An elevator guide rail perpendicularity rapid measurement method, system and storage medium

Abstract

The application discloses a kind of elevator guide rail perpendicularity fast measurement method, system and storage medium, belong to elevator installation detection and intelligent measurement technical field, the method includes: in multiple height positions acquisition laser light spot image;After image is preprocessed, extract light spot center pixel coordinates, and synchronous record height information;With starting point light spot center as reference, pixel offset vector is calculated point by point, and it is converted into actual displacement of horizontal and vertical direction according to pixel-actual length conversion relationship of pre-calibration;According to height order, construct two-dimensional offset matrix and measurement result matrix, the offset distribution of the guide rail to be measured along the height direction is detected, and the guide rail perpendicularity measurement result is generated.The application realizes continuous segmented detection of guide rail in laser plumb and vision fusion mode, avoids error accumulation, has the advantages of high detection efficiency, strong anti-interference ability, intuitive result, and is suitable for elevator installation acceptance and regular maintenance.

Description

Technical Field

[0001] This invention relates to a method, system, and storage medium for rapid measurement of the verticality of elevator guide rails, belonging to the field of elevator installation inspection and intelligent measurement technology. Background Technology

[0002] Elevator guide rails are key components that guide the movement of the car and counterweight. Their verticality directly affects the smoothness, safety, and noise level of elevator operation. Currently, common methods for on-site guide rail verticality testing include: manual contact measurement using a plumb line, square, and gauge; measurement using a laser rangefinder attached to the elevator car as it moves; and data collection from multiple sections along the guide rail using segmented tilt sensors, followed by data aggregation. These methods suffer from low efficiency, require personnel to work at heights, allow errors to accumulate with repeated segmentation, and are highly dependent on on-site operating conditions.

[0003] On the other hand, relying solely on laser technology is hampered by uneven lighting, dust, and air turbulence within the elevator shaft, all of which interfere with laser propagation. Conversely, relying solely on machine vision technology makes it difficult to guarantee the stability and repeatability of feature extraction in an environment like the elevator shaft, which lacks rich textural features. Furthermore, existing motion-guided inspection solutions are mostly geared towards the elevator operation phase, failing to meet the real-time inspection needs during the elevator installation phase (before the car is put into use). Therefore, there is an urgent need in this field for an inspection method that can establish a high-precision vertical reference within the elevator shaft, is suitable for long-distance continuous inspection, directly characterize guide rail offset with horizontal and vertical displacement to avoid the accumulation of segmented errors, and automatically verify, identify out-of-tolerance errors, analyze trends, and generate reports on continuously acquired measurement results. This would reduce human interpretation errors and improve the consistency of installation acceptance and subsequent inspections. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, system and storage medium for rapid measurement of elevator guide rail verticality. It achieves continuous and segmentless detection of the guide rail by using laser alignment and vision fusion. By automatically verifying the measurement results, judging out-of-tolerance, analyzing trends and generating reports, it avoids error accumulation and reduces the burden of manual interpretation. It has the advantages of high detection efficiency, strong anti-interference ability, intuitive results and good consistency of detection conclusions. It is suitable for elevator installation acceptance and regular maintenance.

[0005] To achieve the above objectives, the present invention is implemented using the following technical solution:

[0006] In a first aspect, the present invention provides a method for rapid measurement of the verticality of elevator guide rails, comprising:

[0007] The laser spot images are acquired at multiple height positions by a mobile detection robot equipped with a vision acquisition device and a measurement target as it moves continuously along the guide rail to be tested. The laser source corresponding to the laser spot images is a vertical laser beam projected downward by a laser plumb bob installed at the top of the elevator shaft.

[0008] The laser spot images acquired at each height position are preprocessed sequentially to extract the center pixel coordinates of the spot corresponding to each measurement position;

[0009] The height information of each measurement location is recorded synchronously, and the coordinates of the center pixel of the light spot are associated with the corresponding height information.

[0010] Using the center pixel coordinates of the spot at the initial measurement position as the reference coordinates, the two-dimensional pixel offset vectors of the center pixel coordinates of the spot at the remaining measurement positions relative to the reference coordinates are calculated point by point.

[0011] Based on the pre-defined conversion relationship between pixels and actual length, the two-dimensional pixel offset vectors at each measurement position are converted into actual two-dimensional displacement vectors to obtain the horizontal and vertical offsets at the corresponding measurement positions.

[0012] Arrange the horizontal and vertical offsets of each measurement position in order of height from low to high or from high to low to construct a two-dimensional offset matrix, and integrate it with the height information to form a measurement result matrix;

[0013] Based on the measurement result matrix, the offset distribution of the guide rail under test along the height direction is detected, and the abnormal points, out-of-tolerance positions and offset trends corresponding to the horizontal and vertical offsets at each measurement position are identified. The verticality measurement results of the elevator guide rail are obtained and output.

[0014] Furthermore, the laser spot images acquired at each height position are preprocessed sequentially, including:

[0015] The original laser spot image is remapped using the mapping matrix obtained by pre-calibration of the camera to eliminate lens distortion and obtain a distortion-corrected image;

[0016] The distortion-corrected image is converted from the BGR color space to the HSV color space, first adjusting the luminance component. Filtering is performed, and then threshold segmentation is carried out based on the hue, saturation, and brightness characteristics of the laser spot to generate a candidate spot binary mask. The candidate spot binary mask is located at each pixel. The value of Represented as:

[0017] ;

[0018] in , , Each pixel Hue, saturation, and brightness components, , These are the upper and lower threshold values ​​for the hue corresponding to the color of the light spot. This is the lower limit threshold for saturation. This is the lower limit threshold for brightness.

[0019] The candidate spot binary mask is subjected to morphological processing, which includes opening and closing operations, to remove small noise points and fill the holes inside the spot.

[0020] Contour extraction and spot center localization are performed on the candidate regions after morphological processing.

[0021] Furthermore, the lower limit threshold of brightness The value is adaptively determined based on the brightness statistics within a preset region of interest in the distortion-corrected image. The calculation formula is as follows:

[0022] ;

[0023] in, and These are the mean brightness and standard deviation of all pixels within a preset region of interest before performing brightness lower limit threshold segmentation; the preset region of interest is determined based on the position of the target in the image. This is the threshold adjustment coefficient.

[0024] Furthermore, the spot center localization employs a sub-pixel spot center localization method based on candidate spot region screening and gray-level weighted moment calculation, including:

[0025] Connectivity analysis was performed on the morphologically processed candidate regions to obtain multiple candidate spot regions. ;

[0026] For the Calculate the area of ​​each candidate region. ,perimeter Average brightness and roundness , including roundness Represented as:

[0027] ;

[0028] A candidate region scoring function is established based on spot area, circularity, and average brightness.

[0029] ;

[0030] in , , These are the weighting coefficients. The maximum area among all candidate regions. This is the maximum brightness value;

[0031] Select rating The candidate region that is the largest and satisfies the area range and circularity constraints is selected as the target spot region. ;

[0032] With the target light spot area The pixel brightness within the range is used as a weight to construct a grayscale weighted moment. The formula is:

[0033] ;

[0034] in, , These represent the power terms of the pixel coordinates at the corresponding order, used to describe the gray-level distribution characteristics of the target spot region;

[0035] The weighting function is calculated using the following formula:

[0036] ;

[0037] in, This is the estimated background brightness value. This indicates taking the non-negative part;

[0038] The coordinates of the center pixel of the light spot are obtained by the ratio of the first moment to the zeroth moment of the gray-level weighted moment. The calculation formula is:

[0039] ;

[0040] in, The gray-level weighted zero-order moment represents the sum of the weights of all effective pixels within the target spot region. , These are the gray-level weighted first moments with respect to the x and y directions, respectively, used to calculate the lateral and longitudinal coordinates of the spot center.

[0041] Furthermore, before converting the two-dimensional pixel offset vectors at each measurement location into actual two-dimensional displacement vectors, a pixel-to-actual length scale calibration step is also included:

[0042] Under shooting conditions consistent with those of the formal measurement, a target of known actual length is placed within the plane of the measurement target. The calibration object is calibrated by a vision acquisition device that captures calibration images;

[0043] Select two endpoints of the calibration object in the calibration image and calculate the pixel distance between the two endpoints. and in accordance with A scale for calculating pixel distance and actual length ;

[0044] Perform multiple independent samplings on the same calibration material and statistically analyze the scale. The mean and standard deviation are used as the conversion coefficient for subsequent measurements; when the standard deviation exceeds a preset threshold, or when the focal length, installation distance, or field of view of the visual acquisition device changes, the above calibration steps are repeated.

[0045] Furthermore, the two-dimensional pixel offset vector at each measurement position is converted into an actual two-dimensional displacement vector using the following formula:

[0046] ;

[0047] In the formula, For the first The actual two-dimensional displacement vector at each measurement location For the first A column vector of pixel coordinates of the center of the light spot at each measurement location. The column vector of pixel coordinates of the light spot center at the reference measurement position. This is the transformation matrix from the pixel coordinates obtained from the calibration to the actual length; It contains two components, horizontal and vertical, which respectively characterize the horizontal and vertical offset of the measurement position relative to the reference position;

[0048] When the horizontal proportions are the same as the vertical proportions Simplified to ,in, It is a second-order identity matrix.

[0049] Furthermore, the two-dimensional offset matrix Given an N x 2 matrix, its first... Behavior Where N is the total number of measurement locations, , The first The horizontal and vertical offsets corresponding to each measurement position;

[0050] The measurement result matrix Given an N x 3 matrix, the i-th row is... ,in For the first The measurement result matrix represents the height value corresponding to each measurement position, with height as the index, and characterizes the two-dimensional offset distribution of the guide rail under test along its height direction.

[0051] Furthermore, based on the measurement result matrix, the offset distribution of the guide rail under test along the height direction is detected, including:

[0052] Input the measurement result matrix into the workflow intelligent agent module and execute the following detection steps:

[0053] The height, horizontal offset, and vertical offset values ​​in the measurement result matrix are checked for data integrity to determine if there are any missed data points, duplicate data points, abrupt changes, or outliers.

[0054] Based on preset tolerance thresholds or testing standards, each measurement location is assessed for out-of-tolerance conditions, identifying the out-of-tolerance measurement locations and sections.

[0055] Based on the variation of offset with height, identify the trend patterns of overall tilting, local bending, or local installation offset of the guide rail.

[0056] Based on the results of the aforementioned testing steps, the verticality measurement results of the elevator guide rail are generated and output in at least one of the following formats: line graph, matrix, table, test report, or calibration suggestion.

[0057] Furthermore, as the mobile detection robot moves continuously along the guide rail to be tested, it triggers the acquisition of laser spot images at preset height intervals.

[0058] Secondly, the present invention provides a rapid measurement system for the verticality of elevator guide rails, used to implement the rapid measurement method for the verticality of elevator guide rails as described in any of the preceding claims, comprising:

[0059] The data acquisition module is used to acquire laser spot images at multiple height positions during the continuous movement of a mobile detection robot equipped with a vision acquisition device and a measurement target along the guide rail to be tested. The laser source corresponding to the laser spot image is a vertical laser beam projected downward by a laser plumb bob installed at the top of the elevator shaft.

[0060] The preprocessing module is used to preprocess the laser spot images acquired at each height position in sequence and extract the center pixel coordinates of the spot corresponding to each measurement position.

[0061] The information association module is used to synchronously record the height information of each measurement location and associate the center pixel coordinates of the light spot with the corresponding height information.

[0062] The point-by-point calculation module is used to calculate the two-dimensional pixel offset vector of the center pixel coordinates of the spot at the starting measurement position relative to the reference coordinates.

[0063] The vector conversion module is used to convert the two-dimensional pixel offset vector of each measurement position into the actual two-dimensional displacement vector according to the pre-calibrated conversion relationship between pixels and actual length, so as to obtain the horizontal and vertical offset of the corresponding measurement position.

[0064] The processing module is used to arrange the horizontal and vertical offsets of each measurement position in order of height from low to high or from high to low, construct a two-dimensional offset matrix, and integrate it with the height information into a measurement result matrix.

[0065] The measurement result output module is used to input the measurement result matrix into the workflow agent. The workflow agent performs data integrity verification, out-of-tolerance judgment and trend identification on the horizontal and vertical offsets of each measurement position, analyzes the offset distribution of the guide rail under test along the height direction, determines the maximum offset position and abnormal section, and obtains and outputs the verticality measurement results of the elevator guide rail.

[0066] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0067] Fourthly, the present invention provides an electronic device, comprising:

[0068] Memory, used to store computer programs / instructions;

[0069] A processor for executing the computer program / instructions to implement the steps of any of the methods described above.

[0070] Fifthly, the present invention provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of any of the methods described above.

[0071] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0072] This invention provides a method, system, and storage medium for rapid measurement of elevator guide rail verticality. It uses a vertical laser beam established by a laser plumb line as the vertical reference throughout the elevator shaft. A mobile inspection robot continuously crawls along the guide rail under test, acquiring laser spot images at multiple height positions. After preprocessing, the center pixel coordinates of the laser spots are extracted, height information is recorded synchronously, and pixel offset vectors are calculated point-by-point and converted into actual horizontal and vertical offsets. Finally, a two-dimensional offset matrix or measurement result matrix indexed by height is used to verify the verticality measurement results, identify anomalies, determine out-of-tolerance conditions, analyze trends, and generate reports. This achieves stable transmission of a high-precision vertical reference over long distances, avoiding the drawbacks of error accumulation in traditional segmented measurements. Furthermore, the laser and vision fusion method maintains good detection accuracy in complex shaft environments such as uneven lighting and dust. The guide rail offset distribution is intuitively expressed in a physically clear triplet form, independent of car operation, and applicable to multiple stages including elevator installation, acceptance, and subsequent maintenance. Attached Figure Description

[0073] Figure 1 This is a schematic diagram illustrating the operation of the mobile detection robot along the guide rail according to an embodiment of the present invention;

[0074] Figure 2 This is a flowchart of a rapid measurement method for the verticality of elevator guide rails provided in an embodiment of the present invention;

[0075] Figure 3 This is a schematic diagram of the spot image preprocessing process provided in an embodiment of the present invention;

[0076] Figure 4 This is a schematic diagram illustrating the calculation of the position and offset of the light spot image provided in an embodiment of the present invention;

[0077] Figure 5 This is a framework diagram of the mobile detection robot provided in an embodiment of the present invention.

[0078] The components include: 1. Laser plumb line; 2. Laser optical path; 3. Measurement target; 4. Visual acquisition device; 5. Control device; 6. Laser ranging module; 7. Guide rail to be measured; 8. Crawling device. Detailed Implementation

[0079] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0080] Example 1

[0081] This embodiment describes a method for rapid measurement of the verticality of elevator guide rails, including:

[0082] The laser spot images are acquired at multiple height positions by a mobile detection robot equipped with a vision acquisition device and a measurement target as it moves continuously along the guide rail to be tested. The laser source corresponding to the laser spot images is a vertical laser beam projected downward by a laser plumb bob installed at the top of the elevator shaft.

[0083] The laser spot images acquired at each height position are preprocessed sequentially to extract the center pixel coordinates of the spot corresponding to each measurement position;

[0084] The height information of each measurement location is recorded synchronously, and the coordinates of the center pixel of the light spot are associated with the corresponding height information.

[0085] Using the center pixel coordinates of the spot at the initial measurement position as the reference coordinates, the two-dimensional pixel offset vectors of the center pixel coordinates of the spot at the remaining measurement positions relative to the reference coordinates are calculated point by point.

[0086] Based on the pre-defined conversion relationship between pixels and actual length, the two-dimensional pixel offset vectors at each measurement position are converted into actual two-dimensional displacement vectors to obtain the horizontal and vertical offsets at the corresponding measurement positions.

[0087] Arrange the horizontal and vertical offsets of each measurement position in order of height from low to high or from high to low to construct a two-dimensional offset matrix, and integrate it with the height information to form a measurement result matrix;

[0088] Based on the measurement result matrix, the offset distribution of the guide rail under test along the height direction is detected, abnormal points, out-of-tolerance positions, maximum offset positions and offset trends are identified, and the verticality measurement results of the elevator guide rail are obtained and output.

[0089] like Figure 2 As shown in the figure, the method for rapid measurement of elevator guide rail verticality provided in this embodiment involves the following steps in its application process:

[0090] Step 1: Establishment and continuous acquisition of the vertical reference. For example... Figure 1As shown, a laser plumb bob 1 is fixed at the top or upper part of the elevator shaft. The laser plumb bob 1 projects a laser beam 2 downwards into the shaft, which serves as a vertical reference for measuring the verticality of the guide rail. A mobile inspection robot is mounted on the guide rail 7 to be tested and moves continuously along the guide rail 7 via a crawling device 8. The mobile inspection robot is equipped with a measurement target 3, a vision acquisition device 4, a control device 5, and a laser ranging module 6. The measurement target 3 is used to receive the laser spot projected by the laser plumb bob 1, the vision acquisition device 4 is used to acquire the image of the spot on the measurement target 3, the control device 5 is used to control the robot's movement, image acquisition, and data transmission, and the laser ranging module 6 is used to assist in obtaining the robot's current position, distance, or height information.

[0091] Step 2: Inspect the overall structure and hardware configuration of the robot. For example... Figure 5 As shown, the mobile inspection robot consists of four parts: a host user management platform, a control device, a crawling device, and a detection device. The control device uses an ESP32-S3 and a Raspberry Pi microcontroller, responsible for receiving commands from the host and scheduling crawling and data acquisition actions. The crawling device comprises a chassis system, a drive unit, and a transmission unit, enabling the robot to crawl stably along a guide rail. The detection device includes a laser emitter, a vision acquisition device, and a laser target; each module communicates with the control device via USB or a serial bus. The host user management platform is used to issue measurement tasks, receive real-time status feedback, and complete data recording and human-machine interaction. The host user management platform is also equipped with a workflow intelligent agent module, which receives the measurement result matrix, performs data verification, anomaly identification, deviation judgment, trend analysis, and report generation on the measurement data, thereby forming inspection conclusions for on-site calibration, acceptance review, and periodic inspections.

[0092] Step 3: Spot image processing and center extraction. For example... Figure 3 As shown, the original image is first remapped using a mapping matrix pre-calibrated by the camera to eliminate lens distortion. The corrected image is then converted from BGR space to HSV space, and candidate spot masks are constructed based on the hue, saturation, and brightness characteristics of the spot.

[0093] Let the HSV components of the pixels in the corrected image be respectively , , Then the candidate spot mask It can be represented as:

[0094]

[0095] in, , These are the upper and lower threshold values ​​for the hue corresponding to the color of the light spot. This is the lower limit threshold for saturation. This is the lower limit threshold for brightness. To accommodate uneven lighting, localized reflections, and dust interference within elevator shafts, the lower limit threshold for brightness is... It can be adaptively determined based on the brightness of the current image or a local area:

[0096]

[0097] in, The average brightness. The standard deviation of brightness, This is the threshold adjustment coefficient.

[0098] After obtaining the candidate spot masks, morphological opening and closing operations are performed on them to remove small noise points and fill in the internal holes of the spots. Subsequently, connected component analysis is performed on the processed candidate regions to obtain multiple candidate spot regions. For the first Calculate the area of ​​each candidate region. ,perimeter Average brightness and roundness , including roundness Represented as:

[0099]

[0100] A candidate region scoring function is established based on the characteristics of spot area, circularity, and brightness.

[0101]

[0102] in, , , These are the weighting coefficients. Select the score. The candidate region that is the largest and satisfies the area and circularity constraints is selected as the target spot region. .

[0103] In the target light spot area Within this, grayscale weighted moments are constructed using pixel brightness as the weight. Let the weighting function be:

[0104]

[0105] in, This is the estimated background brightness value. This indicates that the non-negative portion is taken. The gray-level weighted moment is defined as:

[0106] in, , These represent the power terms of the pixel coordinates at their respective orders, used to describe the grayscale distribution characteristics of the target spot region; the summation range is the target spot region. All pixels within the area. Then the sub-pixel coordinates of the spot center are:

[0107]

[0108] in, These are the pixel coordinates of the center of the light spot corresponding to the current height position. The gray-level weighted zero-order moment represents the sum of the weights of all effective pixels within the target spot region. , The first-order gray-level weighted moments with respect to the x and y directions are used to calculate the lateral and longitudinal coordinates of the spot center. Using this method, spot center localization no longer relies solely on the geometric centroid of the binary profile, but comprehensively utilizes information about the spot's color, shape, and brightness distribution, thus improving the stability and repeatability of spot center extraction in complex wellbore environments.

[0109] Step 4: Pixel-to-Actual Length Scale Calibration. Under conditions consistent with the actual measurement (camera focal length, distance between the robot and the target, and field of view), first place a calibration object of known actual length on the target plane, and then capture a calibration image using the camera. Select the two endpoints of the calibration object in the image and calculate the pixel distance between them. and with known actual length Divide by That is, to obtain the pixel-to-actual length scale under this working condition. Multiple independent samplings were performed on the same calibration object, and the statistical scale was determined. The mean and standard deviation of the data are calculated, and the mean is used as a conversion factor for subsequent measurements. If the standard deviation exceeds a preset threshold, or if the focal length, installation distance, or field of view of the visual acquisition device changes, the calibration process is repeated.

[0110] Step 5: Setting the reference point, calculating the offset, and synchronizing the height. (For example...) Figure 4 As shown, the pixel coordinates of the center of the light spot at the agreed reference measurement position S are: , No. The pixel coordinates of the center pixel of the spot at each measurement location are: Then the two-dimensional pixel offset vector is The pixel-to-actual length transformation matrix obtained during the camera calibration phase is used. This pixel offset can be converted into an actual two-dimensional displacement vector: ,in This represents the horizontal offset. This represents the vertical offset. When the camera calibration results show that the horizontal and vertical proportions are the same, It can be simplified to ,in This is a scalar proportionality coefficient. It is a second-order identity matrix. Synchronous with image acquisition, this embodiment uses a laser ranging module, chassis encoder, or vision-based pose estimation to read the height of the current position. and make it with Strict alignment in time ensures that each row of the subsequent matrix corresponds to the same physical height.

[0111] Step 6: Construction of the Measurement Matrix and Evaluation of Guide Rail Offset Status. Assuming a total of N measurement positions are collected throughout the entire process, the horizontal and vertical offsets corresponding to each position are arranged in order of height to obtain the two-dimensional offset matrix. Its scale is , No. Behavior If in Add the corresponding height value to the left of that position. Then you will get Measurement result matrix , its first Behavior During the project evaluation, separate drawings were created. and The curve is observed to track the offset trend of the guide rail along its entire length in two orthogonal directions. Simultaneously, the measurement result matrix, once formed, serves as structured input data for the workflow intelligent agent module. The workflow intelligent agent module first performs integrity checks on the height, horizontal offset, and vertical offset values ​​in the measurement result matrix to determine if there are any missed points, duplicate points, abrupt changes, or obvious outliers. Then, based on preset tolerance thresholds or detection standards, it determines whether each measurement position exceeds tolerance, and combines the trend of offset with height to identify states such as overall guide rail tilt, local bending, or local installation misalignment.

[0112] Step 7: Output and Application of Detection Results. The system inputs the horizontal and vertical offsets and corresponding height information of each measurement location into the workflow intelligent agent module. The workflow intelligent agent module then sequentially performs data integrity verification, anomaly identification, out-of-tolerance judgment, trend pattern recognition, and report generation according to a preset detection process. Specifically, the workflow intelligent agent module can determine whether there are missed samples, duplicate samples, local abrupt changes, or obvious anomalies based on the measurement result matrix; identify out-of-tolerance measurement locations and out-of-tolerance sections based on preset tolerance thresholds or detection standards; determine whether the guide rail has overall skewness, local bending, or local installation misalignment based on the change law of offset with height; and output the detection conclusions in the form of line graphs, matrices, tables, detection reports, or adjustment suggestions. The above output results are used for on-site adjustment during elevator installation, acceptance review upon completion, and periodic inspections after the elevator is put into operation. Since this method adopts a working mode of continuous travel and continuous trigger acquisition along the guide rail throughout the entire process, the entire measurement process does not require manually dividing the guide rail under test into several segments for separate measurement, nor does it require manual splicing of multiple segments of data afterward. Therefore, it can suppress the problem of segmented measurement error accumulating and amplifying along the measurement distance from the source, and reduce the workload of manual interpretation and report compilation through the workflow intelligent agent module.

[0113] This embodiment has the following beneficial effects:

[0114] (1) The vertical laser beam established by the laser plumb line is used as the vertical reference in the shaft. It has a long transmission distance and good stability. It can run through the entire elevator shaft and avoid the reference error caused by the deformation of the mechanical structure.

[0115] (2) The robot moves continuously along the guide rail and completes multi-point data collection in one go. There is no need to divide the detection section along the way, which avoids the drawbacks of frequent machine stops, manual splicing and error accumulation in traditional segmented measurement.

[0116] (3) The two sensing methods of laser and vision complement each other—laser provides a highly stable position reference, while vision is responsible for high-resolution extraction and positioning of the center of the light spot, so that this method can still maintain good detection accuracy under working conditions such as uneven lighting in the well, dust or slight airflow disturbance.

[0117] (4) The measurement results are given directly in the form of a triplet of "horizontal offset - vertical offset - height". The physical meaning is clear and easy for engineers to interpret directly. It is also easy to input the matrix into the workflow intelligent body module for automatic verification, out-of-tolerance judgment, trend recognition, review and subsequent analysis.

[0118] (5) The detection robot moves independently along the guide rail without relying on the car for movement. Therefore, this method is not only applicable to maintenance and retesting after the elevator is in operation, but also applicable to the installation and acceptance stage before the car is installed.

[0119] (6) The workflow intelligent agent module performs process-oriented result detection on continuous measurement data, which can automatically complete anomaly identification, out-of-tolerance location positioning, offset trend analysis, detection report generation and calibration suggestion output, reduce manual interpretation differences, and improve detection efficiency and conclusion consistency in the process of installation, calibration, acceptance review and regular inspection.

[0120] Example 2

[0121] This embodiment provides a rapid measurement system for the verticality of elevator guide rails, including:

[0122] The data acquisition module is used to acquire laser spot images at multiple height positions during the continuous movement of a mobile detection robot equipped with a vision acquisition device and a measurement target along the guide rail to be tested. The laser source corresponding to the laser spot image is a vertical laser beam projected downward by a laser plumb bob installed at the top of the elevator shaft.

[0123] The preprocessing module is used to preprocess the laser spot images acquired at each height position in sequence and extract the center pixel coordinates of the spot corresponding to each measurement position.

[0124] The information association module is used to synchronously record the height information of each measurement location and associate the center pixel coordinates of the light spot with the corresponding height information.

[0125] The point-by-point calculation module is used to calculate the two-dimensional pixel offset vector of the center pixel coordinates of the spot at the starting measurement position relative to the reference coordinates.

[0126] The vector conversion module is used to convert the two-dimensional pixel offset vector of each measurement position into the actual two-dimensional displacement vector according to the pre-calibrated conversion relationship between pixels and actual length, so as to obtain the horizontal and vertical offset of the corresponding measurement position.

[0127] The processing module is used to arrange the horizontal and vertical offsets of each measurement position in order of height from low to high or from high to low, construct a two-dimensional offset matrix, and integrate it with the height information into a measurement result matrix.

[0128] The measurement result output module is used to input the measurement result matrix into the workflow agent. The workflow agent performs data integrity verification, out-of-tolerance judgment and trend identification on the horizontal and vertical offsets of each measurement position, analyzes the offset distribution of the guide rail under test along the height direction, determines the maximum offset position and abnormal section, and obtains and outputs the verticality measurement results of the elevator guide rail.

[0129] The specific functions of each module described above are explained in the relevant content of the method in Embodiment 1, and will not be repeated here.

[0130] Example 3

[0131] This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0132] Example 4

[0133] This embodiment provides an electronic device, including:

[0134] Memory, used to store computer programs / instructions;

[0135] A processor for executing the computer program / instructions to implement the steps of the method described in Embodiment 1.

[0136] Example 5

[0137] This embodiment provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described in Embodiment 1.

[0138] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

[0139] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, SD cards, embedded flash memory, onboard memory, external disks, etc.) containing computer-usable program code.

[0140] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0141] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0142] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure and not to limit its protection scope. Although this disclosure has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading this disclosure, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims.

Claims

1. A method for rapid measurement of the verticality of elevator guide rails, characterized in that, include: The laser spot images are acquired at multiple height positions by a mobile detection robot equipped with a vision acquisition device and a measurement target as it moves continuously along the guide rail to be tested. The laser source corresponding to the laser spot images is a vertical laser beam projected downward by a laser plumb bob installed at the top of the elevator shaft. The laser spot images acquired at each height position are preprocessed sequentially to extract the center pixel coordinates of the spot corresponding to each measurement position; Record the height information at each measurement location, and associate the center pixel coordinates of the light spot with the corresponding height information; Using the center pixel coordinates of the spot at the initial measurement position as the reference coordinates, the two-dimensional pixel offset vectors of the center pixel coordinates of the spot at the remaining measurement positions relative to the reference coordinates are calculated point by point. Based on the pre-defined conversion relationship between pixels and actual length, the two-dimensional pixel offset vectors at each measurement position are converted into actual two-dimensional displacement vectors to obtain the horizontal and vertical offsets at the corresponding measurement positions. Arrange the horizontal and vertical offsets of each measurement position in order of height from low to high or from high to low to construct a two-dimensional offset matrix, and integrate it with the height information to form a measurement result matrix; Based on the measurement result matrix, the offset distribution of the guide rail under test along the height direction is detected, and the abnormal points, out-of-tolerance positions and offset trends corresponding to the horizontal and vertical offsets at each measurement position are identified. The verticality measurement results of the elevator guide rail are obtained and output.

2. The method for rapid measurement of elevator guide rail verticality according to claim 1, characterized in that, The laser spot images acquired at each height position are preprocessed sequentially, including: The original laser spot image is remapped using the mapping matrix obtained by pre-calibration of the camera to eliminate lens distortion and obtain a distortion-corrected image; The distortion-corrected image is converted from the BGR color space to the HSV color space, first adjusting the luminance component. Filtering is performed, and then threshold segmentation is carried out based on the hue, saturation, and brightness characteristics of the laser spot to generate a candidate spot binary mask. The candidate spot binary mask is located at each pixel. The value of Represented as: ； in , , Each pixel Hue, saturation, and brightness components, , These are the upper and lower threshold values ​​for the hue corresponding to the color of the light spot. This is the lower limit threshold for saturation. This is the lower limit threshold for brightness. The candidate spot binary mask is subjected to morphological processing, which includes opening and closing operations, to remove small noise points and fill the holes inside the spot. Contour extraction and spot center localization are performed on the candidate regions after morphological processing.

3. The method for rapid measurement of elevator guide rail verticality according to claim 2, characterized in that, The lower limit threshold of brightness The value is adaptively determined based on the brightness statistics within a preset region of interest in the distortion-corrected image. The calculation formula is as follows: ； in, and These are the mean brightness and standard deviation of all pixels within a preset region of interest before performing brightness lower limit threshold segmentation; the preset region of interest is determined based on the position of the target in the image. This is the threshold adjustment coefficient.

4. The method for rapid measurement of elevator guide rail verticality according to claim 2, characterized in that, The spot center localization employs a sub-pixel spot center localization method based on candidate spot region screening and gray-level weighted moment calculation, including: Connectivity analysis was performed on the morphologically processed candidate regions to obtain multiple candidate spot regions. ; For the Calculate the area of ​​each candidate region. ,perimeter Average brightness and roundness , including roundness Represented as: ； A candidate region scoring function is established based on spot area, circularity, and average brightness. ； in , , These are the weighting coefficients. The maximum area among all candidate regions. This is the maximum brightness value; Select rating The candidate region that is the largest and satisfies the area range and circularity constraints is selected as the target spot region. ; With the target light spot area The pixel brightness within the range is used as a weight to construct a grayscale weighted moment. The formula is: ； in, , These represent the power terms of the pixel coordinates at the corresponding order, used to describe the gray-level distribution characteristics of the target spot region; The weighting function is calculated using the following formula: ； in, This is the estimated background brightness value. This indicates taking the non-negative part; The coordinates of the center pixel of the light spot are obtained by the ratio of the first moment to the zeroth moment of the gray-level weighted moment. The calculation formula is: ； in, The gray-level weighted zero-order moment represents the sum of the weights of all effective pixels within the target spot region. , These are the gray-level weighted first moments with respect to the x and y directions, respectively, used to calculate the lateral and longitudinal coordinates of the spot center.

5. The method for rapid measurement of elevator guide rail verticality according to claim 1, characterized in that, Before converting the two-dimensional pixel offset vectors at each measurement location into actual two-dimensional displacement vectors, a pixel-to-actual length scale calibration step is also included: Under shooting conditions consistent with those of the formal measurement, a target of known actual length is placed within the plane of the measurement target. The calibration object is calibrated by a vision acquisition device that captures calibration images; Select two endpoints of the calibration object in the calibration image and calculate the pixel distance between the two endpoints. and in accordance with A scale for calculating pixel distance and actual length ; Perform multiple independent samplings on the same calibration material and statistically analyze the scale. The mean and standard deviation are used as the conversion coefficient for subsequent measurements; when the standard deviation exceeds a preset threshold, or when the focal length, installation distance, or field of view of the visual acquisition device changes, the above calibration steps are repeated.

6. The method for rapid measurement of elevator guide rail verticality according to claim 5, characterized in that, The formula for converting the two-dimensional pixel offset vector at each measurement position into an actual two-dimensional displacement vector is as follows: ； In the formula, For the first The actual two-dimensional displacement vector at each measurement location For the first A column vector of pixel coordinates of the center of the light spot at each measurement location. The column vector of pixel coordinates of the light spot center at the reference measurement position. This is the transformation matrix from the pixel coordinates obtained from the calibration to the actual length; It contains two components, horizontal and vertical, which respectively characterize the horizontal and vertical offset of the measurement position relative to the reference position; When the horizontal proportions are the same as the vertical proportions Simplified to ,in, It is a second-order identity matrix.

7. The method for rapid measurement of elevator guide rail verticality according to claim 1, characterized in that, The two-dimensional offset matrix Given an N x 2 matrix, its first... Behavior Where N is the total number of measurement locations, , The first The horizontal and vertical offsets corresponding to each measurement position; The measurement result matrix Given an N x 3 matrix, the i-th row is... ,in For the first The height values ​​corresponding to each measurement location; the measurement result matrix Using height as an index, the two-dimensional offset distribution of the guide rail under test along its height direction is characterized.

8. The method for rapid measurement of elevator guide rail verticality according to claim 1, characterized in that, Based on the measurement result matrix, the offset distribution of the guide rail under test along the height direction is detected, including: Input the measurement result matrix into the workflow intelligent agent module and execute the following detection steps: The height, horizontal offset, and vertical offset values ​​in the measurement result matrix are checked for data integrity to determine if there are any missed data points, duplicate data points, abrupt changes, or outliers. Based on preset tolerance thresholds or testing standards, each measurement location is assessed for out-of-tolerance conditions, identifying the out-of-tolerance measurement locations and sections. Based on the variation of offset with height, identify the trend patterns of overall tilting, local bending, or local installation offset of the guide rail. Based on the results of the aforementioned testing steps, the verticality measurement results of the elevator guide rail are generated and output in at least one of the following formats: line graph, matrix, table, test report, or calibration suggestion.

9. A rapid measurement system for the verticality of elevator guide rails, characterized in that, include: The data acquisition module is used to acquire laser spot images at multiple height positions during the continuous movement of a mobile detection robot equipped with a vision acquisition device and a measurement target along the guide rail to be tested. The laser source corresponding to the laser spot image is a vertical laser beam projected downward by a laser plumb bob installed at the top of the elevator shaft. The preprocessing module is used to preprocess the laser spot images acquired at each height position in sequence and extract the center pixel coordinates of the spot corresponding to each measurement position. The information association module is used to synchronously record the height information of each measurement location and associate the center pixel coordinates of the light spot with the corresponding height information. The point-by-point calculation module is used to calculate the two-dimensional pixel offset vector of the center pixel coordinates of the spot at the starting measurement position relative to the reference coordinates. The vector conversion module is used to convert the two-dimensional pixel offset vector of each measurement position into the actual two-dimensional displacement vector according to the pre-calibrated conversion relationship between pixels and actual length, so as to obtain the horizontal and vertical offset of the corresponding measurement position. The processing module is used to arrange the horizontal and vertical offsets of each measurement position in order of height from low to high or from high to low, construct a two-dimensional offset matrix, and integrate it with the height information into a measurement result matrix. The measurement result output module is used to input the measurement result matrix into the workflow agent. The workflow agent performs data integrity verification, out-of-tolerance judgment and trend identification on the horizontal and vertical offsets of each measurement position, analyzes the offset distribution of the guide rail under test along the height direction, determines the maximum offset position and abnormal section, and obtains and outputs the verticality measurement results of the elevator guide rail.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When executed by a processor, the computer program implements the steps of the rapid measurement method for the verticality of elevator guide rails as described in any one of claims 1 to 8.

Images