angle is crucial to pellet quality. The angle also determines the material's rolling trajectory. A proper angle ensures a stable spiral rise, which promotes compact pellets. From an equipment perspective, a too large angle shifts the center of gravity and compromises stability, while a too small angle impairs material flow. Therefore, a suitable angle range is crucial for equipment stability and optimal pelletizing results.

[0088] If the target value of the pelletizing disk speed control is within the allowable range of the pelletizing disk speed, the target value of the pelletizing disk speed control is used as the benchmark for speed control. Otherwise, the boundary value that is closer to the target value of the pelletizing disk speed control is used as the benchmark for speed control.

[0089] It should be noted that this control step calculates the target values of the rotation speed and angle of the pelletizing disk in real time, and combines this with the preset safe operating range to ensure that the parameter adjustment meets the process optimization requirements without exceeding the physical limitations of the equipment. The specific logic is: first, based on the raw ball quality indicators (defects, strength, projection direction, etc.), the target values of the rotation speed and angle are dynamically generated; then these target values are compared with the pre-set allowable range (such as rotation speed 10-14rpm, angle 40°-45°); if the target value is within the allowable range, it is directly adopted; if it exceeds the range, the closest boundary value is selected as the control benchmark. This strategy combines safety boundary constraints with dynamic optimization to get as close to the ideal process state as possible while ensuring the stable operation of the equipment, thereby achieving a balance between raw ball quality and production efficiency.

[0090] It's important to explain that when the calculated target speed or angle exceeds the preset allowable range during pelletizing disc control, the system will select the closest boundary value to the target as the actual control reference. For example, if the allowable speed range is 10-14 rpm and the control target is 15 rpm, 14 rpm (a difference of 1 rpm) will be selected instead of 10 rpm (a difference of 5 rpm).

[0091] The allowable angle range is 40°-45°. If the control target value is 38°, select 40° (difference 2°) instead of 45° (difference 7°).

[0092] It should be noted that by comparing the absolute difference between the target value and the upper and lower limits, the boundary value corresponding to the smaller value is taken. This strategy maximizes the process optimization effect while ensuring the safe operation of the equipment, and avoids the reduction of pelletizing efficiency due to excessive restrictions.

[0093] The angle control is performed similarly.

[0094] It should be added that if the target value of the angle control of the ball-making disk is within the allowable range of the angle of the ball-making disk, the target value of the angle control of the ball-making disk will be used as the benchmark for angle control. Otherwise, the boundary value that is closer to the target value of the angle control of the ball-making disk will be used as the benchmark for angle control.

[0095] It should be noted that the present invention dynamically constructs the target value for controlling the speed of the pelletizing disk and the target value for controlling the angle of the pelletizing disk, and then controls the relevant parameters, which can accurately match production needs, improve production efficiency, reduce costs, and reduce waste and equipment loss.

[0096] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. An intelligent monitoring system for high-strength pellet production, characterized in that: include: A pelletizing image acquisition module is used to acquire real-time sequential images of each production process of the target pellets using an image acquisition device based on a preset acquisition frequency; A pelletizing stage identification module is used to extract scale features based on the time-series images of the production process to obtain the main proportion of raw ball diameters, thereby identifying the pelletizing stage of the target pellet production process and obtaining the corresponding appropriate pelletizing disk rotation speed and angle. The pelletizing stage includes the nucleation stage, the growth stage, and the pelletizing stage. The pelletizing disk speed control module is used to process the production time series images to generate the apparent defects of the raw balls and the degree of deviation of the waterfall area shape. At the same time, it uses the online pressure monitoring equipment to obtain the degree of deviation of the raw ball compressive strength, and combines this with the appropriate speed of the pelletizing disk to construct the target value for the pelletizing disk speed control; The ball-forming disk angle control module is used to analyze the centrifugal motion vector of the raw balls in the production process time series image through the optical flow method, evaluate the degree of deviation of the raw balls' centrifugal projection direction, and combine it with the appropriate angle of the ball-forming disk to construct the target value for the angle control of the ball-forming disk; The parameter dynamic control module is used to control the relevant parameters of the target turntable according to the pelletizing disk speed control target value and the pelletizing disk angle control target value.

2. The intelligent monitoring system for high-strength pellet production according to claim 1, characterized in that: The specific analysis method of the main body ratio of the green ball diameter is as follows: Extract the time series images of each production process of the target pellets, use image processing software to obtain the diameter of each raw ball corresponding to each production process time series image, match each raw ball diameter with the pre-set raw ball diameter-balling stage correspondence, obtain the balling stage of each raw ball, and statistically obtain the number of raw balls corresponding to each balling stage; Compare the number of raw balls in each ball-forming stage, sum the number of raw balls in other ball-forming stages except the ball-forming stage corresponding to the maximum raw ball number to obtain the total number of non-maximum raw balls, compare the maximum raw ball number with the total number of non-maximum raw balls, and if the maximum raw ball number is greater than or equal to the total number of non-maximum raw balls, calculate the mean of the raw ball diameters of each raw ball in the ball-forming stage corresponding to the maximum raw ball number to obtain the raw ball diameter corresponding to the main proportion of each production process time series image; If the maximum number of raw balls is less than the total number of non-maximum raw balls, the raw ball diameters of each ball-forming stage are averaged to obtain the raw ball diameters of the main body of the time series image of each production process; The mean value of the main proportion of green ball diameters in the time series images of each production process is calculated to obtain the main proportion of green ball diameters in the target pellet production process.

3. The intelligent monitoring system for high-strength pellet production according to claim 2, characterized in that: The specific process of identifying the pelletizing stage of the target pellet production process is as follows: The raw ball diameter of the main proportion of the production process of the target pellets is matched with the pre-set raw ball diameter--balling stage comparison relationship, thereby taking the balling stage into which the raw ball diameter of the main proportion of the production process of the target pellets falls as the balling stage of the target pellet production process.

4. The intelligent monitoring system for high-strength pellet production according to claim 1, characterized in that: The specific method for generating the apparent defects of the green balls is as follows: Image processing software is used to obtain the apparent defect area and apparent surface area of each raw ball in the time series images of each production process, and then the ratio is calculated to obtain the apparent defect area ratio of each raw ball in the time series images of each production process; The average of the apparent defect area ratio of each green ball in the time series images of each production process is calculated to obtain the green ball apparent defect evaluation index corresponding to the target pellet production process.

5. The intelligent monitoring system for high-strength pellet production according to claim 4, characterized in that: The specific analysis method of the degree of deviation of the waterfall shape is as follows: Use high-definition image processing software to obtain the ejection point and landing point of each raw ball corresponding to the time-series images of each production process, and then obtain the length of the waterfall area corresponding to each raw ball; The deviation between the waterfall area length of each raw ball in the time series image of each production process and the preset appropriate waterfall area length is calculated, and then normalized and averaged, and the waterfall area shape deviation index of the target pellet production process is obtained by analysis.

6. The intelligent monitoring system for high-strength pellet production according to claim 5, characterized in that: The specific analysis method of the deviation degree of the green ball compressive strength is as follows: The compressive strength of each test green ball is obtained by using online pressure monitoring equipment. The difference and mean analysis between the preset expected compressive strength and the compressive strength of each test green ball is performed to obtain the green ball compressive strength deviation index of the target pellet production process.

7. The intelligent monitoring system for high-strength pellet production according to claim 6, characterized in that: The specific analysis method for constructing the target value of the ball-making disk speed control is as follows: Extract the green ball surface defect evaluation index, waterfall area shape deviation index and green ball compressive strength deviation index of the target pellet production process, multiply them with the preset reference unit speed correction value respectively, and then sum them to obtain the pelletizing disk speed control value; The pelletizing stage of the target pelletizing production process is matched with the pre-set pelletizing stage-pelletizing disk suitable parameter comparison relationship to obtain the suitable speed of the pelletizing disk in the current pelletizing stage; The speed control value of the pelletizing disk is calculated by summing the speed control amount of the pelletizing disk and the appropriate speed of the pelletizing disk to obtain the speed control target value of the pelletizing disk.

8. The intelligent monitoring system for high-strength pellet production according to claim 1, characterized in that: The specific evaluation method of the deviation degree of the centrifugal projection direction of the green ball is as follows: The trajectory of each raw ball in the time series images of each production process of the target pellet is tracked by the optical flow method to obtain the instantaneous velocity vector of each pellet; Obtain the friction coefficient between the material and the disk surface and the radius of the ball-making disk, and at the same time obtain the current angle and speed of the ball-making disk in real time, and then analyze the theoretical centrifugal projection direction and corresponding angle based on the theory of object motion; Based on the instantaneous velocity vector analysis of each pellet, the corresponding centrifugal projection direction angle of each pellet is analyzed, and then the deviation analysis is performed on the angle corresponding to the theoretical centrifugal projection direction, and then the deviation index of the centrifugal projection direction of each raw ball is obtained after normalization, and then the centrifugal projection direction deviation index of the raw ball in the target pellet production process is obtained by averaging calculation.

9. The intelligent monitoring system for high-strength pellet production according to claim 8, characterized in that: The specific method of constructing the target value of the angle control of the ball-making disk is as follows: Extract the green ball centrifugal ejection direction deviation index in the target pellet production process, and then multiply it with the pre-set pelletizing disk angle unit correction value to obtain the pelletizing disk angle control value; The target value of the angle control of the ball-making disk is obtained by performing a difference calculation between the suitable angle of the ball-making disk and the angle control value of the ball-making disk.

10. The intelligent monitoring system for high-strength pellet production according to claim 1, characterized in that: The specific method of regulating the relevant parameters of the target turntable is as follows: Extract the target value of the pelletizing disk speed control and the target value of the pelletizing disk angle control, and then compare them with the preset allowable range of the pelletizing disk speed and the allowable range of the pelletizing disk angle respectively; If the target value of the pelletizing disk speed control is within the allowable range of the pelletizing disk speed, the target value of the pelletizing disk speed control is used as a benchmark for speed control. Otherwise, the boundary value that is closer to the target value of the pelletizing disk speed control is used as a benchmark for speed control. The angle control is performed similarly.

Images