An intelligent detection system for alumina production

Abstract

The present invention relates to the technical field of alumina production detection, and particularly to an intelligent detection system for alumina production. The present invention is provided with a pre-analysis unit, a feature recognition unit, and a detection and analysis unit. The collection tank for collecting spherical alumina is divided into several collection areas by the pre-analysis unit, and the stacking parameters of the spherical alumina are obtained to determine the heat flow disturbance category of the collection area. The disturbance characteristic factors of each collection area are selected by the feature recognition unit, and the disturbance characteristic factors include the alumina particle size value determined based on the surface image of the spherical alumina, or the spacing of several feature points calculated based on the stacking shape curve of the spherical alumina. The detection and analysis unit determines whether there is an abnormality in alumina production according to the disturbance characteristic factors. Furthermore, during the alumina production process, the thermal distribution state in the furnace is monitored in a timely manner, and the selection method of the detection parameters of the spherical alumina is adaptively adjusted, improving the detection accuracy and efficiency of alumina production.

Description

Technical Field

[0001] The present invention relates to the technical field of alumina production detection, and in particular to an intelligent detection system for alumina production. Background Art

[0002] As a key basic industrial raw material, alumina occupies an extremely important position in the national economic system. With the vigorous development of emerging industries such as 5G communications, artificial intelligence, and new energy vehicles, spherical alumina has excellent performance in fluidity, filling and heat dissipation performance due to its unique spherical structure. It is widely used in emerging industries. The demand for high-performance spherical alumina has shown explosive growth, prompting spherical alumina manufacturers to improve the production accuracy of spherical alumina. However, the traditional production process often relies on manual experience to detect the accuracy of spherical alumina, and it is difficult to perform real-time detection of the entire production process. It cannot meet the production process detection needs after the expansion of production scale and the increase of process complexity, affecting the production accuracy and efficiency of alumina. Therefore, real-time monitoring of the alumina production process, timely adjustment of monitoring strategies, and improvement of the production accuracy and efficiency of alumina are technical issues that need to be solved urgently.

[0003] For example, Chinese patent application publication number: CN115308247A, the invention discloses a method for detecting the quality of aluminum oxide powder slag removal, including, obtaining a triangular facet data set of an aluminum oxide sample; the coordinates of each vertex of each target triangular facet in the triangular facet data set constitute the feature vector of the target triangular facet; obtaining the particle size radius discreteness and the non-spherical suspicion of adjacent triangular facets; inputting the feature vectors of all target triangular facets and the non-spherical suspicion of all triangular facets adjacent to each target triangular facet into an impurity detection network, and outputting the classification result of the target triangular facet corresponding to an aluminum oxide sample in combination with the number of aggregation times of the feature vector; and evaluating the quality of the aluminum oxide after slag removal by using the number of triangular facets belonging to impurities in the classification results of the target triangular facets corresponding to multiple aluminum oxide samples sampled multiple times. The invention can shorten the detection time of impurities in aluminum oxide and improve the detection efficiency.

[0004] The prior art still has the following problems:

[0005] The prior art does not take into account that when the alumina powder is flame-melted, the thermal distribution in the furnace will be different, thereby affecting the spherical state of the alumina powder. During the alumina production process, the prior art cannot timely monitor the thermal distribution state in the furnace, and cannot adaptively adjust the selection method of the detection parameters of spherical alumina, which affects the detection efficiency and detection accuracy of alumina production. Summary of the invention

[0006] To this end, the present invention provides an intelligent detection system for alumina production, which is used to overcome the problems in the prior art that, during the alumina production process, the thermal distribution state in the furnace cannot be monitored in time, and the selection method of the detection parameters of spherical alumina cannot be adaptively adjusted, thereby affecting the detection efficiency and detection accuracy of alumina production.

[0007] To achieve the above object, the present invention provides an intelligent detection system for alumina production, comprising:

[0008] A pre-analysis unit, which is used to divide the collection tank for collecting the spherical aluminum oxide formed by spheroidization into a plurality of collection areas, obtain the stacking parameters of the spherical aluminum oxide in each collection area in a preset monitoring period, and determine the thermal flow disturbance category of the collection area according to the comparison of the plurality of stacking parameters;

[0009] A feature recognition unit connected to the pre-analysis unit, for selecting disturbance feature factors of each collection area according to the heat flow disturbance category, wherein the disturbance feature factors include alumina particle size values ​​determined based on a surface image of spherical alumina, or spacings between a plurality of adjacent feature points calculated based on a stacking morphology curve of spherical alumina;

[0010] Wherein, the characteristic points are determined according to the height values ​​of the spherical aluminum oxide at several points on the stacking morphology curve in the direction perpendicular to the horizontal plane;

[0011] A detection and analysis unit is respectively connected to the pre-analysis unit and the feature recognition unit, and is used to determine the melting difference characterization quantity of the collection area according to the alumina particle size value and to determine whether there is an abnormality in the current alumina production according to the comparison between several melting difference characterization quantities, or to determine whether there is an abnormality in the current alumina production according to the comparison between several spacings.

[0012] Furthermore, the pre-analysis unit is used to obtain the stacking parameters of the spherical aluminum oxide in each collection area, wherein:

[0013] The pre-analysis unit obtains the spherical aluminum oxide height values ​​at a plurality of points in the collection area during a preset monitoring period, and determines an average value of the plurality of spherical aluminum oxide height values ​​as the stacking parameter of the collection area.

[0014] Furthermore, the pre-analysis unit is also used to determine the thermal flow disturbance category of the collection area, wherein:

[0015] If the stacking parameters of the collection area meet the first disturbance determination condition, the pre-analysis unit determines the heat flow disturbance category of the collection area as the first heat flow disturbance category;

[0016] If the stacking parameters of the collection area do not meet the first disturbance determination condition, the pre-analysis unit determines the heat flow disturbance category of the collection area as the second heat flow disturbance category;

[0017] The first disturbance determination condition is that the stacking parameter does not exceed a preset stacking reference value.

[0018] Furthermore, the feature recognition unit is used to select disturbance feature factors of each collection area, wherein:

[0019] If the thermal flow disturbance category is the first thermal flow disturbance category, the feature recognition unit selects the disturbance characteristic factor as the aluminum oxide particle size value determined based on the surface image of the spherical aluminum oxide;

[0020] If the thermal flow disturbance category is the second thermal flow disturbance category, the feature recognition unit selects the disturbance feature factor as the distance between a plurality of adjacent feature points calculated based on the stacking morphology curve of spherical aluminum oxide.

[0021] Furthermore, the feature recognition unit is used to determine a stacking morphology curve, wherein:

[0022] The feature recognition unit obtains the surface profile curves of the spherical aluminum oxide in several cross-sectional directions of the collection tank in the collection area, calculates the height difference value of the surface profile curve in the direction perpendicular to the horizontal plane according to the maximum value point of the surface profile curve, and determines the surface profile curve corresponding to the maximum value of the height difference value as the stacking morphology curve;

[0023] The cross-sectional direction of the collecting groove is perpendicular to the axial direction of the collecting groove.

[0024] Furthermore, the feature recognition unit is also used to determine feature points, wherein:

[0025] The feature recognition unit calculates the height values ​​of a plurality of data points on the stacked shape curve in a direction perpendicular to the horizontal plane, and calculates a height average value according to the height values ​​of the plurality of data points;

[0026] If the data point on the stacked shape curve meets the characteristic point determination condition, the characteristic recognition unit determines the data point as the characteristic point;

[0027] The characteristic point determination condition is that the height value corresponding to the data point exceeds the height average value.

[0028] Furthermore, the detection and analysis unit is used to determine the melting difference characterization value of the collection area, wherein:

[0029] The detection and analysis unit calculates the particle size variance according to the alumina particle size values ​​of a plurality of spherical aluminas in the collection area, and determines the particle size variance as a melting difference characterization value of the collection area.

[0030] Furthermore, the detection and analysis unit is used to determine the comparison between several melting difference characterization quantities, wherein:

[0031] The detection and analysis unit obtains melting difference characterization quantities of a plurality of first heat flow disturbance category collection areas, and determines the difference between the maximum value of the melting difference characterization quantity and the minimum value of the melting difference characterization quantity as the melting risk characterization value.

[0032] Furthermore, the detection and analysis unit is also used to determine whether there is any abnormality in the current alumina production, wherein:

[0033] If the melting difference characterization value and the melting risk characterization value do not meet the normal melting judgment condition, the detection and analysis unit determines that there is an abnormality in the current alumina production;

[0034] If the comparison of several intervals of the stacking morphology curve does not meet the normal stacking judgment conditions, the detection and analysis unit determines that there is an abnormality in the current aluminum oxide production.

[0035] Furthermore, the normal melting judgment condition is that the melting difference characterization value does not exceed the preset melting abnormality characterization reference value, and the melting risk characterization value does not exceed the preset melting risk characterization reference value;

[0036] The stacking normal judgment condition is that the variance of a plurality of intervals does not exceed a preset variance threshold.

[0037] Compared with the prior art, the beneficial effect of the present invention lies in that a pre-analysis unit, a feature recognition unit, and a detection and analysis unit are provided in the present invention. The collection tank for collecting spherical alumina formed by spheroidization is divided into several collection areas by the pre-analysis unit, the stacking parameters of the spherical alumina in each collection area are obtained in a preset monitoring period, the heat flow disturbance category of the collection area is determined according to the comparison of several stacking parameters, and the disturbance characteristic factors of each collection area are selected according to the heat flow disturbance category by the feature recognition unit. The disturbance characteristic factors include the alumina particle size value determined based on the surface image of the spherical alumina, or the spacing between several adjacent feature points calculated based on the stacking morphology curve of the spherical alumina. The detection and analysis unit determines the melting difference characterization amount of the collection area according to the alumina particle size value and determines whether there is an abnormality in the current alumina production according to the comparison between several melting difference characterization amounts, or determines whether there is an abnormality in the current alumina production according to the comparison of several spacings. Therefore, it is realized that in the process of alumina production, the thermal distribution state in the furnace is monitored in time, and the selection method of the detection parameters of spherical alumina is adaptively adjusted, thereby improving the detection efficiency and detection accuracy of alumina production.

[0038] In particular, the present invention determines the type of heat flow disturbance in the collection area by comparing several stacking parameters. It can be understood that due to the temperature difference, air flow movement will occur. Hot air with a small density will move upward, while cold air with a large density will move downward. Since the temperature at the edge of the alumina furnace is lower than that in the center of the furnace, air flow movement will occur in the alumina furnace. In the area where the hot air rises, the spherical alumina has a stronger lifting effect, so that the spherical alumina in this area falls relatively slowly. In the same monitoring period, the stacking height of the spherical alumina is relatively low, and in the edge area of ​​the furnace, the spherical alumina is relatively stable. The airflow moves relatively downward, the falling rate of the spherical alumina is relatively fast, and the stacking height is relatively high within the same monitoring period. The stacking parameter is the average value of the height values ​​of the spherical alumina at several points in the collection area. By comparing the stacking parameters in different collection areas, the stacking conditions of the spherical alumina in different areas can be intuitively understood, thereby judging the uniformity of the thermal distribution. The present invention determines the type of heat flux disturbance in the collection area according to the comparison of several stacking parameters, and further, realizes timely monitoring of the thermal distribution state in the furnace during the alumina production process, thereby improving the detection efficiency and detection accuracy of alumina production.

[0039] In particular, the present invention selects the disturbance characteristic factor as the alumina particle size value determined based on the surface image of spherical alumina for the collection area of ​​the first heat flow disturbance category. It can be understood that the temperature of the hot air flow rising area in the alumina furnace is relatively high, and the alumina powder will stay in this area for a long time due to the action of the hot air flow. If the alumina powder stays for too long, it will be over-melted. Over-melting will cause some particles to fuse with each other, or due to excessive heating, internal gas will escape and change the structure, resulting in irregular shape of the molten alumina, so that the alumina particle size in the collection area is inconsistent. The collection area of ​​the first heat flow disturbance category is the hot air flow rising area. The alumina particle size value in this area is prone to fluctuate due to over-melting. The present invention determines the alumina particle size value based on the surface image of spherical alumina in the hot air flow rising area, thereby determining the degree of difference in alumina particle size in the collection area. Furthermore, in the alumina production process, timely monitoring of the thermal distribution state in the furnace is achieved, and the selection method of the detection parameters of spherical alumina is adaptively adjusted, thereby improving the detection efficiency and detection accuracy of alumina production.

[0040] In particular, the present invention selects the disturbance characteristic factor as the distance between several adjacent characteristic points calculated based on the stacking morphology curve of spherical alumina for the collection area of ​​the second heat flow disturbance category. It can be understood that in the area where the airflow moves relatively downward in the furnace, the residence time of the alumina powder in this area is relatively short, which can easily cause incomplete melting of the alumina powder. The incompletely melted alumina is in a semi-solid and semi-liquid transition state. During the collection process, the alumina will be further cooled. Since the temperature gradient between the inside and the surface of the incompletely melted alumina is large, the cooling and solidification speeds are inconsistent, and internal stress will be generated during the solidification process. This internal stress will cause the particles to squeeze each other, increasing the possibility of adhesion, and the stacking morphology curve The stacking morphology of spherical alumina in this area can be intuitively displayed. The characteristic point is the point where the height value of alumina perpendicular to the horizontal plane is larger. Alumina with a larger height value has a higher risk of height abnormality due to adhesion. The calculated spacing of the characteristic points can characterize the distance between alumina with a higher risk of adhesion. The present invention selects the disturbance characteristic factor for the collection area of ​​the second heat flux disturbance category as the spacing of several adjacent characteristic points calculated based on the stacking morphology curve of spherical alumina, thereby achieving timely monitoring of the thermal distribution state in the furnace during the alumina production process, adaptively adjusting the selection method of the detection parameters of spherical alumina, and improving the detection efficiency and detection accuracy of alumina production.

[0041] In particular, the present invention determines whether there is an abnormality in the current alumina production through the melting difference characterization value and the melting risk characterization value. It can be understood that the melting difference characterization value is the variance of several alumina particle sizes in the collection area. In the spherical alumina production process, the obtained spherical alumina particle size should be relatively consistent, and the larger the melting difference characterization value, the larger the variance of several alumina particle sizes, and the greater the discreteness of each spherical alumina particle size in the characterization area, that is, the more obvious the difference in particle size, and the current alumina production is abnormal. The melting risk characterization value is the difference between the maximum and minimum values ​​of the variance in several regions. The discreteness of alumina particle sizes in the collection area under the same heat flux disturbance category should be relatively consistent, and the larger the melting risk characterization value, the more significant the difference in particle size in different regions, and the current alumina production is abnormal. The present invention determines whether there is an abnormality in the current alumina production through the melting difference characterization value and the melting risk characterization value, and further, realizes timely monitoring of the thermal distribution state in the furnace during the alumina production process, adaptively adjusts the selection method of the detection parameters of spherical alumina, and improves the detection efficiency and detection accuracy of alumina production.

[0042] In particular, the present invention determines whether there is an abnormality in the current alumina production based on the comparison of several spacings. It can be understood that the spherical alumina is in the form of a smooth sphere. Normal spherical alumina can achieve regular stacking so that the spacing between surface protrusions is roughly the same, while adhesion will cause the originally standard spherical alumina to become an irregular shape. When the adhered spherical alumina is stacked, due to its irregular shape, the adhered spheres may contact and stack each other at various angles and in various ways, resulting in the formation of gaps of different sizes and shapes at different positions, thereby causing differences in the spacing between surface feature points, and failing to achieve a regular stacking arrangement. The larger the spacing variance, the greater the difference in spacing between the feature points, the more significant the adhesion of the spherical alumina, and the current alumina production has an abnormality. The present invention determines whether there is an abnormality in the current alumina production through the comparison of several spacings, and further, realizes timely monitoring of the thermal distribution state in the furnace during the alumina production process, adaptively adjusts the selection method of the detection parameters of the spherical alumina, and improves the detection efficiency and accuracy of alumina production. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a functional block diagram of an intelligent detection system for alumina production according to an embodiment of the present invention;

[0044] Figure 2 A logic flow chart for determining the thermal flow disturbance category of a collection area by a pre-analysis unit according to an embodiment of the present invention;

[0045] Figure 3 A logic flow chart of the disturbance characteristic factors selected by the characteristic recognition unit of the embodiment of the present invention for each collection area;

[0046] Figure 4 This is a logic flow chart of the detection and analysis unit of an embodiment of the present invention for determining whether there is any abnormality in the current alumina production. DETAILED DESCRIPTION

[0047] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0049] It should be noted that, in the description of the present invention, terms such as "upper", "lower", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0050] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] See also Figure 1 As shown, it is a functional block diagram of an intelligent detection system for aluminum oxide production according to an embodiment of the present invention. An intelligent detection system for aluminum oxide production according to the present invention comprises:

[0052] A pre-analysis unit, which is used to divide the collection tank for collecting the spherical aluminum oxide formed by spheroidization into a plurality of collection areas, obtain the stacking parameters of the spherical aluminum oxide in each collection area in a preset monitoring period, and determine the thermal flow disturbance category of the collection area according to the comparison of the plurality of stacking parameters;

[0053] Specifically, the size of the collection area can be set by those skilled in the art according to the actual size of the collection tank. Preferably, when the size of the collection tank is 2m×2m, the size of the collection area can be 10cm×10cm.

[0054] Specifically, the preset monitoring period can be set by those skilled in the art according to the detection accuracy requirements of alumina production. Preferably, the preset monitoring period can be 6 hours after the collection of spherical alumina begins.

[0055] Specifically, the present invention does not specifically limit the structure of the pre-analysis unit. Preferably, it can be implemented by a laser ranging sensor in conjunction with a microprocessor, the laser ranging sensor is used to obtain the height value of the spherical aluminum oxide in the collection area, the microprocessor is used to divide the collection area, and the stacking parameters and the thermal flow disturbance category of the collection area are determined. No further details are given here.

[0056] A feature recognition unit connected to the pre-analysis unit, for selecting disturbance feature factors of each collection area according to the heat flow disturbance category, wherein the disturbance feature factors include alumina particle size values ​​determined based on a surface image of spherical alumina, or spacings between a plurality of adjacent feature points calculated based on a stacking morphology curve of spherical alumina;

[0057] Wherein, the characteristic points are determined according to the height values ​​of the spherical aluminum oxide at several points on the stacking morphology curve in the direction perpendicular to the horizontal plane;

[0058] Specifically, the present invention does not specifically limit the structure of the feature recognition unit. Preferably, it can be implemented by an industrial camera in conjunction with a processor used in a computer. The surface image of spherical alumina is acquired by the industrial camera, and the alumina particle size value and the stacking morphology curve are determined based on the edge algorithm. The disturbance characteristic factors of each collection area are selected by the processor used in the computer, which will not be repeated here.

[0059] A detection and analysis unit is respectively connected to the pre-analysis unit and the feature recognition unit, and is used to determine the melting difference characterization quantity of the collection area according to the alumina particle size value and to determine whether there is an abnormality in the current alumina production according to the comparison between several melting difference characterization quantities, or to determine whether there is an abnormality in the current alumina production according to the comparison between several spacings.

[0060] Specifically, the present invention does not specifically limit the structure of the detection and analysis unit. Preferably, it can be a field programmable logic component for determining whether there is an abnormality in the current alumina production based on the comparison between the melting difference characterization quantity and a plurality of melting difference characterization quantities, and determining whether there is an abnormality in the current alumina production based on the comparison of a plurality of intervals, which will not be elaborated here.

[0061] Specifically, the pre-analysis unit is used to obtain the stacking parameters of the spherical aluminum oxide in each collection area, wherein:

[0062] The pre-analysis unit obtains the spherical aluminum oxide height values ​​at a plurality of points in the collection area during a preset monitoring period, and determines an average value of the plurality of spherical aluminum oxide height values ​​as the stacking parameter of the collection area.

[0063] Specifically, here is a specific embodiment for determining the stacking parameters, and the height values ​​of spherical alumina at 10 points in the collecting area are 12.5cm, 13.2cm, 11.8cm, 12.9cm, 13.5cm, 12.1cm, 12.7cm, 13cm, 11.6cm, and 12.4cm, respectively. The average height value of the spherical alumina is 12.57cm, that is, the stacking parameter of the current collecting area is 12.57cm.

[0064] Specifically, see Figure 2 As shown, it is a logic flow chart of the pre-analysis unit determining the thermal flow disturbance category of the collection area in an embodiment of the present invention. The pre-analysis unit is also used to determine the thermal flow disturbance category of the collection area, wherein:

[0065] If the stacking parameters of the collection area meet the first disturbance determination condition, the pre-analysis unit determines the heat flow disturbance category of the collection area as the first heat flow disturbance category;

[0066] If the stacking parameters of the collection area do not meet the first disturbance determination condition, the pre-analysis unit determines the heat flow disturbance category of the collection area as the second heat flow disturbance category;

[0067] The first disturbance determination condition is that the stacking parameter does not exceed a preset stacking reference value.

[0068] Specifically, the preset stacking reference value can be set by technical personnel in this field according to the detection accuracy requirements of alumina production. The higher the accuracy requirement, the smaller the preset stacking reference value. Preferably, the stacking reference value can be 20 cm.

[0069] Specifically, the present invention determines the type of heat flow disturbance in the collection area by comparing several stacking parameters. It can be understood that due to the temperature difference, air flow movement will occur. Hot air with low density will move upward, while cold air with high density will move downward. Since the temperature at the edge of the alumina furnace is lower than that in the center of the furnace, air flow movement will occur in the alumina furnace. In the area where the hot air flow rises, the spherical alumina has a stronger lifting effect, so that the spherical alumina in this area falls relatively slowly. In the same monitoring period, the stacking height of the spherical alumina is relatively low, and the temperature at the edge of the furnace is lower than that at the center of the furnace. The air flow in the domain moves relatively downward, the falling rate of the spherical alumina is relatively fast, and the stacking height is relatively high within the same monitoring period. The stacking parameter is the average value of the height values ​​of the spherical alumina at several points in the collection area. By comparing the stacking parameters in different collection areas, the stacking conditions of the spherical alumina in different areas can be intuitively understood, thereby judging the uniformity of the thermal distribution. The present invention determines the type of heat flux disturbance in the collection area according to the comparison of several stacking parameters, and further, realizes timely monitoring of the thermal distribution state in the furnace during the alumina production process, thereby improving the detection efficiency and detection accuracy of alumina production.

[0070] Specifically, see Figure 3 As shown, it is a logic flow chart of the feature recognition unit selecting the disturbance feature factors of each collection area according to an embodiment of the present invention. The feature recognition unit is used to select the disturbance feature factors of each collection area, wherein:

[0071] If the thermal flow disturbance category is the first thermal flow disturbance category, the feature recognition unit selects the disturbance characteristic factor as the aluminum oxide particle size value determined based on the surface image of the spherical aluminum oxide;

[0072] If the thermal flow disturbance category is the second thermal flow disturbance category, the feature recognition unit selects the disturbance feature factor as the distance between a plurality of adjacent feature points calculated based on the stacking morphology curve of spherical aluminum oxide.

[0073] Specifically, the present invention selects the disturbance characteristic factor as the alumina particle size value determined based on the surface image of spherical alumina for the collection area of ​​the first heat flow disturbance category. It can be understood that the temperature of the hot air flow rising area in the alumina furnace is relatively high, and the alumina powder will stay in this area for a long time due to the action of the hot air flow. If the alumina powder stays for too long, it will be over-melted. Over-melting will cause some particles to fuse with each other, or due to excessive heating, internal gas will escape and change the structure, resulting in irregular shape of the molten alumina, so that the alumina particle size in the collection area is inconsistent. The collection area of ​​the first heat flow disturbance category is the hot air flow rising area. The alumina particle size value in this area is prone to fluctuate due to over-melting. The present invention determines the alumina particle size value based on the surface image of spherical alumina in the hot air flow rising area, thereby determining the degree of difference in alumina particle size in the collection area. Furthermore, in the alumina production process, timely monitoring of the thermal distribution state in the furnace is achieved, and the selection method of the detection parameters of spherical alumina is adaptively adjusted, thereby improving the detection efficiency and detection accuracy of alumina production.

[0074] Specifically, the feature recognition unit is used to determine the stacking morphology curve, wherein:

[0075] The feature recognition unit obtains the surface profile curves of the spherical aluminum oxide in several cross-sectional directions of the collection tank in the collection area, calculates the height difference value of the surface profile curve in the direction perpendicular to the horizontal plane according to the maximum value point of the surface profile curve, and determines the surface profile curve corresponding to the maximum value of the height difference value as the stacking morphology curve;

[0076] The cross-sectional direction of the collecting groove is perpendicular to the axial direction of the collecting groove.

[0077] Specifically, the feature recognition unit is also used to determine feature points, wherein:

[0078] The feature recognition unit calculates the height values ​​of a plurality of data points on the stacked shape curve in a direction perpendicular to the horizontal plane, and calculates a height average value according to the height values ​​of the plurality of data points;

[0079] If the data point on the stacked shape curve meets the characteristic point determination condition, the characteristic recognition unit determines the data point as the characteristic point;

[0080] If the data point on the stacked shape curve does not meet the characteristic point determination condition, the characteristic recognition unit does not screen the data point;

[0081] The characteristic point determination condition is that the height value corresponding to the data point exceeds the height average value.

[0082] Specifically, a specific embodiment for determining feature points is given here. The height values ​​of several data points on the stacked morphology curve in the direction perpendicular to the horizontal plane are: point 1 is 22.1 cm, point 2 is 25.8 cm, point 3 is 20.9 cm, point 4 is 28.7 cm, point 5 is 29.4 cm, point 6 is 23.1 cm, point 7 is 21 cm, point 8 is 27.1 cm, point 9 is 24 cm, and point 10 is 26.3 cm. The average height is 24.84. The points whose height values ​​exceed the average height are point 2, point 4, point 5, point 8, and point 10. Therefore, the feature points are point 2, point 4, point 5, point 8, and point 10.

[0083] Specifically, the present invention selects the disturbance characteristic factor as the distance between several adjacent characteristic points calculated based on the stacking morphology curve of spherical alumina for the collection area of ​​the second heat flux disturbance category. It can be understood that in the area where the airflow moves relatively downward in the furnace, the residence time of the alumina powder in this area is relatively short, which can easily cause incomplete melting of the alumina powder. The incompletely melted alumina is in a semi-solid and semi-liquid transition state. During the collection process, the alumina will further cool down. Since the temperature gradient between the inside and the surface of the incompletely melted alumina is large, the cooling and solidification speeds are inconsistent, and internal stress will be generated during the solidification process. This internal stress will cause the particles to squeeze each other, increasing the possibility of adhesion and the stacking morphology curve. The line can intuitively show the stacking morphology of spherical alumina in this area. The characteristic point is the point where the height value of alumina perpendicular to the horizontal plane is larger. Alumina with a larger height value has a higher risk of height abnormality due to adhesion. The calculated spacing of the characteristic points can characterize the distance between alumina with a higher risk of adhesion. The present invention selects the disturbance characteristic factor for the collection area of ​​the second heat flux disturbance category as the spacing of several adjacent characteristic points calculated based on the stacking morphology curve of spherical alumina, thereby achieving timely monitoring of the thermal distribution state in the furnace during the alumina production process, adaptively adjusting the selection method of the detection parameters of spherical alumina, and improving the detection efficiency and detection accuracy of alumina production.

[0084] Specifically, the detection and analysis unit is used to determine the melting difference characterization quantity of the collection area, wherein:

[0085] The detection and analysis unit calculates the particle size variance according to the alumina particle size values ​​of a plurality of spherical aluminas in the collection area, and determines the particle size variance as a melting difference characterization value of the collection area.

[0086] Specifically, a specific embodiment of determining the melting difference characterization quantity is given here. The alumina particle size values ​​of 10 spherical aluminas in the collection area are 82μm, 78μm, 85μm, 79μm, 81μm, 83μm, 77μm, 84μm, 80μm, and 76μm, respectively, and the particle size variance is 8.2, that is, the melting difference characterization quantity of the current collection area is 8.2.

[0087] Specifically, the detection and analysis unit is used to determine the comparison between several melting difference characterization quantities, wherein:

[0088] The detection and analysis unit obtains melting difference characterization quantities of a plurality of first heat flow disturbance category collection areas, and determines the difference between the maximum value of the melting difference characterization quantity and the minimum value of the melting difference characterization quantity as the melting risk characterization value.

[0089] Specifically, see Figure 4 As shown, it is a logic flow chart of the detection and analysis unit of the embodiment of the present invention for determining whether there is an abnormality in the current aluminum oxide production. The detection and analysis unit is also used to determine whether there is an abnormality in the current aluminum oxide production, wherein:

[0090] If the melting difference characterization value and the melting risk characterization value do not meet the normal melting judgment condition, the detection and analysis unit determines that there is an abnormality in the current alumina production;

[0091] If the comparison of several intervals of the stacking morphology curve does not meet the normal stacking judgment condition, the detection and analysis unit determines that there is an abnormality in the current alumina production;

[0092] If the melting difference characterization value and the melting risk characterization value meet the normal melting judgment conditions, and the comparison of several intervals of the stacking morphology curve meets the normal stacking judgment conditions, the detection and analysis unit determines that there is no abnormality in the current alumina production.

[0093] Specifically, the normal melting judgment condition is that the melting difference characterization value does not exceed the preset melting abnormality characterization reference value, and the melting risk characterization value does not exceed the preset melting risk characterization reference value;

[0094] The stacking normal judgment condition is that the variance of a plurality of intervals does not exceed a preset variance threshold.

[0095] Specifically, the preset melting abnormality characterization reference value, melting risk characterization reference value and variance threshold can be set by technical personnel in this field according to the detection accuracy requirements of alumina production. Preferably, the higher the detection accuracy requirements, the smaller the preset melting abnormality characterization reference value, the smaller the preset melting risk characterization reference value, and the smaller the preset variance threshold. Preferably, the melting abnormality characterization reference value can be 5, the melting risk characterization reference value can be 2, and the variance threshold can be 0.5.

[0096] Specifically, here is a specific implementation example for determining the spacing variance of adjacent feature points. The feature points are point 2, point 4, point 5, point 8, and point 10. The spacings of adjacent feature points are 2.8 cm, 2.8 cm, 2.4 cm, and 2 cm, respectively. The spacing variance of adjacent feature points is 0.11.

[0097] Specifically, the present invention determines whether there is an abnormality in the current alumina production through the melting difference characterization value and the melting risk characterization value. It can be understood that the melting difference characterization value is the variance of several alumina particle sizes in the collection area. In the spherical alumina production process, the obtained spherical alumina particle size should be relatively consistent, and the larger the melting difference characterization value, the larger the variance of several alumina particle sizes, and the greater the discreteness of each spherical alumina particle size in the characterization area, that is, the more obvious the difference in particle size, and the current alumina production is abnormal. The melting risk characterization value is the difference between the maximum and minimum values ​​of the variance in several regions. The discreteness of alumina particle sizes in the collection area under the same heat flux disturbance category should be relatively consistent, and the larger the melting risk characterization value, the more significant the difference in particle size in different regions, and the current alumina production is abnormal. The present invention determines whether there is an abnormality in the current alumina production through the melting difference characterization value and the melting risk characterization value, and further, realizes timely monitoring of the thermal distribution state in the furnace during the alumina production process, adaptively adjusts the selection method of the detection parameters of spherical alumina, and improves the detection efficiency and detection accuracy of alumina production.

[0098] Specifically, the present invention determines whether there is an abnormality in the current alumina production based on the comparison of several spacings. It can be understood that the spherical alumina is in the form of a smooth sphere. Normal spherical alumina can achieve regular stacking so that the spacing between surface protrusions is roughly the same, while adhesion will cause the originally standard spherical alumina to become an irregular shape. When the adhered spherical alumina is stacked, due to its irregular shape, the adhered spheres may contact and stack each other at various angles and in various ways, resulting in the formation of gaps of different sizes and shapes at different positions, thereby causing differences in the spacing between surface feature points, and failing to achieve a regular stacking arrangement. The larger the spacing variance, the greater the difference in spacing between the feature points, the more significant the adhesion of the spherical alumina, and the current alumina production has an abnormality. The present invention determines whether there is an abnormality in the current alumina production through the comparison of several spacings, and further, realizes timely monitoring of the thermal distribution state in the furnace during the alumina production process, adaptively adjusts the selection method of the detection parameters of the spherical alumina, and improves the detection efficiency and accuracy of alumina production.

[0099] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent detection system for alumina production, characterized in that: include: A pre-analysis unit, which is used to divide the collection tank for collecting the spherical aluminum oxide formed by spheroidization into a plurality of collection areas, obtain the stacking parameters of the spherical aluminum oxide in each collection area in a preset monitoring period, and determine the thermal flow disturbance category of the collection area according to the comparison of the plurality of stacking parameters; A feature recognition unit connected to the pre-analysis unit, for selecting disturbance feature factors of each collection area according to the heat flow disturbance category, wherein the disturbance feature factors include alumina particle size values ​​determined based on a surface image of spherical alumina, or spacings between a plurality of adjacent feature points calculated based on a stacking morphology curve of spherical alumina; Wherein, the characteristic points are determined according to the height values ​​of the spherical aluminum oxide at several points on the stacking morphology curve in the direction perpendicular to the horizontal plane; A detection and analysis unit is respectively connected to the pre-analysis unit and the feature recognition unit, and is used to determine the melting difference characterization quantity of the collection area according to the alumina particle size value and to determine whether there is an abnormality in the current alumina production according to the comparison between several melting difference characterization quantities, or to determine whether there is an abnormality in the current alumina production according to the comparison between several spacings.

2. The intelligent detection system for alumina production according to claim 1, characterized in that: The pre-analysis unit is used to obtain the stacking parameters of the spherical aluminum oxide in each collection area, wherein: The pre-analysis unit obtains the spherical aluminum oxide height values ​​at a plurality of points in the collection area during a preset monitoring period, and determines an average value of the plurality of spherical aluminum oxide height values ​​as the stacking parameter of the collection area.

3. The intelligent detection system for alumina production according to claim 2, characterized in that: The pre-analysis unit is also used to determine the thermal flow disturbance category of the collection area, wherein: If the stacking parameters of the collection area meet the first disturbance determination condition, the pre-analysis unit determines the heat flow disturbance category of the collection area as the first heat flow disturbance category; If the stacking parameters of the collection area do not meet the first disturbance determination condition, the pre-analysis unit determines the heat flow disturbance category of the collection area as the second heat flow disturbance category; The first disturbance determination condition is that the stacking parameter does not exceed a preset stacking reference value.

4. The intelligent detection system for alumina production according to claim 3, characterized in that: The feature recognition unit is used to select disturbance feature factors of each collection area, wherein: If the thermal flow disturbance category is the first thermal flow disturbance category, the feature recognition unit selects the disturbance characteristic factor as the aluminum oxide particle size value determined based on the surface image of the spherical aluminum oxide; If the thermal flow disturbance category is the second thermal flow disturbance category, the feature recognition unit selects the disturbance feature factor as the distance between a plurality of adjacent feature points calculated based on the stacking morphology curve of spherical aluminum oxide.

5. The intelligent detection system for alumina production according to claim 4, characterized in that: The feature recognition unit is used to determine the stacking morphology curve, wherein: The feature recognition unit obtains the surface profile curves of the spherical aluminum oxide in several cross-sectional directions of the collection tank in the collection area, calculates the height difference value of the surface profile curve in the direction perpendicular to the horizontal plane according to the maximum value point of the surface profile curve, and determines the surface profile curve corresponding to the maximum value of the height difference value as the stacking morphology curve; The cross-sectional direction of the collecting groove is perpendicular to the axial direction of the collecting groove.

6. The intelligent detection system for alumina production according to claim 5, characterized in that: The feature recognition unit is also used to determine feature points, wherein: The feature recognition unit calculates the height values ​​of a plurality of data points on the stacked shape curve in a direction perpendicular to the horizontal plane, and calculates a height average value according to the height values ​​of the plurality of data points; If the data point on the stacked shape curve meets the characteristic point determination condition, the characteristic recognition unit determines the data point as the characteristic point; The characteristic point determination condition is that the height value corresponding to the data point exceeds the height average value.

7. The intelligent detection system for alumina production according to claim 6, characterized in that: The detection and analysis unit is used to determine the melting difference characterization value of the collection area, wherein: The detection and analysis unit calculates the particle size variance according to the alumina particle size values ​​of a plurality of spherical aluminas in the collection area, and determines the particle size variance as a melting difference characterization value of the collection area.

8. The intelligent detection system for alumina production according to claim 7, characterized in that: The detection and analysis unit is used to determine the comparison between several melting difference characterization quantities, wherein: The detection and analysis unit obtains melting difference characterization quantities of a plurality of first heat flow disturbance category collection areas, and determines the difference between the maximum value of the melting difference characterization quantity and the minimum value of the melting difference characterization quantity as the melting risk characterization value.

9. The intelligent detection system for alumina production according to claim 8, characterized in that: The detection and analysis unit is also used to determine whether there is an abnormality in the current alumina production, wherein: If the melting difference characterization value and the melting risk characterization value do not meet the normal melting judgment condition, the detection and analysis unit determines that there is an abnormality in the current alumina production; If the comparison of several intervals of the stacking morphology curve does not meet the normal stacking judgment conditions, the detection and analysis unit determines that there is an abnormality in the current aluminum oxide production.

10. The intelligent detection system for alumina production according to claim 9, characterized in that: The normal melting judgment condition is that the melting difference characterization value does not exceed the preset melting abnormality characterization reference value, and the melting risk characterization value does not exceed the preset melting risk characterization reference value; The stacking normal judgment condition is that the variance of a plurality of intervals does not exceed a preset variance threshold.

Images