Air conditioner display control board assembly detector control method and system

Abstract

The embodiment of the invention relates to the technical field of assembly detection, and particularly discloses a control method and system of an air conditioner display control board assembly detection machine. According to the embodiment of the invention, periodic forward high-angle shooting is carried out on the air conditioner display control panel according to a preset assembly detection period; extracting a plurality of end face feature point images; performing comparison; when the air conditioner display control panel is assembled abnormally, the batch abnormal number is counted; and when the batch abnormal number is greater than a preset standard abnormal number, determining an abnormal display control board batch, and carrying out abnormal transfer. The air conditioner display control board can be subjected to periodic forward high-angle shooting, multiple end face feature point images are extracted, standard feature point data are compared, whether assembly of the air conditioner display control board is abnormal or not is judged, the batch abnormal number is counted, abnormal display control boards are determined to be subjected to abnormal transfer in batches, the detection process is simplified, the abnormal detection precision can be ensured, and meanwhile the detection efficiency is improved. The detection automation degree is improved, the batch of abnormal display control boards can be automatically determined, and abnormal transfer is carried out.

Description

Technical Field

[0001] The present invention belongs to the technical field of assembly detection, and in particular, relates to a control method and system for an assembly detection machine of an air conditioner display and control panel. Background Art

[0002] The assembly inspection of air conditioner display and control panels is a process in which a series of testing means and methods are used to verify whether the display and control panels are correctly assembled according to the design requirements and whether the various functions and performance indicators meet the product standards and user needs after they are assembled during the air conditioner production process. This process is an important part of ensuring the quality and performance of air conditioner products.

[0003] In the prior art, the inspection process for the assembly of air-conditioning display and control panels is usually complicated, requiring inspection and shooting in multiple directions to ensure whether the assembly of the air-conditioning display and control panels meets the standards. In addition, the degree of inspection automation is low, and manual judgment of batch abnormalities is required. It is impossible to automatically determine the batch of abnormal display and control panels and perform abnormal transportation. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a control method and system for an air conditioner display and control panel assembly detection machine, aiming to solve the problems raised in the background technology.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A control method for an air conditioner display and control panel assembly detection machine, the method specifically comprising the following steps:

[0007] According to the preset assembly inspection cycle, the air conditioner display and control panel is periodically photographed from the front to obtain the front-view overhead image;

[0008] Performing feature recognition on the forward overhead image to extract multiple end face feature point images;

[0009] According to the preset standard feature point data, a plurality of the end face feature point images are compared to determine whether the assembly of the air conditioner display control panel is abnormal;

[0010] When the assembly of the air conditioner display and control panel is abnormal, count the number of abnormal batches;

[0011] When the abnormal number of the batch is greater than the preset standard abnormal number, the abnormal display and control board batch is determined, and the air-conditioning display and control boards are abnormally transported according to the abnormal display and control board batch.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the periodic forward overhead shooting of the air conditioner display control panel according to the preset assembly detection cycle to obtain the forward overhead shooting image specifically includes the following steps:

[0013] According to the preset assembly inspection cycle, periodically generate shooting adjustment instructions and shooting control instructions for forward-looking downward shooting;

[0014] Sending the shooting adjustment instruction and the shooting control instruction to a target detection machine;

[0015] According to the shooting adjustment instruction, the target detection machine is adjusted to shoot in a forward direction;

[0016] According to the shooting control instruction, the target detection machine is controlled to periodically shoot the air conditioner display control panel from the forward direction to obtain the forward direction image.

[0017] As a further limitation of the technical solution of the embodiment of the present invention, the feature recognition of the forward overhead image and the extraction of multiple end face feature point images specifically include the following steps:

[0018] Performing pre-processing of denoising, graying and contrast enhancement on the forward overhead image to generate a standard photographed image;

[0019] Performing feature recognition on the standard captured image to determine a plurality of end face feature point areas;

[0020] A plurality of end face feature point images are extracted from the standard captured image according to the plurality of end face feature point regions.

[0021] As a further limitation of the technical solution of the embodiment of the present invention, the comparison of the plurality of end face feature point images according to the preset standard feature point data to determine whether the assembly of the air conditioner display control panel is abnormal specifically includes the following steps:

[0022] According to preset standard feature point data, shape comparison is performed on a plurality of end face feature point images, and a plurality of shape comparison results are recorded;

[0023] According to the preset standard feature point data, position comparison of a plurality of the end face feature point images is performed, and a plurality of position comparison results are recorded;

[0024] Based on the plurality of shape comparison results and the plurality of position comparison results, an assembly analysis is performed to determine whether the assembly of the air conditioner display and control panel is abnormal.

[0025] As a further limitation of the technical solution of the embodiment of the present invention, when the assembly of the air conditioner display and control panel is abnormal, counting the number of abnormal batches specifically includes the following steps:

[0026] When the assembly of the air conditioner display control panel is abnormal, mark the abnormal display control panel;

[0027] Generate edge statistics instructions;

[0028] According to the traceability statistics instruction and the preset traceability statistics quantity, the batch abnormality quantity of the abnormal display and control board is counted.

[0029] As a further limitation of the technical solution of the embodiment of the present invention, when the number of abnormal batches is greater than the preset standard abnormal number, determining the batch of abnormal display and control boards, and abnormally transporting the air conditioner display and control boards according to the batch of abnormal display and control boards specifically includes the following steps:

[0030] When the batch abnormality quantity is greater than the preset standard abnormality quantity, determine the abnormal forward tracing quantity and the abnormal backward tracing quantity according to the batch abnormality quantity;

[0031] Determine the abnormal forward tracing sub-batch according to the abnormal forward tracing quantity;

[0032] Determine the abnormal post-tracing sub-batch according to the abnormal post-tracing quantity;

[0033] Determine the abnormal display and control board batch by comprehensively considering the pre-abnormal tracing batch and the post-abnormal tracing batch;

[0034] According to the batch of abnormal display and control boards, the air-conditioning display and control boards are abnormally transported.

[0035] A control system for an air conditioner display and control panel assembly inspection machine, the system comprising a forward overhead shooting control unit, an image feature point recognition unit, an assembly anomaly judgment unit, an anomaly quantity statistics unit and an anomaly transport control unit, wherein:

[0036] A forward overhead photography control unit is used to periodically take forward overhead photography of the air conditioner display and control panel according to a preset assembly inspection cycle to obtain a forward overhead photography image;

[0037] An image feature point recognition unit, used to perform feature recognition on the forward overhead image and extract a plurality of end face feature point images;

[0038] An assembly abnormality judgment unit, used to compare the plurality of end face feature point images according to preset standard feature point data, and judge whether the assembly of the air conditioner display control panel is abnormal;

[0039] The abnormal quantity statistics unit is used to count the abnormal quantity of batches when the assembly of the air conditioner display and control panel is abnormal;

[0040] The abnormal transfer control unit is used to determine the batch of abnormal display and control boards when the number of abnormalities in the batch is greater than the preset standard abnormal number, and to perform abnormal transfer of the air-conditioning display and control boards according to the batch of abnormal display and control boards.

[0041] As a further limitation of the technical solution of the embodiment of the present invention, the forward-looking overhead shooting control unit specifically includes:

[0042] An instruction generation module, used to periodically generate shooting adjustment instructions and shooting control instructions for forward-looking shooting according to a preset assembly inspection cycle;

[0043] An instruction sending module, used for sending the shooting adjustment instruction and the shooting control instruction to a target detection machine;

[0044] A shooting adjustment module, used for adjusting the target detection machine to perform a forward downward shooting adjustment according to the shooting adjustment instruction;

[0045] The shooting control module is used to control the target detection machine to periodically shoot the air-conditioning display control panel from the front direction according to the shooting control instruction to obtain the front direction shooting image.

[0046] As a further limitation of the technical solution of the embodiment of the present invention, the image feature point recognition unit specifically includes:

[0047] A shape comparison module, used for comparing the shapes of the plurality of end face feature point images according to preset standard feature point data, and recording a plurality of shape comparison results;

[0048] A position comparison module, used for comparing the positions of the plurality of end face feature point images according to preset standard feature point data, and recording a plurality of position comparison results;

[0049] The abnormality judgment module is used to integrate the multiple shape comparison results and the multiple position comparison results to perform assembly analysis and judge whether the assembly of the air conditioner display and control panel is abnormal.

[0050] As a further limitation of the technical solution of the embodiment of the present invention, the abnormal transport control unit specifically includes:

[0051] A quantity determination module, used to determine the abnormal forward tracing quantity and the abnormal backward tracing quantity according to the batch abnormal quantity when the batch abnormal quantity is greater than the preset standard abnormal quantity;

[0052] A forward tracing determination module, used to determine an abnormal forward tracing sub-batch according to the abnormal forward tracing quantity;

[0053] A traceback determination module, used to determine an abnormal traceback sub-batch according to the abnormal traceback quantity;

[0054] A batch determination module, used to determine the abnormal display and control board batch by comprehensively considering the pre-abnormal tracing batch and the post-abnormal tracing batch;

[0055] The abnormal transfer module is used to perform abnormal transfer of the air-conditioning display and control panels according to the abnormal display and control panel batches.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] The embodiment of the present invention periodically shoots the air conditioner display and control panel from above according to a preset assembly detection cycle; extracts multiple end face feature point images; and compares them; when the assembly of the air conditioner display and control panel is abnormal, counts the number of batch abnormalities; when the number of batch abnormalities is greater than the preset standard abnormal number, determines the batch of abnormal display and control panels, and performs abnormal transportation. The air conditioner display and control panel can be periodically shot from above, multiple end face feature point images can be extracted, and the standard feature point data can be used for comparison to determine whether the assembly of the air conditioner display and control panel is abnormal, and the number of batch abnormalities can be counted to determine the batch of abnormal display and control panels for abnormal transportation, which simplifies the detection process and ensures the accuracy of abnormal detection. At the same time, the degree of detection automation is improved, and the batch of abnormal display and control panels can be automatically determined, and abnormal transportation can be performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0059] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0060] Figure 2 A flow chart of obtaining a forward-looking overhead image in the method provided in an embodiment of the present invention is shown.

[0061] Figure 3 A flow chart of extracting an end face feature point image in a method provided by an embodiment of the present invention is shown.

[0062] Figure 4 A flow chart of determining whether assembly is abnormal in the method provided by an embodiment of the present invention is shown.

[0063] Figure 5 A flow chart of counting the number of abnormal batches in the method provided by an embodiment of the present invention is shown.

[0064] Figure 6 A flow chart of batch transfer of abnormal display and control panels in the method provided by an embodiment of the present invention is shown.

[0065] Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0066] Figure 8 The structure block diagram of the forward overhead shooting control unit in the system provided by the embodiment of the present invention is shown.

[0067] Fig. 9 The structure block diagram of the image feature point recognition unit in the system provided by the embodiment of the present invention is shown.

[0068] Fig.10 A structural block diagram of an abnormal transport control unit in a system provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0070] It is understandable that in the prior art, the inspection process for the assembly of air-conditioning display and control panels is usually more complicated, requiring inspection and shooting in multiple directions to ensure whether the assembly of the air-conditioning display and control panels meets the standards. In addition, the degree of inspection automation is low, and manual judgment of batch abnormalities is required. It is impossible to automatically determine the batch of abnormal display and control panels and perform abnormal transportation.

[0071] To solve the above problems, the embodiment of the present invention periodically shoots the air conditioner display and control panel from the front according to the preset assembly detection cycle to obtain the front overhead image; performs feature recognition on the front overhead image to extract multiple end face feature point images; compares the multiple end face feature point images according to the preset standard feature point data to determine whether the assembly of the air conditioner display and control panel is abnormal; when the assembly of the air conditioner display and control panel is abnormal, count the number of batch abnormalities; when the number of batch abnormalities is greater than the preset standard abnormal number, determine the batch of abnormal display and control panels, and according to the batch of abnormal display and control panels, the air conditioner display and control panels are transported abnormally. The air conditioner display and control panel can be periodically shot from the front to extract multiple end face feature point images, compare them through the standard feature point data to determine whether the assembly of the air conditioner display and control panel is abnormal, count the number of batch abnormalities, determine the batch of abnormal display and control panels for abnormal transportation, simplify the detection process, and ensure the accuracy of abnormal detection. At the same time, the degree of detection automation is improved, and the batch of abnormal display and control panels can be automatically determined and transported abnormally.

[0072] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0073] Specifically, a control method for an air conditioner display and control panel assembly detection machine comprises the following steps:

[0074] Step S101: According to a preset assembly inspection cycle, the air conditioner display and control panel is periodically photographed from the front to obtain a front-view image.

[0075] In an embodiment of the present invention, according to a preset assembly inspection cycle, shooting adjustment instructions and shooting control instructions for forward overhead shooting are periodically generated, and the shooting adjustment instructions and shooting control instructions are sent to a target detection machine on the air-conditioning display and control board assembly line, so that the target detection machine adjusts the position and angle of the forward overhead shooting according to the shooting adjustment instructions. After the adjustment is completed, the target detection machine is controlled to perform periodic forward overhead shooting of the air-conditioning display and control board according to the shooting control instructions, so that the forward overhead shooting images of the assembled air-conditioning display and control board can be periodically obtained.

[0076] Specifically, Figure 2 A flow chart of obtaining a forward-looking overhead image in the method provided in an embodiment of the present invention is shown.

[0077] Among them, in the preferred embodiment provided by the present invention, the periodic forward overhead shooting of the air conditioner display control panel according to the preset assembly detection cycle, and the acquisition of the forward overhead shooting image specifically includes the following steps:

[0078] Step S1011, periodically generating shooting adjustment instructions and shooting control instructions for forward-looking downward shooting according to a preset assembly inspection cycle;

[0079] Among them, according to the preset assembly inspection cycle, the process of periodically generating the shooting adjustment instructions and shooting control instructions for the forward-looking downward shooting corresponds to the following relationship:

[0080]

[0081] Wherein, p(θ, x′, y′, f, e) represents the optimization objective function of the shooting instruction optimization cost after output minimization, θ represents the shooting angle, x′, y′ represent the coordinates of the shooting position, f represents the shooting frequency, e represents the vector of the external condition, θ0 represents the preset ideal shooting angle, x′0, y′0 represent the coordinates of the preset ideal shooting position, f0 represents the preset ideal shooting frequency, e0 represents the ideal value of the external condition, |θ-θ0| represents the difference between the current shooting angle and the ideal shooting angle, represents the Euclidean distance between the current shooting position and the ideal shooting position, |f-f0| represents the difference between the current shooting frequency and the ideal shooting frequency, |e-e0| represents the difference between the current external conditions and the ideal external conditions, I represents the number of factors affecting the external conditions, and h i (e) represents the function describing the i-th influencing factor of the external condition e, ω1 represents the weight factor of the shooting angle, ω2 represents the weight factor of the shooting position, ω3 represents the weight factor of the shooting frequency, and ω4 represents the weight factor of the external condition;

[0082] Among them, the calculation process of the function describing the influencing factors of external conditions has the following relationship:

[0083]

[0084] Among them, h(e) represents the overall influence function of external conditions, e1 represents light intensity, e2 represents temperature, and e3 represents humidity. Indicates the ideal light intensity, Indicates the ideal temperature, represents the ideal humidity, k1, k2, and k3 represent the influence coefficients of various external conditions respectively.

[0085] Step S1012, sending the shooting adjustment instruction and the shooting control instruction to the target detection machine;

[0086] Step S1013, adjusting the target detection machine to shoot in a forward direction according to the shooting adjustment instruction;

[0087] Step S1014: According to the shooting control instruction, the target detection machine is controlled to periodically shoot the air conditioner display control panel from the front direction to obtain the front direction shooting image.

[0088] In the above-mentioned process of generating shooting instructions, the present invention adopts an optimization objective function, and finds a set of shooting parameters through an optimization algorithm (such as nonlinear programming, genetic algorithm or other optimization methods) to minimize the total cost. The optimization objective function of the present invention comprehensively considers the shooting angle, position, frequency and external conditions, can comprehensively optimize the shooting plan, and adjusts the weight factor and the external condition influence coefficient according to the specific situation, so that the optimization result is more suitable for actual needs. In addition, the external condition influence function of the present invention can also be customized according to actual conditions, and can effectively cope with different external environments.

[0089] Furthermore, the air conditioner display and control panel assembly detection machine control method further includes the following steps:

[0090] Step S102: performing feature recognition on the forward overhead image to extract a plurality of end face feature point images.

[0091] In an embodiment of the present invention, a standard shot image is generated by performing pre-processing such as denoising, graying and contrast enhancement on the forward overhead image, and then feature recognition is performed on the standard shot image to determine a plurality of end face feature point areas on the upper end face of the assembled air-conditioning display and control panel, and then, according to the plurality of end face feature point areas, a plurality of end face feature point images are extracted from the standard shot image.

[0092] Specifically, Figure 3 A flow chart of extracting an end face feature point image in a method provided by an embodiment of the present invention is shown.

[0093] Among them, in the preferred embodiment provided by the present invention, the feature recognition of the forward overhead image and the extraction of multiple end face feature point images specifically include the following steps:

[0094] Step S1021, performing pre-processing of denoising, graying and contrast enhancement on the forward overhead image to generate a standard photographed image;

[0095] Step S1022, performing feature recognition on the standard captured image to determine a plurality of end face feature point areas;

[0096] The process of performing feature recognition on the standard photographed image and determining the correspondence of multiple end face feature point areas is as follows:

[0097] R=fr(C)={(x″,y″,σ,θ)|det(H G C(x″,y″,σ))-α·trace 2 (H G C(x″,y″,σ))≥T′};

[0098] Where R represents a set of multiple end face feature point regions, C represents the matrix representation of the standard captured image, fr(C) represents the feature recognition operation, x″, y″ represents the pixel coordinates in the standard captured image, σ represents the feature scale, θ represents the feature direction, and H G C(x″, y″, σ) represents the Hessian matrix of image I at point x″, y″ at scale σ, det(H G C(x″, y″, σ)) represents the determinant of the Hessian matrix, trace 2 (H G C(x″, y″, σ)) represents the trace of the Hessian matrix, α represents the parameter that adjusts the relationship between the determinant and the trace, and T′ represents the threshold for feature point detection;

[0099] Step S1023 , extracting a plurality of end face feature point images from the standard captured image according to the plurality of end face feature point regions.

[0100] In the above-mentioned feature recognition process of the standard captured image, the present invention first calculates the Hessian matrix of the standard captured image at different scales. The Hessian matrix contains second-order derivative information, so it can capture the local curvature changes in the image. Then the determinant and the trace are combined, the determinant represents the extreme value of the curvature of the local area, and the trace represents the sum of the curvature. By adjusting the parameters, the contribution of the determinant and the trace to the feature point detection can be balanced. Finally, the feature point area is determined by comparing the result of the combination of the determinant and the trace with the threshold. Then, the significant feature points in the image, that is, the end face feature point area, can be effectively identified.

[0101] Furthermore, the air conditioner display and control panel assembly detection machine control method further includes the following steps:

[0102] Step S103 , comparing the plurality of end face feature point images according to preset standard feature point data, and determining whether the assembly of the air conditioner display control panel is abnormal.

[0103] In an embodiment of the present invention, shapes of multiple end face feature point images are compared according to preset standard feature point data, and multiple shape comparison results are recorded. Positions of multiple end face feature point images are compared according to preset standard feature point data, and multiple position comparison results are recorded. Then, the multiple shape comparison results and the multiple position comparison results are combined to analyze the assembly status of the assembled air-conditioning display and control panel to determine whether the assembly of the air-conditioning display and control panel is abnormal.

[0104] It can be understood that by comparing the shapes and positions of multiple end face feature point images, it is possible to detect abnormal defects such as assembly misalignment, panel deformation, appearance damage, uneven gaps, and upper plate bulges of the assembled air-conditioning display and control panel.

[0105] Specifically, Figure 4 A flow chart of determining whether assembly is abnormal in the method provided by an embodiment of the present invention is shown.

[0106] Among them, in the preferred embodiment provided by the present invention, the comparison of the plurality of end face feature point images according to the preset standard feature point data to determine whether the assembly of the air conditioner display control panel is abnormal specifically includes the following steps:

[0107] Step S1031, comparing the shapes of the plurality of end face feature point images according to preset standard feature point data, and recording a plurality of shape comparison results;

[0108] Step S1032, comparing the positions of the plurality of end face feature point images according to the preset standard feature point data, and recording a plurality of position comparison results;

[0109] Step S1033, combining the plurality of shape comparison results and the plurality of position comparison results, performing assembly analysis, and determining whether the assembly of the air conditioner display and control panel is abnormal.

[0110] Among them, the following relationship exists in the process of performing assembly analysis and judging whether the assembly of the air conditioner display control panel is abnormal by combining the plurality of shape comparison results and the plurality of position comparison results:

[0111]

[0112] Where A represents the assembly judgment result. If A>0, it indicates abnormality, otherwise it indicates normality. ass(S, P) represents the assembly analysis operation, S represents the set of multiple shape comparison results, e represents the base of the natural logarithm, P represents the set of multiple position comparison results, N represents the number of feature points, M′ represents the number of comparison results of the nth shape feature point, M″ represents the number of comparison results of the nth position feature point, s nm′ represents the m′th comparison result of the nth shape feature point, represents the m′th preset standard value of the nth shape feature point, p nm″ represents the m″th comparison result of the nth position feature point, represents the m″th preset standard value of the nth position feature point, They represent the adjustment factors of shape and position feature points respectively, and T″ represents the threshold for judging abnormality.

[0113] In the above process of judging whether the assembly of the air conditioner display control panel is abnormal, the present invention calculates the average of the absolute deviations of multiple comparison results from the standard value for each shape feature point and position feature point, multiplies it by a weight factor and performs smoothing through a sigmoid function with an adjustment factor; finally, all shape and position comparison results are weighted and integrated. If the final value is greater than 0 after subtracting the threshold, it is judged to be abnormal, otherwise it is normal. By combining the comparison results of shape and position, the present invention can more comprehensively evaluate the assembly quality and avoid the deviation caused by a single-dimensional evaluation. It can also increase or decrease feature points as needed, flexibly adjust weights and adjustment factors, and adapt to different assembly analysis needs.

[0114] Furthermore, the air conditioner display and control panel assembly detection machine control method further includes the following steps:

[0115] Step S104, when the assembly of the air conditioner display and control panel is abnormal, counting the number of abnormal batches.

[0116] In an embodiment of the present invention, in the event of an assembly abnormality of an air-conditioning display and control board, the air-conditioning display and control board is marked as an abnormal display and control board, and an edge tracing statistical instruction is generated. Then, according to the edge tracing statistical instruction and the preset edge tracing statistical quantity, the number of occurrences of the abnormal display and control boards within the edge tracing statistical quantity is analyzed forward to obtain the batch abnormality quantity.

[0117] Specifically, Figure 5 A flow chart of counting the number of abnormal batches in the method provided by an embodiment of the present invention is shown.

[0118] Among them, in the preferred embodiment provided by the present invention, when the assembly of the air conditioner display and control panel is abnormal, counting the number of abnormal batches specifically includes the following steps:

[0119] Step S1041, when the assembly of the air conditioner display and control panel is abnormal, marking the abnormal display and control panel;

[0120] Step S1042, generating an edge tracing statistics instruction;

[0121] Step S1043, counting the number of abnormal batches of abnormal display and control boards according to the traceability statistics instruction and the preset traceability statistics quantity.

[0122] Furthermore, the air conditioner display and control panel assembly detection machine control method further includes the following steps:

[0123] Step S105, when the abnormal number of the batch is greater than the preset standard abnormal number, determine the abnormal display and control board batch, and perform abnormal transportation of the air conditioner display and control boards according to the abnormal display and control board batch.

[0124] In an embodiment of the present invention, when the number of batch abnormalities is greater than the preset standard abnormal number, it indicates that there is a serious abnormal problem. At this time, the number of forward tracing and the number of backward tracing are determined according to the number of batch abnormalities, and then the forward tracing sub-batch of the abnormality is determined according to the forward tracing number, and the backward tracing sub-batch of the abnormality is determined according to the backward tracing number. The batch of abnormal display and control boards is determined by combining the forward tracing sub-batch and the backward tracing sub-batch. According to the batch of abnormal display and control boards, the air-conditioning display and control boards are abnormally transferred, thereby realizing the abnormal batch prediction and transfer of the air-conditioning display and control boards, and avoiding the problem of greatly extending the detection time by still performing abnormal detection and abnormal processing in the event of serious abnormalities.

[0125] Specifically, Figure 6 A flow chart of batch transfer of abnormal display and control panels in the method provided by an embodiment of the present invention is shown.

[0126] Among them, in the preferred embodiment provided by the present invention, when the number of abnormal batches is greater than the preset standard abnormal number, determining the abnormal display and control board batch, and abnormally transporting the air conditioner display and control boards according to the abnormal display and control board batch specifically includes the following steps:

[0127] Step S1051, when the batch abnormality quantity is greater than the preset standard abnormality quantity, determine the abnormal forward tracing quantity and the abnormal backward tracing quantity according to the batch abnormality quantity;

[0128] Step S1052, determining an abnormal forward tracing sub-batch according to the abnormal forward tracing quantity;

[0129] Step S1053, determining the abnormal post-tracing sub-batch according to the abnormal post-tracing quantity;

[0130] Step S1054, combining the pre-abnormal tracing batch and the post-abnormal tracing batch to determine the abnormal display and control board batch;

[0131] Among them, the process of determining the abnormal display and control board batch corresponding to the abnormal display and control board batch is determined by combining the abnormal pre-tracing sub-batch and the abnormal post-tracing sub-batch, and the following relationship exists:

[0132]

[0133] Among them, E represents the batch of abnormal display and control boards determined, a u represents the abnormal forward sub-batch of the u-th batch, b u represents the abnormal post-tracing batch of the u-th batch, ω a Represents the weight factor of the abnormal front-end sub-batch, which is used to adjust the weight of the front-end sub-batch in the total number of abnormalities; ω b It represents the weight factor of the post-abnormal tracing batch, which is used to adjust the weight of the post-abnormal tracing batch in the total abnormal number. α and β represent two different adjustment factors, which are used to control the sensitivity of the exponential function. γ represents the adjustment factor of the logarithmic term, which is used to control the impact of the logarithmic function on the final result. a represents the pre-abnormal tracing batch of the th sub-batch, b represents the post-abnormal tracing batch of the lth sub-batch, L represents the number of sub-batches in a batch, and U represents the total number of batches.

[0134] In the above process of determining the abnormal display control board batch, the present invention comprehensively considers the influence of the abnormal pre-tracing sub-batch and the abnormal post-tracing sub-batch, and uses weighted and nonlinear processing items to determine the abnormal display control board batch. The calculation results are more accurate and comprehensive, and the cubic root smoothing is used to reduce the impact of extreme values. The difference and sum of the forward and backward sub-batches are adjusted nonlinearly, making the calculation process more sensitive to abnormal situations. In addition, weight factors and adjustment factors are introduced to adjust the importance and sensitivity of abnormalities in different batches according to actual conditions, with high flexibility and strong adaptability.

[0135] Step S1055, abnormally transporting the air-conditioning display and control panels according to the batch of abnormal display and control panels.

[0136] Furthermore, Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0137] Among them, in another preferred embodiment provided by the present invention, a control system for an air conditioner display and control panel assembly detection machine includes:

[0138] The forward overhead shooting control unit 101 is used to periodically shoot the air conditioner display control panel in a forward overhead shooting manner according to a preset assembly detection cycle to obtain a forward overhead shooting image.

[0139] In an embodiment of the present invention, the forward overhead shooting control unit 101 periodically generates shooting adjustment instructions and shooting control instructions for the forward overhead shooting according to a preset assembly detection cycle, and sends the shooting adjustment instructions and shooting control instructions to the target detection machine on the air-conditioning display and control board assembly production line, so that the target detection machine adjusts the position and angle of the forward overhead shooting according to the shooting adjustment instructions. After the adjustment is completed, the target detection machine is controlled to perform periodic forward overhead shooting of the air-conditioning display and control board according to the shooting control instructions, so that the forward overhead shooting images of the assembled air-conditioning display and control board can be periodically obtained.

[0140] Specifically, Figure 8 The structure block diagram of the forward overhead shooting control unit 101 in the system provided by the embodiment of the present invention is shown.

[0141] Among them, in the preferred embodiment provided by the present invention, the forward-looking overhead shooting control unit 101 specifically includes:

[0142] The instruction generation module 1011 is used to periodically generate shooting adjustment instructions and shooting control instructions for forward-looking shooting according to a preset assembly inspection cycle;

[0143] An instruction sending module 1012 is used to send the shooting adjustment instruction and the shooting control instruction to a target detection machine;

[0144] The shooting adjustment module 1013 is used to adjust the target detection machine to a forward downward shooting direction according to the shooting adjustment instruction;

[0145] The shooting control module 1014 is used to control the target detection machine to periodically shoot the air conditioner display control panel from the front direction according to the shooting control instruction to obtain the front direction shooting image.

[0146] Furthermore, the air conditioner display and control panel assembly detection machine control system also includes:

[0147] The image feature point recognition unit 102 is used to perform feature recognition on the forward overhead image and extract a plurality of end face feature point images.

[0148] In an embodiment of the present invention, the image feature point recognition unit 102 generates a standard captured image by performing pre-processing such as denoising, graying and contrast enhancement on the forward overhead image, and then performs feature recognition on the standard captured image to determine multiple end face feature point areas on the upper end face of the assembled air-conditioning display and control panel, and then extracts multiple end face feature point images from the standard captured image according to the multiple end face feature point areas.

[0149] Specifically, Fig. 9 It shows a structural block diagram of the image feature point recognition unit 102 in the system provided by an embodiment of the present invention.

[0150] Among them, in the preferred embodiment provided by the present invention, the image feature point recognition unit 102 specifically includes:

[0151] A shape comparison module 1021 is used to compare the shapes of the plurality of end face feature point images according to preset standard feature point data, and record a plurality of shape comparison results;

[0152] A position comparison module 1022 is used to compare the positions of the plurality of end face feature point images according to preset standard feature point data, and record a plurality of position comparison results;

[0153] The abnormality judgment module 1023 is used to integrate the multiple shape comparison results and the multiple position comparison results to perform assembly analysis and judge whether the assembly of the air conditioner display and control panel is abnormal.

[0154] Furthermore, the air conditioner display and control panel assembly detection machine control system also includes:

[0155] The assembly abnormality judgment unit 103 is used to compare the plurality of end surface feature point images according to preset standard feature point data to judge whether the assembly of the air conditioner display and control panel is abnormal.

[0156] In an embodiment of the present invention, the assembly abnormality judgment unit 103 compares the shapes of multiple end face feature point images according to preset standard feature point data, records multiple shape comparison results, and compares the positions of multiple end face feature point images according to preset standard feature point data, records multiple position comparison results, and then combines the multiple shape comparison results and the multiple position comparison results to analyze the assembly status of the assembled air-conditioning display and control panel to determine whether the assembly of the air-conditioning display and control panel is abnormal.

[0157] The abnormal quantity counting unit 104 is used to count the abnormal quantity of batches when the assembly of the air conditioner display and control panel is abnormal.

[0158] In an embodiment of the present invention, in the event of an assembly abnormality in an air-conditioning display and control panel, the abnormal quantity statistics unit 104 marks the air-conditioning display and control panel as an abnormal display and control panel, and generates an edge tracing statistics instruction, and then analyzes the number of occurrences of abnormal display and control panels within the edge tracing statistics quantity according to the edge tracing statistics instruction and the preset edge tracing statistics quantity to obtain the batch abnormality quantity.

[0159] The abnormal transfer control unit 105 is used to determine the batch of abnormal display and control boards when the abnormal number of the batch is greater than the preset standard abnormal number, and perform abnormal transfer of the air-conditioning display and control boards according to the abnormal display and control board batch.

[0160] In an embodiment of the present invention, when the number of batch abnormalities is greater than the preset standard abnormal number, it indicates that there is a serious abnormal problem. At this time, the abnormal transfer control unit 105 determines the abnormal forward tracing number and the abnormal backward tracing number according to the batch abnormality number, and then determines the abnormal forward tracing sub-batch of the air-conditioning display and control board according to the abnormal forward tracing number, and determines the abnormal backward tracing sub-batch of the air-conditioning display and control board according to the abnormal backward tracing number. The abnormal display and control board batch is determined by combining the abnormal forward tracing sub-batch and the abnormal backward tracing sub-batch, and the air-conditioning display and control board batch is abnormally transferred according to the abnormal display and control board batch, so as to realize the abnormal batch prediction and transfer of the air-conditioning display and control board, and avoid the problem of greatly extending the detection time by still performing abnormal detection and abnormal processing in the event of serious abnormalities.

[0161] Specifically, Fig.10 It shows a structural block diagram of the abnormal transport control unit 105 in the system provided by the embodiment of the present invention.

[0162] Among them, in the preferred embodiment provided by the present invention, the abnormal transport control unit 105 specifically includes:

[0163] The quantity determination module 1051 is used to determine the abnormal forward tracing quantity and the abnormal backward tracing quantity according to the batch abnormal quantity when the batch abnormal quantity is greater than the preset standard abnormal quantity;

[0164] A forward tracing determination module 1052 is used to determine an abnormal forward tracing sub-batch according to the abnormal forward tracing quantity;

[0165] A traceability determination module 1053 is used to determine an abnormal traceability sub-batch according to the abnormal traceability quantity;

[0166] The batch determination module 1054 is used to determine the abnormal display and control board batch by comprehensively considering the pre-abnormal tracing sub-batch and the post-abnormal tracing sub-batch;

[0167] The abnormal transfer module 1055 is used to perform abnormal transfer of the air conditioner display and control panels according to the abnormal display and control panel batches.

[0168] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0169] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0170] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0171] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0172] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A control method for an air conditioner display and control panel assembly detection machine, characterized in that: The method specifically comprises the following steps: According to the preset assembly inspection cycle, the air conditioner display and control panel is periodically photographed from the front to obtain the front-view overhead image; Performing feature recognition on the forward overhead image to extract multiple end face feature point images; According to the preset standard feature point data, a plurality of the end face feature point images are compared to determine whether the assembly of the air conditioner display control panel is abnormal; When the assembly of the air conditioner display and control panel is abnormal, count the number of abnormal batches; When the abnormal number of the batch is greater than the preset standard abnormal number, the abnormal display and control board batch is determined, and the air-conditioning display and control boards are abnormally transported according to the abnormal display and control board batch.

2. The control method of the air conditioner display and control panel assembly detection machine according to claim 1, characterized in that: According to the preset assembly inspection cycle, the air conditioner display and control panel is periodically photographed from the front and below, and obtaining the front and below-view images specifically includes the following steps: According to the preset assembly inspection cycle, periodically generate shooting adjustment instructions and shooting control instructions for forward-looking downward shooting; Sending the shooting adjustment instruction and the shooting control instruction to a target detection machine; According to the shooting adjustment instruction, the target detection machine is adjusted to shoot in a forward direction; According to the shooting control instruction, the target detection machine is controlled to periodically shoot the air conditioner display control panel from the forward direction to obtain the forward direction image.

3. The control method of the air conditioner display and control panel assembly detection machine according to claim 2, characterized in that: According to the preset assembly inspection cycle, the process of periodically generating the shooting adjustment instructions and shooting control instructions for the forward-looking downward shooting corresponds to the following relationship: Wherein, p(θ, x′, y′, f, e) represents the optimization objective function of the shooting instruction optimization cost after output minimization, θ represents the shooting angle, x′, y′ represent the coordinates of the shooting position, f represents the shooting frequency, e represents the vector of the external condition, θ0 represents the preset ideal shooting angle, x′0, y′0 represent the coordinates of the preset ideal shooting position, f0 represents the preset ideal shooting frequency, e0 represents the ideal value of the external condition, |θ-θ0| represents the difference between the current shooting angle and the ideal shooting angle, represents the Euclidean distance between the current shooting position and the ideal shooting position, |f-f0| represents the difference between the current shooting frequency and the ideal shooting frequency, |e-e0| represents the difference between the current external conditions and the ideal external conditions, I represents the number of factors affecting the external conditions, and h i (e) represents the function describing the i-th influencing factor of the external condition e, ω1 represents the weight factor of the shooting angle, ω2 represents the weight factor of the shooting position, ω3 represents the weight factor of the shooting frequency, and ω4 represents the weight factor of the external condition; Among them, the calculation process of the function describing the influencing factors of external conditions has the following relationship: Among them, h(e) represents the overall influence function of external conditions, e1 represents light intensity, e2 represents temperature, and e3 represents humidity. Indicates the ideal light intensity, Indicates the ideal temperature, represents the ideal humidity, k1, k2, and k3 represent the influence coefficients of various external conditions respectively.

4. The control method of the air conditioner display and control panel assembly detection machine according to claim 3, characterized in that: The feature recognition of the forward overhead image to extract multiple end face feature point images specifically comprises the following steps: Performing pre-processing of denoising, graying and contrast enhancement on the forward overhead image to generate a standard photographed image; Performing feature recognition on the standard captured image to determine a plurality of end face feature point areas; A plurality of end face feature point images are extracted from the standard captured image according to the plurality of end face feature point regions.

5. The control method of the air conditioner display and control panel assembly detection machine according to claim 4, characterized in that: The process of performing feature recognition on the standard captured image and determining the correspondence of multiple end face feature point areas has the following relationship: R=fr(C)={(x″,y″,σ,θ)|det(H G C(x″,y″,σ))-α·trace 2 (H G c(x″,y″,σ))≥T′}; Where R represents a set of multiple end face feature point regions, C represents a matrix representation of a standard captured image, fr(C) represents a feature recognition operation, x″, y″ represents pixel coordinates in the standard captured image, σ represents a feature scale, and θ represents a feature direction; H G C(x″, y″, σ) represents the Hessian matrix of image I at point x″, y″ at scale σ; det(H G C(x″, y″, σ)) represents the determinant of the Hessian matrix, trace 2 (H G C(x″, y″, σ)) represents the trace of the Hessian matrix, α represents a parameter for adjusting the relationship between the determinant and the trace, and T′ represents the threshold for feature point detection.

6. The control method of the air conditioner display and control panel assembly detection machine according to claim 5, characterized in that: The step of comparing the plurality of end face feature point images according to the preset standard feature point data to determine whether the assembly of the air conditioner display control panel is abnormal specifically includes the following steps: According to preset standard feature point data, shape comparison is performed on a plurality of end face feature point images, and a plurality of shape comparison results are recorded; According to the preset standard feature point data, position comparison of a plurality of the end face feature point images is performed, and a plurality of position comparison results are recorded; Based on the plurality of shape comparison results and the plurality of position comparison results, an assembly analysis is performed to determine whether the assembly of the air conditioner display and control panel is abnormal.

7. The control method of the air conditioner display and control panel assembly detection machine according to claim 6, characterized in that: Combining the plurality of shape comparison results and the plurality of position comparison results, performing assembly analysis, and judging whether the assembly of the air conditioner display control panel is abnormal, the corresponding process has the following relationship: Where A represents the assembly judgment result. If A>0, it indicates abnormality, otherwise it indicates normality. ass(S, P) represents the assembly analysis operation, S represents the set of multiple shape comparison results, e represents the base of the natural logarithm, P represents the set of multiple position comparison results, N represents the number of feature points, M′ represents the number of comparison results of the nth shape feature point, M″ represents the number of comparison results of the nth position feature point, s nm′ represents the m′th comparison result of the nth shape feature point, represents the m′th preset standard value of the nth shape feature point, p nm″ represents the m″th comparison result of the nth position feature point, represents the m″th preset standard value of the nth position feature point, They represent the adjustment factors of shape and position feature points respectively, and T″ represents the threshold for judging abnormality.

8. The control method of the air conditioner display and control panel assembly detection machine according to claim 7, characterized in that: When the assembly of the air conditioner display and control panel is abnormal, counting the number of abnormal batches specifically includes the following steps: When the assembly of the air conditioner display control panel is abnormal, mark the abnormal display control panel; Generate edge statistics instructions; According to the traceability statistics instruction and the preset traceability statistics quantity, the batch abnormality quantity of the abnormal display and control board is counted.

9. The control method of the air conditioner display and control panel assembly detection machine according to claim 8, characterized in that: When the number of abnormal batches is greater than the preset standard abnormal number, determining the abnormal display and control board batch, and abnormally transporting the air conditioner display and control boards according to the abnormal display and control board batch specifically includes the following steps: When the batch abnormality quantity is greater than the preset standard abnormality quantity, determine the abnormal forward tracing quantity and the abnormal backward tracing quantity according to the batch abnormality quantity; Determine the abnormal forward tracing sub-batch according to the abnormal forward tracing quantity; Determine the abnormal post-tracing sub-batch according to the abnormal post-tracing quantity; Determine the abnormal display and control board batch by comprehensively considering the pre-abnormal tracing batch and the post-abnormal tracing batch; Among them, the process of determining the abnormal display and control board batch corresponding to the abnormal display and control board batch is determined by combining the abnormal pre-tracing sub-batch and the abnormal post-tracing sub-batch, and the following relationship exists: Among them, E represents the batch of abnormal display and control boards determined, a u represents the abnormal forward sub-batch of the u-th batch, b u represents the abnormal post-tracing batch of the u-th batch, ω a Represents the weight factor of the abnormal front-end sub-batch, which is used to adjust the weight of the front-end sub-batch in the total number of abnormalities; ω b It represents the weight factor of the post-abnormal traceability batch, which is used to adjust the weight of the post-abnormal traceability batch in the total number of abnormalities. α and β represent two different adjustment factors, which are used to control the sensitivity of the exponential function. γ represents the adjustment factor of the logarithmic term, which is used to control the impact of the logarithmic function on the final result. l represents the abnormal forward sub-batch of the lth sub-batch, b l It represents the abnormal post-tracing sub-batch of the l-th sub-batch, L represents the number of sub-batches in a batch, and U represents the total number of batches; According to the batch of abnormal display and control boards, the air-conditioning display and control boards are abnormally transported.

10. A control system for an air conditioner display and control panel assembly inspection machine, the system applying the air conditioner display and control panel assembly inspection machine control method according to any one of claims 1 to 9, characterized in that: The system includes a forward overhead shooting control unit, an image feature point recognition unit, an assembly anomaly judgment unit, an anomaly quantity statistics unit and an anomaly transport control unit, wherein: A forward overhead photography control unit is used to periodically take forward overhead photography of the air conditioner display and control panel according to a preset assembly inspection cycle to obtain a forward overhead photography image; An image feature point recognition unit, used to perform feature recognition on the forward overhead image and extract a plurality of end face feature point images; An assembly abnormality judgment unit, used to compare the plurality of end face feature point images according to preset standard feature point data, and judge whether the assembly of the air conditioner display control panel is abnormal; The abnormal quantity statistics unit is used to count the abnormal quantity of batches when the assembly of the air conditioner display and control panel is abnormal; The abnormal transfer control unit is used to determine the batch of abnormal display and control boards when the number of abnormalities in the batch is greater than the preset standard abnormal number, and to perform abnormal transfer of the air-conditioning display and control boards according to the batch of abnormal display and control boards.

Images