A visual positioning system for circuit breaker tripping screws

Abstract

The invention relates to the technical field of circuit breaker detection, and specifically discloses a circuit breaker trip screw visual positioning system; the system comprises: an image recognition unit extracts the outer contour of a preprocessed trip screw ROI area image and a reference center point of the trip screw ROI area image through a Canny algorithm; a test analysis unit obtains a sample of a distance parameter set of a historical trip screw ROI area image reference center point, inputs the sample into a preset simulation test model to perform a positioning test and output positioning parameters; a visual positioning analysis is performed in combination with the trip screw ROI area image processed by an image processing unit and the positioning parameters output by a test unit to determine whether an offset is generated when aligning the center position of the trip screw: if not, a positioning test result is output; if yes, a current operation is paused and an adjustment strategy is generated; a trip screw control unit generates a control instruction according to the adjustment strategy to control a servo motor to perform axial adjustment on an alignment mechanism.

Description

Technical Field

[0001] The invention relates to the technical field of circuit breaker detection, and in particular to a circuit breaker tripping screw visual positioning system. Background Art

[0002] In recent years, with the development of computer vision technology, vision-based positioning systems have been widely used in the field of industrial automation. Such systems use cameras to obtain images of target objects, and then use image processing and analysis technology to determine the position and posture of the object; in the visual positioning system of circuit breaker tripping screws, it is usually necessary to identify and analyze the shape, size, color and other features of the screws to achieve accurate positioning.

[0003] Currently, a simplified process of visual positioning operation flow for circuit breaker tripping screws is realized through automated equipment systems and optimized image processing algorithms. However, there is a problem of scope of use when only simple image positioning and geometric center analysis are performed. In fact, the accuracy of image acquisition alignment information is required to be high during the visual positioning analysis of the tripping screws. It is usually only applicable to specific viewing angle scenes and standard angle alignment image conditions. Therefore, the applicable image alignment selection range is relatively limited. At the same time, the control of the accuracy range of machine alignment mostly or even completely depends on the selection method of the image area. Therefore, the accuracy of the top center position alignment of the tripping screw in actual operation is also ignored. Summary of the invention

[0004] The purpose of the present invention is to provide a circuit breaker tripping screw visual positioning system to solve the following technical problems:

[0005] How to improve the alignment information accuracy of the image information of the stripping screw to achieve the accuracy of the top center position positioning and alignment of the stripping screw.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A circuit breaker tripping screw visual positioning system, comprising:

[0008] An image acquisition unit is used to obtain an ROI area image of a stripped screw acquired by an industrial camera and transmit position information corresponding to the ROI area image through a limit sensor; the position information includes longitudinal position coordinate parameters and transverse position coordinate parameters of the ROI area image;

[0009] An image processing unit, used for grayscale processing and bilateral filtering noise reduction preprocessing of the ROI area image of the stripped screw;

[0010] An image recognition unit is used to extract the outer contour of the pre-processed ROI area image of the detached screw and the reference center point of the ROI area image of the detached screw by using a Canny algorithm;

[0011] A test analysis unit is used to obtain a distance parameter set of a reference center point of an image of a historically tripped screw ROI area based on the position information, and use it as a sample and input it into a preset simulation test model to perform a positioning test and output positioning parameters;

[0012] The positioning analysis unit performs visual positioning analysis based on the ROI area image of the stripping screw processed by the image processing unit and the positioning parameters output by the test analysis unit to determine whether the alignment with the center position of the stripping screw is offset:

[0013] If not, output the positioning result;

[0014] If yes, the current operation is suspended and an adjustment strategy is generated;

[0015] A release screw control unit, used for generating a control instruction according to an adjustment strategy to control the servo motor to perform axial adjustment on the position information of the release screw;

[0016] The result output unit is used for visually outputting the positioning result of the alignment stripping screw.

[0017] Preferably, the test analysis unit comprises:

[0018] A plurality of key points are set according to the longitudinal position coordinate parameters and the transverse position coordinate parameters of the image of the ROI area of ​​the stripping screw;

[0019] Calculate the distance parameter set from each key point of the outer contour of the ROI area image of the stripped screw to the reference center point of the ROI area image of the stripped screw , ∈ ,in, is the total number of key points; , , These are all key point distance parameters;

[0020] Before acquisition The distance parameter set of each key point of the outer contour of the ROI area image of the stripping screw to the corresponding reference center point of the ROI area image of the stripping screw .

[0021] Preferably, the test analysis unit further comprises:

[0022] Get the number of times in the preset historical time period A set of distance parameters for the tripping screws Each key point distance parameter within Curve parameter set that changes with test time , and input it as a sample into the preset simulation test model for test analysis and judgment of the current set Whether the number of elements in meets the requirement of belonging to the preset threshold range:

[0023] If so, the simulated specific gravity of the ratio X of the number of elements that meet the requirements and the total elements in each stripping screw is output as a positioning parameter;

[0024] If not, then the ratio of the number of elements that do not meet the requirements to the total elements in each stripping screw is X ’ The simulated specific gravity is output as the warning value.

[0025] Preferably, the positioning analysis unit:

[0026] Get the number of key points of the current stripped screw And the positioning parameters of the corresponding key points ; Through the formula Calculate the positioning state coefficient ;

[0027] in, ; is the visual positioning time interval, and 0< < ; is the preset function; are standard positioning parameters; is the preset positioning parameter deviation value; is the preset weight coefficient.

[0028] Preferably, the results of the visual positioning analysis include:

[0029] Positioning state coefficient and preset positioning state coefficient threshold To compare:

[0030] like ≥ , it is determined that the current alignment release screw center position is offset and an adjustment strategy is generated.

[0031] Preferably, the adjustment strategy includes:

[0032] Preset the initial load, initial alignment distance, and initial alignment accuracy of the alignment mechanism based on the historical servo motor motion control system;

[0033] The initial load, initial alignment distance and initial alignment accuracy of the alignment mechanism are adjusted according to the visual positioning analysis results.

[0034] Preferably, the adjustment strategy generates a control instruction to control the servo motor to perform axial adjustment on the position information of the alignment release screw in the following manner:

[0035] Generate control instructions for motion control adjustment: within the specified power-on time, the center of the concentric dual flexible axis and the center of the screw are tracked according to the image positioning results, and the servo motor is started to realize the combined movement and rotation of the concentric dual flexible axis along the Z axis to complete the adjustment action of the alignment release screw.

[0036] Preferably, it also includes an adaptive unit for determining the distribution position of the ROI area image of the release screw in the shooting window of the industrial camera according to the position information.

[0037] Preferably, the adaptive unit comprises:

[0038] Get N pixels of the ROI area image of the stripped screw and determine the mean value of the RGB red component of the N pixels of the ROI area image , RGB green component mean , RGB blue component mean ;

[0039] according to , and The historical RGB color component mean value interval of the target stripped screw is screened and obtained, and the pixel distribution interval of the key points of the image of the stripped screw ROI area is determined;

[0040] The distribution position of the ROI area image of the release screw in the shooting window of the industrial camera is obtained according to the pixel distribution interval of its key points.

[0041] Beneficial effects of the present invention:

[0042] (1) The present invention sets a test analysis unit to obtain a distance parameter set of the image reference center point of the historically disengaged screw ROI area based on the position information, takes it as a sample, performs a simulation process of the positioning test through a machine algorithm such as a neural network algorithm, and inputs it into a preset simulation test model for positioning test, thereby realizing the accurate output process of the positioning parameters.

[0043] (2) The present invention performs visual positioning analysis by setting a positioning analysis unit in combination with the ROI area image of the disengaged screw processed by the image processing unit and the positioning parameters output by the test analysis unit, so as to determine whether an offset occurs to the top center position of the aligned disengaged screw, and generates a corresponding processing method according to the result of the determination. If not, the positioning result is output; if so, the current operation is paused and an adjustment strategy is generated; and adjustments and the next step of control are performed according to the result of the determination, and a disengaged screw control unit is set to generate a control instruction according to the adjustment strategy to control the servo motor to perform axial adjustment on the position information of the aligned disengaged screw; the axial adjustment is performed by the disengaged screw control unit to ensure the center position of the aligned disengaged screw, thereby realizing the precise positioning and tracking process of the screw position.

[0044] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0046] Figure 1 This is a module diagram of a circuit breaker release screw visual positioning system of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 As shown, the present invention is a circuit breaker release screw visual positioning system, comprising:

[0049] An image acquisition unit is used to obtain an ROI area image of a stripped screw acquired by an industrial camera and transmit position information corresponding to the ROI area image through a limit sensor; the position information includes longitudinal position coordinate parameters and transverse position coordinate parameters of the ROI area image;

[0050] An image processing unit, used for grayscale processing and bilateral filtering noise reduction preprocessing of the ROI area image of the stripped screw;

[0051] An image recognition unit is used to extract the outer contour of the pre-processed ROI area image of the detached screw and the reference center point of the ROI area image of the detached screw by using a Canny algorithm;

[0052] A test analysis unit is used to obtain a distance parameter set of a reference center point of an image of a historically tripped screw ROI area based on the position information, and use it as a sample and input it into a preset simulation test model to perform a positioning test and output positioning parameters;

[0053] The positioning analysis unit performs visual positioning analysis based on the ROI area image of the stripping screw processed by the image processing unit and the positioning parameters output by the test analysis unit to determine whether the alignment with the center position of the stripping screw is offset:

[0054] If not, output the positioning result;

[0055] If yes, the current operation is suspended and an adjustment strategy is generated;

[0056] A release screw control unit, used for generating a control instruction according to an adjustment strategy to control the servo motor to perform axial adjustment on the position information of the release screw;

[0057] The result output unit is used for visually outputting the positioning result of the alignment stripping screw.

[0058] In the above technical solution, in this embodiment, an image acquisition unit, an image processing unit, an image recognition unit, a test analysis unit, a positioning analysis unit, a tripping screw control unit and a result output unit are used to realize accurate visual positioning analysis of the position of the circuit breaker tripping screw, and determine the height positioning adjustment process for the position of the tripping screw.

[0059] Specifically, first, the image acquisition unit, the image processing unit, and the image recognition unit are used to respectively acquire the surface image information of the disengaged screw, acquire the ROI area image of the disengaged screw and perform preprocessing; wherein the image acquisition unit acquires the ROI area image of the disengaged screw acquired by the industrial camera and transmits the position information corresponding to the ROI area image through the limit sensor; wherein the position information includes the longitudinal position coordinate parameters and the lateral position coordinate parameters of the ROI area image; the method for acquiring the ROI area image of the disengaged screw here is to automatically detect the ROI area of ​​the disengaged screw by using a common image processing algorithm; for example, edge detection, threshold segmentation, morphological operation and other methods are used to identify the target object disengaged screw in the image, thereby determining the ROI area, and by determining the ROI area of ​​the disengaged screw, the area range is limited.

[0060] The range is initially positioned and limited by obtaining the ROI area image of the disengaged screw and obtaining the current ROI area image area position information through the positioning device; the ROI area image of the disengaged screw is preprocessed by grayscale processing and bilateral filtering noise reduction by setting an image processing unit to ensure further processing of the ROI area image of the disengaged screw, and the image recognition unit is set to extract the outer contour of the preprocessed ROI area image of the disengaged screw by the Canny algorithm and calculate the reference center point of the ROI area image of the disengaged screw according to the Hough circle center detection algorithm, and mark it on the image; the positioning data is tested and analyzed based on the accurate identification of the outer contour of the ROI area image of the disengaged screw and the extraction of the reference center point of the ROI area image of the disengaged screw.

[0061] Then, a test analysis unit is set to obtain a distance parameter set of the image reference center point of the historical disengaged screw ROI area based on the position information. The distance parameter set is used as a training sample and a simulation alignment process of the positioning test is performed through machine algorithms such as a neural network algorithm. The positioning test is performed by inputting the set into a preset simulation test model. After the test, the network is trained with sample data from different groups, and the weights and biases in the network are adjusted to make the output of the network as close to the actual positioning parameters as possible, thereby realizing the accurate output process of the positioning parameters.

[0062] Next, a positioning analysis unit is set up to perform visual positioning analysis in combination with the ROI area image of the disengaged screw processed by the image processing unit and the positioning parameters output by the test analysis unit. Real-time positioning analysis is performed on the ROI area image of the disengaged screw obtained by the image processing unit and the positioning parameters collected by the test analysis unit to judge the accuracy of the acquired alignment information, that is, to judge whether an offset occurs in the top center position of the alignment disengaged screw. A corresponding processing method is generated according to the result of the judgment. If not, the positioning result is output; if so, the current operation is paused and an adjustment strategy is generated; and adjustments and the next step of control are performed according to the result of the judgment.

[0063] Furthermore, by setting a release screw control unit to generate control instructions according to the adjustment strategy, the servo motor is controlled to perform axial adjustment on the position information of the release screw; the axial adjustment is performed by the release screw control unit to ensure the center position of the release screw, thereby realizing the precise positioning and tracking process of the screw position.

[0064] In addition, in addition to generating adjustment information according to the adjustment strategy, the control instructions also include: first, resetting the alignment mechanism. Before performing image acquisition and positioning visual tracking on the next release screw, the alignment is reset. The reset action includes mechanical origin reset and coordinate origin reset. Mechanical origin reset refers to the alignment mechanism being controlled by each axial limit switch to return from the current position to the mechanical origin; coordinate origin reset refers to the concentric dual flexible axes returning from the mechanical origin to the coordinate origin; second, the PLC control system drives the motor to complete the tracking and adjustment action of the release screw by the alignment mechanism, and the release screw is positioned and controlled so that the mobile alignment mechanism platform is accurately moved to the screw target position along the coordinate axis (generally the X-axis and Y-axis directions) according to the system indicator speed and accuracy requirements, so that the concentric dual flexible axes are aligned with the corresponding release screws, and then stop to prepare for the subsequent long-delay adjustment action on the release screw nut.

[0065] Finally, the result output unit is set to visually output the positioning results of the alignment and release screws. The visual form includes chart information, early warning prompt information, and next operation reminders.

[0066] As an embodiment of the present invention, the test analysis unit includes:

[0067] A plurality of key points are set according to the longitudinal position coordinate parameters and the transverse position coordinate parameters of the image of the ROI area of ​​the stripping screw;

[0068] Calculate the distance parameter set from each key point of the outer contour of the ROI area image of the stripped screw to the reference center point of the ROI area image of the stripped screw , ∈ ,in, is the total number of key points;

[0069] Before acquisition The distance parameter set of each key point of the outer contour of the ROI area image of the stripping screw to the corresponding reference center point of the ROI area image of the stripping screw .

[0070] In the above technical scheme, the test analysis unit in this embodiment performs a distance analysis on the reference center point of the ROI area image of the disengaged screw, and then determines whether the current reference center of the ROI area of ​​the disengaged screw conforms to the center point of the actual disengaged screw, so as to adjust the center point; first, a plurality of key points are set according to the longitudinal position coordinate parameters and the transverse position coordinate parameters of the ROI area image of the disengaged screw; by setting the coordinate points on the outer contour of the ROI area image of the disengaged screw and the position information of the points, it is noted that the key points here include the key points for identifying the contour features of the head of the disengaged screw; for example, if the head is a polygon, the intersection of multiple edges of the head is the key point; if it is an arc-shaped head, the outer contour of the arc or circle is the intersection of the bisectors of the centers of the arc or circle as the key points, and the bisectors are determined according to actual needs.

[0071] Then, the distance parameter set from each key point of the outer contour of the ROI area image of the stripped screw to the reference center point of the ROI area image of the stripped screw is calculated respectively. , ∈ ,in, is the total number of key points; , , are all key point distance parameters; by obtaining the set of distances between each key point and the center point, the accuracy of the current center point distribution position can be reflected; then, the previous The distance parameter set of each key point of the outer contour of the ROI area image of the stripping screw to the corresponding reference center point of the ROI area image of the stripping screw , according to the set It can reflect the changes of each key point in the recognition process, and then reflect the change process of positioning tracking, provide the change trend of each key point for positioning tracking, and provide the basic data parameters of alignment and positioning changes for the alignment mechanism of test analysis.

[0072] As an embodiment of the present invention, the test analysis unit further includes:

[0073] Get the number of times in the preset historical time period A set of distance parameters for the tripping screws Each key point distance parameter within The parameter set of the curve that changes with the test time , and input it as a sample into the preset simulation test model for test analysis and judgment of the current set Whether the number of elements in meets the requirement of belonging to the preset threshold range:

[0074] If so, the simulated specific gravity of the ratio X of the number of elements that meet the requirements and the total elements in each stripping screw is output as a positioning parameter;

[0075] If not, then the ratio of the number of elements that do not meet the requirements to the total elements in each stripping screw is X ’ The simulated specific gravity is output as the warning value.

[0076] In the above technical solution, in this embodiment, after obtaining the basic data parameters of the main test, the test analysis unit performs a simulation test process on these obtained data parameters. Specifically, first, obtain the first A set of distance parameters for the tripping screws Each key point distance parameter within The parameter set of the curve that changes with the test time , and input it as a sample into a preset simulation test model for test analysis. In this embodiment, the test efficiency is improved through an automated test tool.

[0077] By analyzing the test process and judging the parameter changes, we can obtain the evaluation index, that is, to judge the current set Whether the number of elements in the screw meets the requirement of belonging to the preset threshold range; if so, the simulated proportion of the ratio of the number of elements that meet the requirements to the total elements in each stripping screw is output as the positioning parameter; if not, the ratio of the number of elements that do not meet the requirements to the total elements in each stripping screw is output as the positioning parameter. ’ The simulated specific gravity is output as the warning value.

[0078] As an implementation manner of the present invention, the positioning analysis unit:

[0079] Get the number of key points of the current stripped screw And the positioning parameters of the corresponding key points ; Through the formula Calculate the positioning state coefficient ;

[0080] in, ; is the visual positioning time interval, and 0< < ; is the preset function; are standard positioning parameters; is the preset positioning parameter deviation value; is the preset weight coefficient.

[0081] In the above technical solution, in this embodiment, the positioning analysis unit is set to calculate the number of key points of the current release screw and the positioning parameters of the corresponding key points. Perform calculation analysis and use the formula Calculate the positioning state coefficient , according to the positioning state coefficient The size is further analyzed to determine the changes in the positioning parameters during the positioning tracking process, to determine the stability of the changing process state, and then to determine whether the center position of the head of the release screw aligned by the alignment mechanism is offset, and then the next step of adjustment is carried out to realize the alignment adjustment and debugging process.

[0082] Among them, it needs to be explained that the preset weight coefficient , All of them are obtained by simulation based on historical experience data and will not be elaborated here; The settings are selected in advance based on the empirical data in the historical database, so they will not be described in detail here; It is a limiting function set according to historical data to ensure that the calculation result of the positioning state coefficient is within a specific and reasonable range. The limiting function is usually used in the preset performance control PPC of the control system. The form of the limiting function is specifically set according to the output positioning state coefficient result form. Common limiting functions include saturation function, hysteresis function, etc.

[0083] As an embodiment of the present invention, the result of the visual positioning analysis includes:

[0084] Positioning state coefficient and preset positioning state coefficient threshold To compare:

[0085] like ≥ , it is determined that the current alignment release screw center position is offset and an adjustment strategy is generated.

[0086] In the above technical scheme, this embodiment adjusts the alignment process of the disengaging screw according to the positioning state coefficient obtained in the above scheme. When the positioning state coefficient is greater than the set threshold, it means that the center position of the currently aligned disengaging screw is offset. Therefore, the alignment mechanism is adjusted in time to ensure the accuracy of the center position of the aligned disengaging screw.

[0087] As an implementation mode of the present invention, the adjustment strategy includes:

[0088] Preset the initial load, initial alignment distance, and initial alignment accuracy of the alignment mechanism based on the historical servo motor motion control system;

[0089] The initial load, initial alignment distance and initial alignment accuracy of the alignment mechanism are adjusted according to the visual positioning analysis results.

[0090] In the above technical scheme, the adjustment strategy in this embodiment is based on visual positioning, and mainly considers that in the actual positioning process, system parameter requirements such as load size, moving adjustment distance and adjustment accuracy need to be taken into account. The initial load, initial alignment distance and initial alignment accuracy of the alignment mechanism are pre-set through the historical servo motor motion control system. According to the visual positioning analysis results, the adjustment strategy is started to adjust the already set initial load, initial alignment distance and initial alignment accuracy of the alignment mechanism, so as to ensure that the adjustment strategy realizes the process of adjusting and changing the alignment parameter results.

[0091] As an implementation mode of the present invention, the adjustment strategy generates a control instruction to control the servo motor to perform axial adjustment on the alignment mechanism in the following manner:

[0092] Generate control instructions for motion control adjustment: within the specified power-on time, the center of the concentric dual flexible axis and the center of the screw are tracked according to the image positioning results, and the servo motor is started to realize the combined movement and rotation of the concentric dual flexible axis along the Z axis to complete the adjustment action of the alignment release screw.

[0093] As an embodiment of the present invention, it also includes an adaptive unit, which is used to determine the distribution position of the ROI area image of the stripping screw in the shooting window of the industrial camera according to the position information.

[0094] In the above technical solution, the adaptive unit is also set to distribute the position information of the ROI area image of the detached screw acquired by the image acquisition unit, thereby realizing the position extraction of the ROI area image of the detached screw.

[0095] As an embodiment of the present invention, the adaptive unit includes:

[0096] Get N pixels of the ROI area image of the stripped screw and determine the mean value of the RGB red component of the N pixels of the ROI area image , RGB green component mean , RGB blue component mean ;

[0097] according to , and The historical RGB color component mean value interval of the target stripped screw is screened and obtained, and the pixel distribution interval of the key points of the image of the stripped screw ROI area is determined;

[0098] The distribution position of the ROI area image of the release screw in the shooting window of the industrial camera is obtained according to the pixel distribution interval of its key points.

[0099] In the above technical solution, the process of collecting pixel points of the ROI area image of the stripped screw by the adaptive unit in this embodiment is a process of extracting and judging the components of RGB color, and the average value of the RGB red component of N pixel points of the ROI area image is determined by screening. , RGB green component mean , RGB blue component mean Specifically, through the formula Calculate the mean of the red components of N pixels , is the red component of the RGB parameters of N pixels; through the formula Calculate the mean of the green components of N pixels , is the green component of the RGB parameters of N pixels; through the formula Calculate the mean of the blue components of N pixels , The blue component of the RGB parameters of N pixels.

[0100] Then according to , and The historical RGB color component mean interval of the target stripped screw is screened and obtained, and the pixel distribution interval of the key points of the stripped screw ROI area image is determined; this is a process of color feature analysis, and the RGB average component is determined according to the known color features of the historical stripped screws, and if the red average component range, green average component range, and blue average component range of the stripped screw ROI area are all within the range of each color component of the known standard, it is judged to meet the currently selected features; and according to the RGB component range of the normal color of the screw, combined with the mean calculation result, its pixel distribution interval is determined. For example, if the normal range of the red component of the key point [r1, r2] can be determined by analyzing the relationship with the current red mean of the stripped screw, and the relationship between the red component of other pixels and the mean of other color components of the stripped screw, the pixel distribution interval of the key point red component and others can be determined; finally, according to the pixel distribution interval of its key point, the distribution position of the stripped screw ROI area image in the shooting window of the industrial camera is obtained.

[0101] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0102] The above specific embodiments of this specification are described. Other embodiments are within the scope of the attached documents. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. A circuit breaker trip screw visual positioning system, characterized in that: include: An image acquisition unit, used to obtain the ROI area image of the stripped screw acquired by the industrial camera and transmit the position information corresponding to the ROI area image through the limit sensor; The position information includes longitudinal position coordinate parameters and transverse position coordinate parameters of the ROI area image; An image processing unit, used for grayscale processing and bilateral filtering noise reduction preprocessing of the ROI area image of the stripped screw; An image recognition unit is used to extract the outer contour of the pre-processed ROI area image of the detached screw and the reference center point of the ROI area image of the detached screw by using a Canny algorithm; A test analysis unit is used to obtain a distance parameter set of a reference center point of an image of a historically tripped screw ROI area based on the position information, and use it as a sample and input it into a preset simulation test model to perform a positioning test and output positioning parameters; The positioning analysis unit performs visual positioning analysis based on the ROI area image of the stripping screw processed by the image processing unit and the positioning parameters output by the test analysis unit to determine whether the alignment with the center position of the stripping screw is offset: If not, output the positioning result; If yes, the current operation is suspended and an adjustment strategy is generated; A release screw control unit, used to generate control instructions according to an adjustment strategy to control the servo motor to perform axial adjustment on the alignment mechanism; A result output unit, used for visually outputting the positioning result of the alignment stripping screw; The test analysis unit comprises: A plurality of key points are set according to the longitudinal position coordinate parameters and the transverse position coordinate parameters of the image of the ROI area of ​​the stripping screw; Calculate the distance parameter set from each key point of the outer contour of the ROI area image of the stripped screw to the reference center point of the ROI area image of the stripped screw , ∈ ,in, is the total number of key points; , , They are all key point distance parameters; Before acquisition The distance parameter set of each key point of the outer contour of the ROI area image of the stripping screw to the corresponding reference center point of the ROI area image of the stripping screw ; The test analysis unit also includes: Get the number of times in the preset historical time period A set of distance parameters for the tripping screws Each key point distance parameter within Curve parameter set that changes with test time , and input it as a sample into the preset simulation test model for test analysis.

2. A circuit breaker release screw visual positioning system according to claim 1, characterized in that: The method of conducting the test analysis is as follows: Will gather As a sample input into the preset simulation test model for test analysis and judgment of the current set Whether the number of elements in meets the requirement of belonging to the preset threshold range: If so, the simulated specific gravity of the ratio X of the number of elements that meet the requirements and the total elements in each stripping screw is output as a positioning parameter; If not, then the ratio of the number of elements that do not meet the requirements to the total elements in each stripping screw is X ’ The simulated specific gravity is output as the warning value.

3. A circuit breaker release screw visual positioning system according to claim 2, characterized in that: The positioning analysis unit: Get the number of key points of the current stripped screw And the positioning parameters of the corresponding key points ; Through the formula Calculate the positioning state coefficient ; in, ; is the visual positioning time interval, and 0< < ; is the preset function; are standard positioning parameters; is the preset positioning parameter deviation value; is the preset weight coefficient.

4. A circuit breaker release screw visual positioning system according to claim 3, characterized in that: The results of the visual positioning analysis include: Positioning state coefficient and preset positioning state coefficient threshold To compare: like ≥ , it is determined that the current alignment release screw center position is offset and an adjustment strategy is generated.

5. A circuit breaker release screw visual positioning system according to claim 4, characterized in that: The adjustment strategies include: Preset the initial load, initial alignment distance, and initial alignment accuracy of the alignment mechanism based on the historical servo motor motion control system; The initial load, initial alignment distance and initial alignment accuracy of the alignment mechanism are adjusted according to the visual positioning analysis results.

6. A circuit breaker release screw visual positioning system according to claim 5, characterized in that: The adjustment strategy generates control instructions to control the servo motor to perform axial adjustment on the alignment mechanism in the following manner: Generate control instructions for motion control adjustment: within the specified power-on time, the center of the concentric dual flexible axis and the center of the screw are tracked according to the image positioning results, and the servo motor is started to realize the combined movement and rotation of the concentric dual flexible axis along the Z axis to complete the adjustment action of the alignment release screw.

7. A circuit breaker release screw visual positioning system according to claim 1, characterized in that: It also includes an adaptive unit, which is used to determine the distribution position of the ROI area image of the stripping screw in the shooting window of the industrial camera according to the position information.

8. A circuit breaker release screw visual positioning system according to claim 7, characterized in that: The adaptive unit comprises: Get N pixels of the ROI area image of the stripped screw and determine the mean value of the RGB red component of the N pixels of the ROI area image , RGB green component mean , RGB blue component mean ; according to , and The historical RGB color component mean value interval of the target stripped screw is screened and obtained, and the pixel distribution interval of the key points of the image of the stripped screw ROI area is determined; The distribution position of the ROI area image of the release screw in the shooting window of the industrial camera is obtained according to the pixel distribution interval of its key points.

Images