Intelligent supervision system for geopolymer production

Abstract

The invention discloses an intelligent supervision system for geopolymer production, and belongs to the technical field of geopolymer product quality detection. According to the method, the length characterization parameter, the inner and outer cambered surface accuracy characterization parameter and the width characterization parameter of the refractory brick can be accurately obtained; the length between the center points of the corresponding detection frames is used as a length characterization parameter of the refractory brick, so that whether the length of the refractory brick is in an error range or not can be accurately and conveniently judged; the arrangement of the positioning circular plate is matched with an image recognition technology, so that the accuracy characterization parameters of the inner and outer cambered surfaces of the current refractory brick can be accurately detected, and whether the accuracy of the inner and outer cambered surfaces of the refractory brick is within an error range can be accurately and conveniently judged; and the width characterization parameter of the current refractory brick is obtained ingeniously according to the intermediate parameter obtained by the inner and outer cambered surface detection module, so that whether the width of the refractory brick is within the error range can be accurately and conveniently judged.

Description

Technical Field

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

[0002] Geopolymers have various types of products, which are classified into construction geopolymers, road geopolymers and special-purpose geopolymers according to their application fields. Construction geopolymers such as geopolymer cement, geopolymer concrete and geopolymer refractory bricks are used for the construction and maintenance of buildings; road geopolymers such as geopolymer grouting materials and geopolymer adhesives are used for the laying and maintenance of roads; special-purpose geopolymers such as geopolymer products used in the fields of electric furnaces and reactor insulators, composite materials, decorative products, etc.

[0003] Geopolymer refractory brick is a kind of refractory brick made of geopolymer material. Geopolymer refractory brick has a wide range of application prospects in the fields of construction and industry due to its excellent refractory performance and multiple functional characteristics: Geopolymer refractory bricks have good adhesion and plasticity, and are more suitable than cement for the preparation of building block materials, such as standard bricks, building blocks and paving bricks. In addition, it can also be used to prepare grouting materials for filling underground caves, mine goafs, etc. Geopolymer refractory bricks can withstand high temperature environments, so they are suitable for the construction of various furnaces and furnaces that need to withstand high temperatures, such as incinerators, blast furnaces, glass kilns, steel manufacturing and other industrial structures. These structures need to maintain stability and durability at high temperatures, and geopolymer refractory bricks are the ideal material to meet these requirements.

[0004] In the high-temperature furnace masonry project with high precision requirements, the dimensional accuracy of geopolymer refractory bricks needs to be controlled within the set range. How to accurately detect the dimensional error of geopolymer refractory bricks during the production process is an urgent problem to be solved. To this end, an intelligent supervision system for geopolymer production is proposed. Summary of the invention

[0005] The technical problem to be solved by the present invention is how to accurately detect the dimensional error of geopolymer refractory bricks during the production process, and provides an intelligent monitoring system for geopolymer production.

[0006] The present invention solves the above technical problems through the following technical solutions, which include an image acquisition module, a length detection module, an inner and outer arc surface detection module, a width detection module and a background management module; The image acquisition module is used to acquire the overhead image of the refractory bricks on the positioning frame and pre-process the image; The length detection module is used to obtain the length characterization parameter of the current refractory brick according to the recognition result of the preprocessed overhead image of the refractory brick; The inner and outer curved surface detection module is used to obtain the inner and outer curved surface accuracy characterization parameters of the current refractory bricks according to the recognition results of the pre-processed overhead image of the refractory bricks; The width detection module is used to obtain the width characterization parameters of the current refractory brick according to the intermediate parameters obtained by the inner and outer arc surface detection modules; The background management module is used to determine whether the length, inner and outer arc surface accuracy, and width of the refractory bricks are within the error range based on the length characterization parameters, inner and outer arc surface accuracy characterization parameters, and width characterization parameters of each refractory brick, and record the number of qualified and unqualified refractory bricks, and feed back to the brick forming control department.

[0007] Furthermore, the image acquisition module includes an image capturing unit and an image preprocessing unit; the image capturing unit is used to capture the overhead image of the refractory bricks by an industrial camera vertically downward from above the refractory bricks to obtain the overhead image of the refractory bricks; the image preprocessing unit is used to perform noise reduction processing on the overhead image of the refractory bricks.

[0008] Furthermore, the positioning frame includes a first connecting plate, a second connecting plate, a boss, a recessed platform, a positioning circular plate and a connecting arm; wherein the first connecting plate and the second connecting plate are symmetrically arranged, the positioning circular plate is respectively connected to the first connecting plate and the second connecting plate through two symmetrically arranged connecting arms, the center of the positioning circular plate is located on the symmetry axis between the first connecting plate and the second connecting plate, the boss is arranged on the inner side of the first connecting plate, the recessed platform is arranged on the inner side of the second connecting plate, a positioning outer convex arc surface is arranged on the boss, and the shape of the inner concave arc surface of the end of the standard refractory brick is matched, and a positioning inner concave arc surface is arranged on the recessed platform, and the shape of the outer convex arc surface of the positioning end of the standard refractory brick is matched; the gap between the positioning outer convex arc surface and the positioning inner concave arc surface can just accommodate a standard refractory brick; when the standard refractory brick is placed between the positioning outer convex arc surface and the positioning inner concave arc surface, the center position corresponding to the contour lines of the outer convex arc surface and the inner concave arc surface of the standard refractory brick coincides with the center point position of the positioning circular plate; standard refractory bricks refer to refractory bricks whose outer dimensions have no error with the designed outer dimensions.

[0009] Furthermore, the length detection module includes a first arc surface recognition unit, a second arc surface recognition unit and a length characterization parameter acquisition unit; the first arc surface recognition unit is used to detect and identify the first arc surface in the overhead image of the refractory brick using a trained target detection model, and obtain two first arc surface detection frame position information; the second arc surface recognition unit is used to detect and identify the second arc surface in the overhead image of the refractory brick using the target detection model, and obtain two second arc surface detection frame position information; the length characterization parameter acquisition unit is used to obtain the length characterization parameters of the current refractory brick based on the first arc surface detection frame position information and the second arc surface detection frame position information.

[0010] Furthermore, the specific processing process of the length characterization parameter acquisition unit is as follows: Step S11: obtaining the position information of two first arc surface detection frames and the position information of the second arc surface detection frame, wherein the first arc surface is the positioning convex arc surface and the concave arc surface at the end of the refractory brick, and the second arc surface is the positioning concave arc surface and the convex arc surface at the end of the refractory brick, and the position information is the coordinates of the upper left corner point and the lower right corner point of the corresponding detection frame in the image; Step S12: Calculate the center point coordinates of the two first arc surface detection frames according to the position information of the two first arc surface detection frames, and the center points of the two first arc surface detection frames are respectively recorded as M1 and M2; at the same time, calculate the center point coordinates of the two second arc surface detection frames according to the position information of the two second arc surface detection frames, and the center points of the two second arc surface detection frames are respectively recorded as N1 and N2; Step S13: Calculate the lengths of line segments M1N1, M1N2, N1M1, and N1M2, and select the shortest length among them as the length characterization parameter of the current refractory brick, denoted as C.

[0011] Furthermore, the inner and outer arc surface detection module includes a positioning circular plate recognition unit, a refractory brick recognition unit and a arc surface accuracy characterization parameter acquisition unit; the positioning circular plate recognition unit is used to use the target detection model to identify the positioning circular plate in the overhead image of the refractory brick, and obtain the positioning circular plate detection frame position information; the refractory brick recognition unit is used to use the target detection model to identify the refractory bricks as a whole in the overhead image of the refractory brick, and obtain the refractory brick detection frame position information; the arc surface accuracy characterization parameter acquisition unit is used to obtain the inner and outer arc surface accuracy characterization parameters of the current refractory brick according to the positioning circular plate detection frame position information and the refractory brick detection frame position information.

[0012] Furthermore, the specific processing process of the arc surface accuracy characterization parameter acquisition unit is as follows: Step S21: obtaining the position information of the positioning circular plate detection frame and the refractory brick detection frame, wherein the position information is the coordinates of the upper left corner point and the lower right corner point of the corresponding detection frame in the image; Step S22: Calculate the coordinates of the center point of the positioning circular plate detection frame according to the position information of the positioning circular plate detection frame, the center point of the positioning circular plate detection frame is recorded as Y, and its coordinates are used as the center point position of the positioning circular plate; Step S23: cutting out the refractory brick detection frame area from the refractory brick overhead image according to the refractory brick detection frame position information, and recording it as the refractory brick detection frame area image; Step S24: using the contour detection function in OpenCV to identify each contour line in the refractory brick detection frame area image, delete the contour line with the number of pixels less than the set threshold, and the remaining two contour lines are the contour lines of the outer convex arc surface and the inner concave arc surface, respectively, recorded as the outer convex arc surface contour line L1 and the inner concave arc surface contour line L2; Step S25: Read the coordinates of each pixel point on the outer convex arc contour line L1 and the inner concave arc contour line L2 respectively, and record them as Z 1j , Z 2k , where j represents the total number of pixels on the outer convex arc contour line L1, and k represents the total number of pixels on the inner concave arc contour line L2; Step S26: Calculate the distance between each pixel point on the outer convex arc contour line L1 and the center point Y of the positioning circular plate detection frame, and calculate the mean value of the distance, which is recorded as the distance mean d 1avg At the same time, the distance between each pixel point on the inner concave arc contour line L2 and the center point Y of the positioning circular plate detection frame is calculated, and the mean of the distance is calculated, which is recorded as the distance mean d 2avg ; where d 1avg >d 2avg ; Step S27: Calculate the distance mean d 1avg and the preset first distance threshold d 1预设 The difference between them is denoted as D c1 ; At the same time, calculate the distance mean d 2avg and the preset second distance threshold d 2预设 The difference between them is denoted as D c2 ; Among them, D c1 That is, the current characterization parameter of the accuracy of the outer arc surface of refractory bricks, D c2 That is, the parameter characterizing the accuracy of the inner arc surface of current refractory bricks.

[0013] Furthermore, the specific processing process of the width detection module is as follows: Step S31: Obtain the distance mean d in step S26 1avg , distance mean d 2avg ; Step S32: Calculate the distance mean d 1avg , distance mean d 2avg The difference between them is denoted as Kd , which is the width characterization parameter of the current refractory brick.

[0014] Furthermore, the specific processing process of the background management module is as follows: Step S41: respectively comparing the length characterization parameters, inner and outer camber accuracy characterization parameters, and width characterization parameters of each refractory brick with the preset refractory brick length characterization parameter thresholds, inner and outer camber accuracy characterization parameter thresholds, and width characterization parameter thresholds; Step S42: for a single refractory brick, when all the characterization parameters are within the corresponding threshold range, it is considered a qualified product; when any characterization parameter is not within the corresponding threshold range, it is considered a failed product; Step S43: Count and record the number of qualified and unqualified refractory bricks in the current batch, as well as the reasons for the unqualified products, and feed the data back to the brick forming control department.

[0015] Compared with the prior art, the present invention has the following advantages: the intelligent monitoring system for geopolymer production can realize the accurate acquisition of refractory brick length characterization parameters, inner and outer arc surface accuracy characterization parameters, and width characterization parameters; the length between the corresponding detection frame center points is used as the length characterization parameter of the refractory brick, and it is possible to accurately and conveniently judge whether the length of the refractory brick is within the error range; and through the setting of the positioning circular plate in combination with the image recognition technology, it is possible to accurately detect the inner and outer arc surface accuracy characterization parameters of the current refractory brick, and then it is possible to accurately and conveniently judge whether the inner and outer arc surface accuracy of the refractory brick is within the error range; it is also possible to cleverly obtain the width characterization parameters of the current refractory brick based on the intermediate parameters obtained by the inner and outer arc surface detection module, and then it is possible to accurately and conveniently judge whether the width of the refractory brick is within the error range. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of the structure of an arc-shaped geopolymer refractory brick in an embodiment of the present invention (top view); Figure 2 2 is a schematic diagram of the overall structure of the arc-shaped geopolymer refractory brick in an embodiment of the present invention (front view); Figure 3 is a schematic block diagram of the structure of an intelligent monitoring system for geopolymer production in an embodiment of the present invention; Figure 4 Schematic diagram of the position of the arc-shaped geopolymer refractory brick when placed on the positioning frame in an embodiment of the present invention (top view); Figure 5 Schematic diagram of a bird's-eye view of a refractory brick in an embodiment of the present invention.

[0017] In the figure: 1, outer convex arc surface of outer contour; 2, inner concave arc surface of inner contour; 3, inner concave arc surface of end portion; 4, outer convex arc surface of end portion; 5, positioning slot; 6, positioning plug-in block; 7, first connecting plate; 71, boss; 72, positioning outer convex arc surface; 8, second connecting plate; 81, concave boss; 82, positioning inner concave arc surface; 9, positioning circular plate; 10, connecting arm. DETAILED DESCRIPTION

[0018] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiment.

[0019] like Figure 1 , 2 As shown, the arc-shaped geopolymer refractory brick used for high-temperature furnace masonry engineering in this embodiment has an outer convex arc surface 1, an inner concave arc surface 2, an end surface on one side is an end concave arc surface 3, and an end surface on the other side is an end convex arc surface 4. The top and bottom surfaces are both flat, and a positioning slot 5 (square) with a set depth is reserved on the top surface, and a positioning plug 6 with a set length is provided on the bottom surface, which matches the shape of the positioning slot 5. During masonry, the end concave arc surface 3 of the two adjacent refractory bricks is connected end to end with the end convex arc surface 4, and finally a cylindrical furnace structure is formed. The positioning slot 5 cooperates with the positioning plug 6 to realize the positioning of the upper and lower layers of refractory bricks.

[0020] like Figure 3 , 4 As shown, this embodiment provides a technical solution: an intelligent supervision system for geopolymer production, mainly used in the quality inspection link of the geopolymer refractory brick production process, including an image acquisition module, a length detection module, an inner and outer arc surface detection module, a width detection module and a background management module; In this embodiment, the image acquisition module is used to acquire the overhead image of the refractory bricks on the positioning frame and pre-process the image.

[0021] As more specific, the image acquisition module includes an image capturing unit and an image preprocessing unit; the image capturing unit is used to capture a top-down image of the refractory bricks by an industrial camera. Figure 5 The image preprocessing unit is used to perform noise reduction on the overhead image of refractory bricks to improve the image quality.

[0022] It should be noted that during the inspection, a single refractory brick is placed on the positioning frame by manual or robot grabbing, and the positioning frame includes a first connecting plate 7, a second connecting plate 8, a boss 71, a recessed platform 81, a positioning circular plate 9 and a connecting arm 10; wherein the first connecting plate 7 and the second connecting plate 8 are symmetrically arranged, and the positioning circular plate 9 is respectively connected to the first connecting plate 7 and the second connecting plate 8 through two symmetrically arranged connecting arms 10, and the center of the positioning circular plate 9 is located on the symmetry axis between the first connecting plate 7 and the second connecting plate 8, the boss 71 is arranged on the inner side of the first connecting plate 7, the recessed platform 81 is arranged on the inner side of the second connecting plate 8, and the boss 71 is provided with a positioning outer The convex arc surface 72 matches the shape of the inner concave arc surface 3 of the end portion, and a positioning inner concave arc surface 82 is provided on the concave platform 81, which matches the shape of the outer convex arc surface 4 of the end portion; the gap between the positioning outer convex arc surface 72 and the positioning inner concave arc surface 82 can just accommodate a standard refractory brick; the bottom surfaces of the convex platform 71 and the concave platform 81 are provided with corresponding supporting plates for supporting a single refractory brick placed between the positioning outer convex arc surface 72 and the positioning inner concave arc surface 82; when the standard refractory brick is placed between the positioning outer convex arc surface 72 and the positioning inner concave arc surface 82, the center position corresponding to the contour line of the outer convex arc surface 1 and the inner concave arc surface 2 of the standard refractory brick coincides with the center point position of the positioning circular plate 9.

[0023] It should be noted that standard refractory bricks refer to refractory bricks whose external dimensions have no error with the designed external dimensions.

[0024] In this embodiment, the length detection module is used to obtain the length characterization parameter of the current refractory brick according to the recognition result of the preprocessed overhead image of the refractory brick.

[0025] More specifically, the length detection module includes a first arc surface recognition unit, a second arc surface recognition unit and a length characterization parameter acquisition unit; the first arc surface recognition unit is used to detect and identify the first arc surface in the overhead image of the refractory brick using a trained target detection model, and obtain two first arc surface detection frame position information; the second arc surface recognition unit is used to detect and identify the second arc surface in the overhead image of the refractory brick using the target detection model, and obtain two second arc surface detection frame position information; the length characterization parameter acquisition unit is used to obtain the length characterization parameters of the current refractory brick based on the first arc surface detection frame position information and the second arc surface detection frame position information.

[0026] It should be noted that the target detection model in this embodiment is obtained based on the training of the yolo v3s detection network, which can realize multi-target detection and classification.

[0027] As more specific, the specific processing process of the length characterization parameter acquisition unit is as follows: Step S11: obtaining the position information of two first arc surface detection frames and the position information of the second arc surface detection frame, wherein the first arc surface is the positioning outer convex arc surface 72 and the end inner concave arc surface 3, and the second arc surface is the positioning inner concave arc surface 82 and the end outer convex arc surface 4, and the position information is the coordinates of the upper left corner point and the lower right corner point of the corresponding detection frame in the image; Step S12: Calculate the center point coordinates of the two first arc surface detection frames according to the position information of the two first arc surface detection frames, and the center points of the two first arc surface detection frames are respectively recorded as M1 and M2; at the same time, calculate the center point coordinates of the two second arc surface detection frames according to the position information of the two second arc surface detection frames, and the center points of the two second arc surface detection frames are respectively recorded as N1 and N2; Step S13: Calculate the lengths of line segments M1N1, M1N2, N1M1, and N1M2, and select the shortest length among them as the length characterization parameter of the current refractory brick, denoted as C.

[0028] In the present invention, by calculating the detection frame position corresponding to the positioning outer convex arc surface 72 and the end inner concave arc surface 3, and calculating the detection frame position corresponding to the positioning inner concave arc surface 82 and the end outer convex arc surface 4, the length between the corresponding detection frame center points is used as the length characterization parameter of the refractory brick, so as to accurately and conveniently determine whether the length of the refractory brick is within the error range.

[0029] In this embodiment, the inner and outer curved surface detection module is used to obtain the inner and outer curved surface accuracy characterization parameters of the current refractory bricks according to the recognition results of the preprocessed overhead image of the refractory bricks.

[0030] More specifically, the inner and outer arc surface detection module includes a positioning circular plate recognition unit, a refractory brick recognition unit and a arc surface accuracy characterization parameter acquisition unit; the positioning circular plate recognition unit is used to use the target detection model to identify the positioning circular plate 9 in the overhead image of the refractory brick, and obtain the positioning circular plate detection frame position information; the refractory brick recognition unit is used to use the target detection model to identify the refractory bricks as a whole in the overhead image of the refractory brick, and obtain the refractory brick detection frame position information; the arc surface accuracy characterization parameter acquisition unit is used to obtain the inner and outer arc surface accuracy characterization parameters of the current refractory brick according to the positioning circular plate detection frame position information and the refractory brick detection frame position information.

[0031] As more specific, the specific processing process of the arc surface accuracy characterization parameter acquisition unit is as follows: Step S21: obtaining the position information of the positioning circular plate detection frame and the refractory brick detection frame, wherein the position information is the coordinates of the upper left corner point and the lower right corner point of the corresponding detection frame in the image; Step S22: Calculate the coordinates of the center point of the positioning circular plate detection frame according to the position information of the positioning circular plate detection frame. The center point of the positioning circular plate detection frame is recorded as Y, and its coordinates are used as the center point position of the positioning circular plate 9; Step S23: cutting out the refractory brick detection frame area from the refractory brick overhead image according to the refractory brick detection frame position information, and recording it as the refractory brick detection frame area image; Step S24: using the contour detection function in OpenCV to identify each contour line in the refractory brick detection frame area image, delete the contour lines with the number of pixels less than the set threshold, and the remaining two contour lines are the contour lines of the outer contour convex arc surface 1 and the inner contour concave arc surface 2, which are recorded as the outer contour convex arc surface contour line L1 and the inner contour concave arc surface contour line L2; Step S25: Read the coordinates of each pixel point on the outer convex arc contour line L1 and the inner concave arc contour line L2 respectively, and record them as Z 1j , Z 2k , where j represents the total number of pixels on the outer convex arc contour line L1, and k represents the total number of pixels on the inner concave arc contour line L2; Step S26: Calculate the distance between each pixel point on the outer convex arc contour line L1 and the center point Y of the positioning circular plate detection frame, and calculate the mean value of the distance, which is recorded as the distance mean d 1avg At the same time, the distance between each pixel point on the inner concave arc contour line L2 and the center point Y of the positioning circular plate detection frame is calculated, and the mean of the distance is calculated, which is recorded as the distance mean d 2avg ; where d 1avg >d 2avg ; Step S27: Calculate the distance mean d 1avg and the preset first distance threshold d 1预设 The difference between them is denoted as D c1 ; At the same time, calculate the distance mean d 2avg and the preset second distance threshold d 2预设 The difference between them is denoted as D c2 ; Among them, D c1 That is, the current characterization parameter of the accuracy of the outer arc surface of refractory bricks, D c2 That is, the parameter characterizing the accuracy of the inner arc surface of current refractory bricks.

[0032] In the present invention, by setting a positioning circular plate in conjunction with image recognition technology, the accuracy characterization parameters of the inner and outer arc surfaces of the current refractory bricks can be accurately detected, and then it can be accurately and conveniently determined whether the accuracy of the inner and outer arc surfaces of the refractory bricks is within the error range.

[0033] In this embodiment, the width detection module is used to obtain the width characterization parameters of the current refractory brick according to the intermediate parameters obtained by the inner and outer curved surface detection modules.

[0034] As more specific, the specific processing process of the width detection module is as follows: Step S31: Obtain the distance mean d in step S26 1avg , distance mean d 2avg ; Step S32: Calculate the distance mean d 1avg , distance mean d 2avg The difference between them is denoted as K d , which is the width characterization parameter of the current refractory brick.

[0035] In the present invention, the width characterization parameters of the current refractory bricks are obtained ingeniously according to the intermediate parameters obtained by the inner and outer arc surface detection modules, so as to accurately and conveniently judge whether the width of the refractory bricks is within the error range.

[0036] In this embodiment, the background management module is used to determine whether the length, inner and outer arc surface accuracy, and width of the refractory bricks are within the error range based on the length characterization parameters, inner and outer arc surface accuracy characterization parameters, and width characterization parameters of each refractory brick, and record the number of qualified and unqualified refractory bricks, and feed back to the brick forming control department.

[0037] As more specific, the specific processing process of the background management module is as follows: Step S41: respectively comparing the length characterization parameters, inner and outer camber accuracy characterization parameters, and width characterization parameters of each refractory brick with the preset refractory brick length characterization parameter thresholds, inner and outer camber accuracy characterization parameter thresholds, and width characterization parameter thresholds; Step S42: for a single refractory brick, when all the characterization parameters are within the corresponding threshold range, it is considered a qualified product; when any characterization parameter is not within the corresponding threshold range, it is considered a failed product; Step S43: Count and record the number of qualified and unqualified refractory bricks in the current batch, as well as the reasons for the unqualified products, and feed the data back to the brick forming control department.

[0038] In the present invention, after feedback is given to the brick forming control department, the corresponding links in the brick forming process are adjusted according to the reasons for the failure of the unqualified products, thereby improving the brick qualification rate.

[0039] It should be noted that the thickness of bricks can be detected manually.

[0040] To sum up, the intelligent supervision system for geopolymer production of the above-mentioned embodiment can realize the accurate acquisition of the length characterization parameters, inner and outer arc surface accuracy characterization parameters, and width characterization parameters of the refractory brick; taking the length between the center points of the corresponding detection frames as the length characterization parameter of the refractory brick, it is possible to accurately and conveniently judge whether the length of the refractory brick is within the error range; and through the setting of the positioning circular plate in combination with the image recognition technology, it is possible to accurately detect the inner and outer arc surface accuracy characterization parameters of the current refractory brick, and then accurately and conveniently judge whether the inner and outer arc surface accuracy of the refractory brick is within the error range; it is also possible to cleverly obtain the width characterization parameters of the current refractory brick based on the intermediate parameters obtained by the inner and outer arc surface detection module, and then accurately and conveniently judge whether the width of the refractory brick is within the error range.

[0041] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0042] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0043] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent monitoring system for geopolymer production, characterized in that: include: Image acquisition module, length detection module, inner and outer arc surface detection module, width detection module and background management module; The image acquisition module is used to acquire the overhead image of the refractory bricks on the positioning frame and pre-process the image; The length detection module is used to obtain the length characterization parameter of the current refractory brick according to the recognition result of the preprocessed overhead image of the refractory brick; The inner and outer curved surface detection module is used to obtain the inner and outer curved surface accuracy characterization parameters of the current refractory bricks according to the recognition results of the pre-processed overhead image of the refractory bricks; The width detection module is used to obtain the width characterization parameters of the current refractory brick according to the intermediate parameters obtained by the inner and outer arc surface detection modules; The background management module is used to determine whether the length, inner and outer arc surface accuracy, and width of the refractory bricks are within the error range based on the length characterization parameters, inner and outer arc surface accuracy characterization parameters, and width characterization parameters of each refractory brick, and record the number of qualified and unqualified refractory bricks, and feed back to the brick forming control department.

2. The intelligent monitoring system for geopolymer production according to claim 1, characterized in that: The image acquisition module includes an image capturing unit and an image preprocessing unit; the image capturing unit is used to capture an overhead image of the refractory bricks by an industrial camera vertically downward from above the refractory bricks; the image preprocessing unit is used to perform noise reduction processing on the overhead image of the refractory bricks.

3. The intelligent monitoring system for geopolymer production according to claim 2, characterized in that: The positioning frame includes a first connecting plate, a second connecting plate, a boss, a recessed platform, a positioning circular plate and a connecting arm; wherein the first connecting plate and the second connecting plate are symmetrically arranged, and the positioning circular plate is respectively connected to the first connecting plate and the second connecting plate through two symmetrically arranged connecting arms, and the center of the positioning circular plate is located on the symmetry axis between the first connecting plate and the second connecting plate, the boss is arranged on the inner side of the first connecting plate, and the recessed platform is arranged on the inner side of the second connecting plate, and a positioning outer convex arc surface is arranged on the boss, which matches the shape of the inner concave arc surface at the end of the standard refractory brick, and a positioning inner concave arc surface is arranged on the recessed platform, which matches the shape of the outer convex arc surface at the end of the standard refractory brick; the gap between the positioning outer convex arc surface and the positioning inner concave arc surface can just accommodate a standard refractory brick; when the standard refractory brick is placed between the positioning outer convex arc surface and the positioning inner concave arc surface, the center position corresponding to the contour lines of the outer convex arc surface and the inner concave arc surface of the standard refractory brick coincides with the center point position of the positioning circular plate; the standard refractory brick refers to a refractory brick whose outer dimensions have no error with the designed outer dimensions.

4. The intelligent monitoring system for geopolymer production according to claim 3, characterized in that: The length detection module includes a first arc surface recognition unit, a second arc surface recognition unit and a length characterization parameter acquisition unit; the first arc surface recognition unit is used to detect and recognize the first arc surface in the overhead image of the refractory brick using the trained target detection model, and obtain the position information of two first arc surface detection frames; The second arc surface recognition unit is used to detect and identify the second arc surface in the overhead image of the refractory brick using the target detection model, and obtain the position information of two second arc surface detection frames; the length characterization parameter acquisition unit is used to obtain the length characterization parameters of the current refractory brick based on the first arc surface detection frame position information and the second arc surface detection frame position information.

5. The intelligent monitoring system for geopolymer production according to claim 4, characterized in that: The specific processing process of the length characterization parameter acquisition unit is as follows: Step S11: obtaining the position information of two first arc surface detection frames and the position information of the second arc surface detection frame, wherein the first arc surface is the positioning convex arc surface and the concave arc surface at the end of the refractory brick, and the second arc surface is the positioning concave arc surface and the convex arc surface at the end of the refractory brick, and the position information is the coordinates of the upper left corner point and the lower right corner point of the corresponding detection frame in the image; Step S12: Calculate the center point coordinates of the two first arc surface detection frames according to the position information of the two first arc surface detection frames, and the center points of the two first arc surface detection frames are respectively recorded as M1 and M2; at the same time, calculate the center point coordinates of the two second arc surface detection frames according to the position information of the two second arc surface detection frames, and the center points of the two second arc surface detection frames are respectively recorded as N1 and N2; Step S13: Calculate the lengths of line segments M1N1, M1N2, N1M1, and N1M2, and select the shortest length among them as the length characterization parameter of the current refractory brick, denoted as C.

6. The intelligent monitoring system for geopolymer production according to claim 5, characterized in that: The inner and outer arc surface detection module includes a positioning circular plate recognition unit, a refractory brick recognition unit and a arc surface accuracy characterization parameter acquisition unit; the positioning circular plate recognition unit is used to use the target detection model to identify the positioning circular plate in the overhead image of the refractory brick, and obtain the positioning circular plate detection frame position information; the refractory brick recognition unit is used to use the target detection model to identify the refractory bricks as a whole in the overhead image of the refractory brick, and obtain the refractory brick detection frame position information; the arc surface accuracy characterization parameter acquisition unit is used to obtain the inner and outer arc surface accuracy characterization parameters of the current refractory brick according to the positioning circular plate detection frame position information and the refractory brick detection frame position information.

7. The intelligent monitoring system for geopolymer production according to claim 6, characterized in that: The specific processing process of the arc surface accuracy characterization parameter acquisition unit is as follows: Step S21: obtaining the position information of the positioning circular plate detection frame and the refractory brick detection frame, wherein the position information is the coordinates of the upper left corner point and the lower right corner point of the corresponding detection frame in the image; Step S22: Calculate the coordinates of the center point of the positioning circular plate detection frame according to the position information of the positioning circular plate detection frame, the center point of the positioning circular plate detection frame is recorded as Y, and its coordinates are used as the center point position of the positioning circular plate; Step S23: cutting out the refractory brick detection frame area from the refractory brick overhead image according to the refractory brick detection frame position information, and recording it as the refractory brick detection frame area image; Step S24: using the contour detection function in OpenCV to identify each contour line in the refractory brick detection frame area image, delete the contour line with the number of pixels less than the set threshold, and the remaining two contour lines are the contour lines of the outer convex arc surface and the inner concave arc surface, respectively, recorded as the outer convex arc surface contour line L1 and the inner concave arc surface contour line L2; Step S25: Read the coordinates of each pixel point on the outer convex arc contour line L1 and the inner concave arc contour line L2 respectively, and record them as Z 1j , Z 2k , where j represents the total number of pixels on the outer convex arc contour line L1, and k represents the total number of pixels on the inner concave arc contour line L2; Step S26: Calculate the distance between each pixel point on the outer convex arc contour line L1 and the center point Y of the positioning circular plate detection frame, and calculate the mean value of the distance, which is recorded as the distance mean d 1avg At the same time, the distance between each pixel point on the inner concave arc contour line L2 and the center point Y of the positioning circular plate detection frame is calculated, and the mean of the distance is calculated, which is recorded as the distance mean d 2avg ; where d 1avg >d 2avg ; Step S27: Calculate the distance mean d 1avg and the preset first distance threshold d 1预设 The difference between them is denoted as D c1 ; At the same time, calculate the distance mean d 2avg and the preset second distance threshold d 2预设 The difference between them is denoted as D c2 ; Among them, D c1 That is, the current characterization parameter of the accuracy of the outer arc surface of refractory bricks, D c2 That is, the parameter characterizing the accuracy of the inner arc surface of current refractory bricks.

8. The intelligent monitoring system for geopolymer production according to claim 7, characterized in that: The specific processing process of the width detection module is as follows: Step S31: Obtain the distance mean d in step S6 1avg , distance mean d 2avg ; Step S32: Calculate the distance mean d 1avg , distance mean d 2avg The difference between them is denoted as K d , which is the width characterization parameter of the current refractory brick.

9. The intelligent monitoring system for geopolymer production according to claim 1, characterized in that: The specific processing process of the background management module is as follows: Step S41: respectively comparing the length characterization parameters, inner and outer camber accuracy characterization parameters, and width characterization parameters of each refractory brick with the preset refractory brick length characterization parameter thresholds, inner and outer camber accuracy characterization parameter thresholds, and width characterization parameter thresholds; Step S42: for a single refractory brick, when all the characterization parameters are within the corresponding threshold range, it is considered a qualified product; when any characterization parameter is not within the corresponding threshold range, it is considered a failed product; Step S43: Count and record the number of qualified and unqualified refractory bricks in the current batch, as well as the reasons for the unqualified products, and feed the data back to the brick forming control department.

Images