Steel wire rope tension detection method and steel wire rope tension detection device

Abstract

The embodiment of the invention provides a steel wire rope tension detection method and a steel wire rope tension detection device.The method comprises the steps that under the condition that a steel wire rope is excited, a detection video of the steel wire rope is collected in real time, and the detection video comprises multiple pieces of image data on the time sequence; processing the detection video based on the tension detection model to obtain tension detection result data of the steel wire rope, acquiring the detection video of the excited steel wire rope in real time, and processing the detection image by using the tension detection model to obtain the tension of the steel wire rope. The problem that tension detection is inaccurate due to the fact that a sensor-based tension detection device is used in the prior art is solved, the field detection efficiency is improved, and the tension detection cost is reduced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wire rope detection, and more specifically, to a wire rope tension detection method, a wire rope tension detection device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] The tension of traditional elevator wire ropes is generally tested based on the height deviation of the rope head spring. Due to the influence of factors such as the deviation of the rope head spring stiffness and the torsion of the wire rope, it is difficult to ensure the accuracy of the wire rope tension test using traditional tension adjustment methods. In addition, as the elevator is running, the tension difference between the wire ropes will gradually increase due to the elongation and wear of the wire ropes. If it is not measured and adjusted in time, the high-stress wire ropes will wear faster, greatly reducing the fatigue life of the wire ropes. The amplitude of the low-stress wire ropes will increase. In severe cases, they will hit the wire rope guard plate and other parts with a small distance from the wire rope, generating abnormal noise, causing wire rope wear and reducing ride comfort.

[0003] At present, the relevant technology detects the tension of the wire rope by testing sensors and equipping special testing equipment. However, the testing equipment needs to be inspected and calibrated regularly every year to ensure the reliability of the measurement. Since it is difficult to ensure regular inspection and calibration of the tools used on site in practice, the accuracy of actual detection is low.

[0004] Public Content

[0005] In order to solve the technical problems in the prior art, the present disclosure provides a wire rope tension detection method, a wire rope tension detection device, an electronic device, a computer-readable storage medium and a computer program product.

[0006] In order to achieve the above object, the present disclosure provides a method for detecting the tension of a steel wire rope, comprising:

[0007] When the steel wire rope is excited, a detection video of the steel wire rope is collected in real time, wherein the detection video includes a plurality of image data in a time sequence;

[0008] The detection video is processed based on the tension detection model to obtain the tension detection result data of the wire rope.

[0009] According to an embodiment of the present disclosure, when the steel wire rope is excited, real-time acquisition of the detection video of the steel wire rope includes:

[0010] Using an excitation device to excite the steel wire rope so as to make the steel wire rope shake;

[0011] The detection video is collected, wherein the shape and position of the steel wire rope in two adjacent image data are different.

[0012] According to an embodiment of the present disclosure, the steel wire rope is excited by an excitation device so as to make the steel wire rope shake, including:

[0013] Marking the position on the steel wire rope to obtain a steel wire rope including the marked position, wherein the marked position includes a mark mark made by a marking buckle;

[0014] The steel wire rope is excited by using an excitation device so that the distance between the mark position in two adjacent image data obtained and the preset mark area of ​​the image data is different.

[0015] According to an embodiment of the present disclosure, the tension detection model is trained in the following manner:

[0016] Obtaining a training set, wherein the training set includes a plurality of tension detection videos and label data corresponding to each of the tension detection videos, wherein the label data represents an actual tension parameter of the training steel wire rope in the tension detection video;

[0017] For each of the tension detection videos, input the tension detection video into the initial neural network to obtain the predicted change duration;

[0018] Based on the preset wire rope tension driving formula, the predicted tension parameters are generated according to the above-mentioned predicted change duration and the training wire rope parameters;

[0019] Input the predicted tension parameter and the label data into the loss function, and output the loss result;

[0020] The network parameters of the initial neural network are iteratively adjusted according to the loss result to obtain the trained tension detection model.

[0021] According to an embodiment of the present disclosure, the tension detection video includes a plurality of tension detection images in a time sequence, and each of the tension detection images includes the training wire rope;

[0022] The tension detection video is input into the initial neural network to obtain the predicted change duration, including:

[0023] For each of the tension detection images, the tension detection image is input into a feature extraction group, and the position data of the training wire rope is output;

[0024] For any two of the tension detection images that are adjacent in time sequence, a position identification information is determined according to the two position data, wherein the position identification information indicates whether the posture of the training wire rope has changed;

[0025] The predicted change duration of the posture change of the training wire rope is determined based on the plurality of position identification information.

[0026] According to an embodiment of the present disclosure, the tension detection image is input into a feature extraction group, and the position data of the training wire rope is output, including:

[0027] Input the tension detection image into the convolution group and output feature extraction information;

[0028] The feature extraction information is input into the fully connected group, and the position data of the training wire rope is output.

[0029] According to an embodiment of the present disclosure, the above-mentioned convolution group includes at least three convolution layers, and the above-mentioned fully connected group includes at least two fully connected layers.

[0030] According to an embodiment of the present disclosure, determining the predicted change duration of the posture change of the training wire rope according to the plurality of the position identification information includes:

[0031] For each of the position identification information, when the position identification information indicates that the posture of the training steel wire rope in the two tension detection images corresponding to the position identification information changes, respectively determine the detection time of the two tension detection images;

[0032] For the plurality of detection times, determining the detection time with the shortest time as the starting time when the posture of the training wire rope changes;

[0033] The maximum detection time is determined as the end time when the posture of the training wire rope changes;

[0034] The predicted change duration is generated based on the start time and the end time.

[0035] According to an embodiment of the present disclosure, the above-mentioned preset wire rope tension driving formula is shown in formula (1):

[0036]

[0037] Wherein, T represents the predicted tension parameter, t represents the predicted change duration, L represents the length of the training wire rope, Mr represents the unit weight of the training wire rope, Mr=aX 2 -bX+c, a, b, c are all preset coefficients, and X is the rope diameter of the above training wire rope.

[0038] According to an embodiment of the present disclosure, the wire rope tension detection method further includes:

[0039] The above tension test result data is displayed in a visual form.

[0040] The present disclosure also provides a wire rope tension detection device, comprising:

[0041] An image acquisition module, used for acquiring a detection video of the steel wire rope in real time when the steel wire rope is excited, wherein the detection video includes a plurality of image data in a time sequence;

[0042] The data processing module is used to process the above detection video based on the tension detection model to obtain the tension detection result data of the above wire rope.

[0043] Another aspect of an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described above.

[0044] Another aspect of an embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method described above when executed.

[0045] Another aspect of an embodiment of the present disclosure provides a computer program product, wherein the computer program product includes computer executable instructions, and the instructions are used to implement the method described above when executed.

[0046] According to the embodiments of the present disclosure, the tension of the steel wire rope can be obtained by collecting detection videos of the excited steel wire rope in real time and processing the detection images using a tension detection model, thereby avoiding the problem of inaccurate tension detection caused by the use of sensor-based tension detection equipment in related technologies, improving on-site detection efficiency and reducing tension detection costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0048] Figure 1 A flow chart of a method for detecting tension of a steel wire rope according to an embodiment of the present disclosure is schematically shown;

[0049] Figure 2 Schematically shows a flow chart of a method for detecting tension of a steel wire rope according to another embodiment of the present disclosure;

[0050] Figure 3 A flowchart schematically shows a method for training a tension detection model according to an embodiment of the present disclosure;

[0051] Figure 4 A block diagram of a wire rope tension detection device according to an embodiment of the present disclosure is schematically shown;

[0052] Figure 5 A block diagram schematically shows a training device for a tension detection model according to an embodiment of the present disclosure;

[0053] Figure 6 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure.

[0055] The terms "include", "comprising", etc. used herein indicate the presence of the features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components. All terms used herein, including technical and scientific terms, have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0056] In this document, unless otherwise specified, directional terms such as "upper", "lower", "left", "right", "inner", "outer", etc. are used to indicate the orientation or positional relationship based on the drawings, and are only for the convenience of describing the present disclosure, and do not indicate or imply that the device, element or component referred to must have a specific orientation, be constructed or operate in a specific orientation. It should be understood that when the absolute position of the described object changes, the relative positional relationship they represent may also change accordingly. Therefore, these directional terms should not be understood as limiting the present disclosure.

[0057] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0058] Figure 1 A flow chart of a wire rope tension detection method according to an embodiment of the present disclosure is schematically shown.

[0059] like Figure 1 As shown, the wire rope tension detection method includes operations S101-S102.

[0060] In operation S101, when the steel wire rope is excited, a detection video of the steel wire rope is collected in real time, wherein the detection video includes a plurality of image data in a time sequence;

[0061] In operation S102, the detection video is processed based on the tension detection model to obtain the tension detection result data of the wire rope.

[0062] According to the embodiments of the present disclosure, the detection video can be collected by using an image acquisition module, wherein the image acquisition module can be a small electronic device such as a mobile phone, which is convenient for the staff to carry. At the same time, the processor, that is, the processor in the electronic device, processes the detection video through the internal tension detection model, so as to determine the current tension of the wire rope.

[0063] In one embodiment, when the wire rope is excited, the wire rope shakes. At this time, the image acquisition module can be used to capture a video of the shaking wire rope. After the wire rope stops shaking, the detection video can be sent to the tension detection model in the processor, so that the tension detection model outputs the tension detection result data of the wire rope according to the detection video. The tension detection result data can clearly display the tension of the wire rope.

[0064] It should be noted that the detection of the compensating wire rope mentioned above is only an example. It can also be other wire ropes in the elevator. Its detection process is the same as the detection process of the compensating wire rope, which will not be repeated here.

[0065] According to the embodiments of the present disclosure, the tension of the steel wire rope can be obtained by collecting detection videos of the excited steel wire rope in real time and processing the detection images using a tension detection model, thereby avoiding the problem of inaccurate tension detection caused by the use of sensor-based tension detection equipment in related technologies, improving on-site detection efficiency and reducing tension detection costs.

[0066] According to an embodiment of the present disclosure, when the steel wire rope is excited, real-time acquisition of a detection video of the steel wire rope includes:

[0067] Using an excitation device to excite the steel wire rope so as to make the steel wire rope shake;

[0068] The detection video is collected, wherein the shape and position of the steel wire rope in two adjacent image data are different.

[0069] In one embodiment, the excitation device can be a top rod driven by a motor, and the end of the top rod in contact with the wire rope can be a T-shaped end face. When driven by the motor, the top rod applies a certain horizontal thrust to the compensating wire rope near the compensation wheel in the elevator to cause the wire rope to bend. At this time, the image acquisition module is used to capture images, and the horizontal thrust is removed at the same time to cause the wire rope to shake until the wire rope is completely still to obtain a detection video.

[0070] Figure 2 A flow chart of a method for detecting tension of a steel wire rope according to another embodiment of the present disclosure is schematically shown.

[0071] like Figure 2 As shown, the steel wire rope is excited by using an excitation device to make the steel wire rope shake, including:

[0072] Marking a position on the steel wire rope to obtain a steel wire rope including a marked position, wherein the marked position includes a mark mark made by a marking buckle;

[0073] The steel wire rope is excited by using an excitation device so that the distances between the marking positions in two adjacent image data obtained and the preset marking areas of the image data are different.

[0074] According to an embodiment of the present disclosure, before excitation, the steel wire rope is firstly position-marked so that the tension detection model can output corresponding tension detection result data according to the position mark.

[0075] According to an embodiment of the present disclosure, after the position is marked, the excitation device is used to apply a certain horizontal thrust at the marked position. Thereafter, the horizontal thrust is canceled to cause the wire rope to shake under the action of the elevator gravity, thereby using the image acquisition module to capture detection video from the start of shaking to the stop of shaking.

[0076] Figure 3 The flowchart of the training method of the tension detection model according to the embodiment of the present disclosure is schematically shown.

[0077] like Figure 3 As shown, the training method of the tension detection model includes operations S301 to S305.

[0078] In operation S301, a training set is obtained, wherein the training set includes a plurality of tension detection videos and label data corresponding to each tension detection video, and the label data represents an actual tension parameter of the training steel wire rope in the tension detection video;

[0079] In operation S302, for each tension detection video, the tension detection video is input into an initial neural network to obtain a predicted change duration;

[0080] In operation S303, based on the preset wire rope tension driving formula, the predicted tension parameter is generated according to the predicted change duration and the training wire rope parameter;

[0081] In operation S304, the predicted tension parameter and the label data are input into a loss function, and a loss result is output;

[0082] In operation S305 , the network parameters of the initial neural network are iteratively adjusted according to the loss result to obtain a trained tension detection model.

[0083] According to an embodiment of the present disclosure, the initial neural network may be a feedforward neural network, a convolutional neural network, a recursive neural network, etc., and the loss function may be a cross entropy loss function, an L1 loss function, an L2 loss function, etc.

[0084] According to an embodiment of the present disclosure, the training wire rope parameters may refer to the wire rope's own parameters, such as length, unit weight, etc.

[0085] According to an embodiment of the present disclosure, before actually using the tension detection model, it is necessary to train the model using a training set, and input each tension detection video in the training set into an initial neural network so that the initial neural network outputs a corresponding predicted change duration. Thereafter, the predicted change duration is substituted into a preset wire rope tension driving formula to obtain the predicted tension parameters corresponding to the tension detection video, and the predicted tension parameters and the corresponding label data are input into a loss function, and the network parameters of the initial neural network are iteratively adjusted based on the loss results, thereby obtaining a tension detection model that can be used for actual use.

[0086] According to an embodiment of the present disclosure, the tension detection video includes a plurality of tension detection images in a time sequence, and each tension detection image includes a training wire rope.

[0087] According to an embodiment of the present disclosure, the tension detection video is input into the initial neural network to obtain the predicted change duration, including:

[0088] For each tension detection image, the tension detection image is input into a feature extraction group, and the position data of the training wire rope is output;

[0089] For any two adjacent tension detection images in time sequence, a position identification information is determined according to two position data, wherein the position identification information represents whether the posture of the training wire rope has changed;

[0090] The predicted change duration of the posture change of the training wire rope is determined based on the multiple position recognition information.

[0091] According to an embodiment of the present disclosure, for each tension detection image in the tension detection video, a feature extraction group is used to detect the position of the mark on the wire rope in the tension detection image to obtain the position data of the training wire rope. If the position data of the training wire rope in two adjacent tension detection images are different, it can be determined that the training wire rope has shaken at the time corresponding to the two tension detection images. At this time, corresponding position identification information representing the shaking can be generated, thereby determining the predicted change duration of the posture change of the training wire rope based on multiple position identification information.

[0092] According to an embodiment of the present disclosure, after the predicted change duration is determined, the predicted tension parameter can be obtained using a preset wire rope tension driving formula.

[0093] According to an embodiment of the present disclosure, the tension detection image is input into a feature extraction group, and the position data of the training wire rope is output, including:

[0094] Input the tension detection image into the convolution group and output feature extraction information;

[0095] The feature extraction information is input into the fully connected group, and the position data of the training wire rope is output.

[0096] According to an embodiment of the present disclosure, the convolution group includes at least three convolution layers, and the fully connected group includes at least two fully connected layers. It should be noted that the number of layers in the convolution group and the fully connected group can be set according to actual needs.

[0097] According to an embodiment of the present disclosure, the convolution group can extract the position information of the training wire rope, thereby outputting corresponding feature extraction information. The fully connected group processes the output feature extraction information to obtain the position data of the training wire rope corresponding to the tension detection image. The position data can be represented by coordinates in the image, so as to generate position identification information based on whether the coordinates in the two position data change.

[0098] According to an embodiment of the present disclosure, determining the predicted change duration of the posture change of the training wire rope according to multiple position identification information includes:

[0099] For each position identification information, when the position identification information represents that the posture of the training wire rope in two tension detection images corresponding to the position identification information changes, the detection time of the two tension detection images is determined respectively;

[0100] For multiple detection times, the detection time with the shortest time is determined as the starting time when the posture of the training wire rope changes;

[0101] The maximum detection time is determined as the end time when the posture of the training wire rope changes;

[0102] Generate the predicted change duration based on the start time and end time.

[0103] According to an embodiment of the present disclosure, since the shaking duration of the training wire rope includes the time when the shaking starts and the time when the shaking stops, it is first determined whether the position identification information represents a change in the posture of the training wire rope, that is, whether shaking occurs. If the posture changes, the detection time of the corresponding two tension detection images is determined.

[0104] According to the embodiment of the present disclosure, after the detection time of multiple tension detection images corresponding to different position identification information is obtained, the detection time with the smallest time is determined as the time when the training steel wire rope starts to shake, that is, the starting time, and similarly, the largest detection time is determined as the time when the training steel wire rope stops shaking, that is, the ending time. After determining the starting time and the ending time, the total duration of the shaking of the training steel wire rope can be determined, that is, the predicted change duration.

[0105] According to an embodiment of the present disclosure, the preset wire rope tension driving formula is shown in formula (1):

[0106]

[0107] Among them, T represents the predicted tension parameter, t represents the predicted change duration, L represents the length of the training wire rope, Mr represents the unit weight of the training wire rope, Mr=aX 2 -bX+c, a, b, c are all preset coefficients, and X is the rope diameter of the training wire rope.

[0108] According to the embodiments of the present disclosure, a, b, and c may be specifically set according to the steel wire rope actually tested. For example, for a certain type of steel wire rope, a, b, and c may be 0.005046, 0.01968, and 0.1093, respectively.

[0109] According to the embodiment of the present disclosure, the rope diameter X of the training wire rope of this model is substituted into Mr=aX 2 -bX+c, the unit weight Mr of the training steel wire rope can be obtained. Substituting the unit weight Mr, the length L of the training steel wire rope and the predicted change time t into formula (1) can determine the predicted tension parameter T of the training steel wire rope.

[0110] It should be noted that the specific steps of the tension detection result data output by the tension detection model in actual use are the same as the process of predicting the tension parameter T, which will not be repeated here.

[0111] See also Figure 2 , the wire rope tension detection method also includes:

[0112] Display the tension test result data in a visual form.

[0113] According to an embodiment of the present disclosure, the form of visualization includes but is not limited to displaying using a display device, playing using a voice device, etc.

[0114] Figure 4 A block diagram of a wire rope tension detection device according to an embodiment of the present disclosure is schematically shown.

[0115] like Figure 4 As shown, the wire rope tension detection device 400 includes an image acquisition module 410 and a data processing module 420 .

[0116] The image acquisition module 410 is used to acquire a detection video of the steel wire rope in real time when the steel wire rope is excited, wherein the detection video includes a plurality of image data in a time sequence;

[0117] The data processing module 420 is used to process the detection video based on the tension detection model to obtain the tension detection result data of the wire rope.

[0118] According to the embodiments of the present disclosure, the tension of the steel wire rope can be obtained by collecting detection videos of the excited steel wire rope in real time and processing the detection images using a tension detection model, thereby avoiding the problem of inaccurate tension detection caused by the use of sensor-based tension detection equipment in related technologies, improving on-site detection efficiency and reducing tension detection costs.

[0119] According to an embodiment of the present disclosure, the image acquisition module 410 includes an excitation unit and an acquisition unit.

[0120] An excitation unit, used for performing an excitation process on the steel wire rope by using an excitation device, so as to make the steel wire rope shake;

[0121] The acquisition unit is used to acquire the detection video, wherein the shape and position of the steel wire rope in two adjacent image data are different.

[0122] According to an embodiment of the present disclosure, the excitation unit includes a marking subunit and an excitation subunit.

[0123] A marking subunit, used for marking a position on the steel wire rope to obtain a steel wire rope including a marked position, wherein the marked position includes a marking mark made by a marking buckle;

[0124] The excitation subunit is used to use the excitation device to excite the steel wire rope so that the distance between the marked position in two adjacent image data obtained and the preset marked area of ​​the image data is different.

[0125] Figure 5 A block diagram of a training device for a tension detection model according to an embodiment of the present disclosure is schematically shown.

[0126] like Figure 5 As shown, the training device of the tension detection model includes an acquisition module 501, a obtaining module 502, a generation module 503, a loss module 504 and an adjustment module 505.

[0127] An acquisition module 501 is used to acquire a training set, wherein the training set includes a plurality of tension detection videos and label data corresponding to each tension detection video, and the label data represents an actual tension parameter of the training steel wire rope in the tension detection video;

[0128] Obtaining module 502, for each tension detection video, inputting the tension detection video into the initial neural network to obtain the predicted change duration;

[0129] A generating module 503 is used to generate a predicted tension parameter based on a preset wire rope tension driving formula, according to the predicted change duration and the training wire rope parameters;

[0130] A loss module 504, for inputting the predicted tension parameter and the label data into a loss function and outputting a loss result;

[0131] The adjustment module 505 is used to iteratively adjust the network parameters of the initial neural network according to the loss result to obtain a trained tension detection model.

[0132] According to an embodiment of the present disclosure, the tension detection video includes a plurality of tension detection images in a time sequence, and each tension detection image includes a training wire rope.

[0133] According to an embodiment of the present disclosure, the obtaining module 502 includes a feature extraction unit, a first determination unit, and a second determination unit.

[0134] A feature extraction unit is used for inputting the tension detection image into a feature extraction group for each tension detection image, and outputting position data of the training wire rope;

[0135] A first determination unit is used to determine a position identification information according to two position data for any two adjacent tension detection images in time sequence, wherein the position identification information indicates whether the posture of the training wire rope has changed;

[0136] The second determination unit is used to determine the predicted change time of the posture change of the training wire rope according to the multiple position identification information.

[0137] According to an embodiment of the present disclosure, the feature extraction unit includes a convolution subunit and a fully connected subunit.

[0138] The convolution subunit is used to input the tension detection image into the convolution group and output feature extraction information;

[0139] The fully connected subunit is used to input the feature extraction information into the fully connected group and output the position data of the training wire rope.

[0140] According to an embodiment of the present disclosure, the convolution group includes at least three convolution layers, and the fully connected group includes at least two fully connected layers.

[0141] According to an embodiment of the present disclosure, the second determining unit includes a first determining subunit, a second determining subunit, a third determining subunit, and a generating subunit.

[0142] A first determination subunit is used to determine, for each position identification information, the detection time of the two tension detection images respectively when the position identification information represents that the posture of the training wire rope in the two tension detection images corresponding to the position identification information changes;

[0143] A second determining subunit is used to determine, with respect to a plurality of detection times, a detection time with a minimum time as a starting time when the posture of the training wire rope changes;

[0144] A third determining subunit is used to determine the maximum detection time as the termination time of the posture change of the training wire rope;

[0145] The generating subunit is used to generate the predicted change duration according to the start time and the end time.

[0146] According to an embodiment of the present disclosure, the wire rope tension detection device 400 further includes a display module.

[0147] The display module is used to display the tension detection result data in a visual form.

[0148] According to the modules, units, and sub-units of the embodiments of the present disclosure, any multiple or at least part of the functions of any multiple thereof can be implemented in one module. According to the modules, units, and sub-units of the embodiments of the present disclosure, any one or more can be split into multiple modules for implementation. According to the modules, units, and sub-units of the embodiments of the present disclosure, any one or more can be at least partially implemented as a hardware circuit, such as a field programmable gate array (Field Programmable Gate Array, FPGA), a programmable logic array (Programmable Logic Arrays, PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or can be implemented by hardware or firmware of any other reasonable way of integrating or encapsulating the circuit, or implemented in any one of the three implementation modes of software, hardware, and firmware or in any appropriate combination of any of them. Alternatively, according to the modules, units, and sub-units of the embodiments of the present disclosure, one or more can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0149] For example, any of the image acquisition module 410 and the data processing module 420, or the acquisition module 501, the obtaining module 502, the generating module 503, the loss module 504, and the adjustment module 505 can be combined in one module / unit / sub-unit for implementation, or any of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, the image acquisition module 410 and the data processing module 420, or at least one of the acquisition module 501, the obtaining module 502, the generation module 503, the loss module 504 and the adjustment module 505 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in an appropriate combination of any of them. Alternatively, the image acquisition module 410 and the data processing module 420, or at least one of the acquisition module 501, the obtaining module 502, the generation module 503, the loss module 504 and the adjustment module 505 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0150] It should be noted that the wire rope tension detection device part in the embodiment of the present disclosure corresponds to the wire rope tension detection method part in the embodiment of the present disclosure. The description of the wire rope tension detection device part specifically refers to the wire rope tension detection method part, which will not be repeated here.

[0151] Similarly, the training device part of the tension detection model in the embodiment of the present disclosure corresponds to the training method part of the tension detection model in the embodiment of the present disclosure. The description of the training device part of the tension detection model specifically refers to the training method part of the tension detection model, which will not be repeated here.

[0152] Figure 6 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0153] like Figure 6As shown, the electronic device 600 according to the embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0154] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0155] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The system 600 may further include one or more of the following components connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0156] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0157] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0158] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM (Erasable Programmable Read Only Memory, EPROM) or flash memory), a portable compact disk read-only memory (Computer Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device.

[0159] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603 .

[0160] The embodiments of the present disclosure also include a computer program product, which includes a computer program, which contains program code for executing the method provided by the embodiments of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the wire rope tension detection method or the tension detection model training method provided by the embodiments of the present disclosure.

[0161] When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0162] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0163] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0164] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0165] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for detecting the tension of a steel wire rope, characterized in that: include: When the steel wire rope is excited, a detection video of the steel wire rope is collected in real time, wherein the detection video includes a plurality of image data in a time sequence; The detection video is processed based on the tension detection model to obtain the tension detection result data of the wire rope.

2. The detection method according to claim 1, characterized in that: When the steel wire rope is excited, real-time detection video of the steel wire rope is collected, including: Using an excitation device to excite the steel wire rope so as to make the steel wire rope shake; The detection video is collected, wherein the shape and position of the steel wire rope in two adjacent image data are different.

3. The detection method according to claim 2, characterized in that: The steel wire rope is excited by using an excitation device to make the steel wire rope shake, including: Marking a position on the steel wire rope to obtain a steel wire rope including a marked position, wherein the marked position includes a mark mark made by a marking buckle; The steel wire rope is excited by using an excitation device so that the distances between the marking positions in two adjacent image data obtained and the preset marking areas of the image data are different.

4. The detection method according to claim 1, characterized in that: The tension detection model is trained in the following way: Acquire a training set, wherein the training set includes a plurality of tension detection videos and label data corresponding to each of the tension detection videos, wherein the label data represents an actual tension parameter of the training steel wire rope in the tension detection video; For each of the tension detection videos, inputting the tension detection video into an initial neural network to obtain a predicted change duration; Based on a preset wire rope tension driving formula, a predicted tension parameter is generated according to the predicted change duration and the training wire rope parameters; Input the predicted tension parameter and the label data into a loss function, and output a loss result; The network parameters of the initial neural network are iteratively adjusted according to the loss result to obtain the trained tension detection model.

5. The detection method according to claim 4, characterized in that: The tension detection video includes a plurality of tension detection images in time sequence, and each of the tension detection images includes the training wire rope; The tension detection video is input into the initial neural network to obtain the predicted change duration, including: For each of the tension detection images, input the tension detection image into a feature extraction group, and output the position data of the training steel wire rope; For any two adjacent tension detection images in time sequence, a position identification information is determined according to the two position data, wherein the position identification information indicates whether the posture of the training steel wire rope has changed; The predicted change duration of the posture change of the training wire rope is determined based on the multiple position identification information.

6. The detection method according to claim 5, characterized in that: Inputting the tension detection image into a feature extraction group and outputting the position data of the training wire rope comprises: Inputting the tension detection image into a convolution group and outputting feature extraction information; The feature extraction information is input into a fully connected group, and the position data of the training wire rope is output.

7. The detection method according to claim 6, characterized in that: The convolution group includes at least three convolution layers, and the fully connected group includes at least two fully connected layers.

8. The detection method according to claim 5, characterized in that: Determining the predicted change duration of the posture change of the training wire rope according to the plurality of position identification information includes: For each of the position identification information, when the position identification information represents that the posture of the training steel wire rope in the two tension detection images corresponding to the position identification information changes, respectively determine the detection time of the two tension detection images; For the plurality of detection times, determining the detection time with the shortest time as the starting time when the posture of the training steel wire rope changes; The maximum detection time is determined as the end time of the posture change of the training steel wire rope; The predicted change duration is generated according to the start time and the end time.

9. The detection method according to any one of claims 4 to 8, characterized in that: The preset wire rope tension driving formula is shown in formula (1): Wherein, T represents the predicted tension parameter, t represents the predicted change duration, L represents the length of the training wire rope, Mr represents the unit weight of the training wire rope, Mr = aX 2 -bX+c, a, b, c are all preset coefficients, and X is the rope diameter of the training wire rope.

10. The detection method according to claim 1, characterized in that: Also includes: The tension detection result data is displayed in a visual form.

11. A wire rope tension detection device, comprising: An image acquisition module, used for acquiring a detection video of the steel wire rope in real time when the steel wire rope is excited, wherein the detection video includes a plurality of image data in a time sequence; The data processing module is used to process the detection video based on the tension detection model to obtain the tension detection result data of the wire rope.

12. An electronic device comprising: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the method according to any one of claims 1 to 10.

14. A computer program product, comprising a computer program, wherein the computer program is used to implement the method according to any one of claims 1 to 10 when executed by a processor.

Images