Intelligent belt conveyor debugging method, system, device and readable storage medium
By setting visual signs on the tape conveyor and using visual and sound recognition technology, the problem of difficult to measure the tension force of the tape conveyor is solved, and quick debugging and fault detection is achieved without additional equipment, improving operational efficiency.
Patent Information
- Application Number
- CN202311177412.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-13
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2043-09-13
AI Technical Summary
In debugging and fault detection, existing tape conveyors have problems such as difficulty in measuring tension directly, requiring additional mechanical equipment, and affecting operating efficiency.
By setting visual signs on the tape, using visual recognition and sound recognition technology to calculate the tension force and fault signal of the tape, it realizes quick debugging and fault detection without additional equipment.
The fast and accurate tension detection and fault detection of tape conveyors are realized, operating efficiency is improved, and the impact of equipment structure is reduced.
Smart Images

Figure CN117049079B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of belt conveyor control technology, and in particular to an intelligent belt conveyor debugging method, system, equipment and computer-readable storage medium. Background Art
[0002] Belt conveyor is an industrial equipment used to transport materials. It consists of a continuous belt, rollers and a drive device, which is used to transport items from one location to another. Belt conveyors play an important role in many industrial fields, such as manufacturing, logistics and warehousing, mining and quarrying, agriculture, etc. Belts are usually made of wear-resistant and high-temperature resistant materials such as rubber, polyester fiber, nylon, etc., and have a certain degree of elasticity.
[0003] The belt is usually made of wear-resistant and high-temperature resistant materials, such as rubber, polyester fiber, nylon, etc., and has a certain elasticity. The tension of the belt directly affects the working effect of the belt conveyor. After the new belt is installed, the belt conveyor often needs to be debugged. One of the tasks is to adjust the tension of the belt in order to achieve the best working condition.
[0004] However, after the tape is installed on the conveyor, it is difficult to directly measure the tension of the tape machine. It is often necessary to measure the force on the roller to indirectly measure the tension of the tape. This measurement method requires the installation of additional mechanical measuring equipment on the roller, which is more troublesome, and the equipment must be kept in a stopped state. There is a certain gap with the actual working state of the equipment, which is easy to cause measurement errors, thus affecting the debugging effect. Moreover, debugging and equipment fault detection are carried out separately, which takes a lot of time and affects the operation.
[0005] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the invention
[0006] The embodiment of the present invention provides a smart belt conveyor debugging method, comprising:
[0007] A first visual mark including two identification points is arranged on the belt of the belt conveyor, wherein a line connecting the two identification points of the first visual mark is parallel to a length direction of the belt, and when the belt is relaxed and flat, a distance between the two identification points of the first visual mark is a static distance;
[0008] Controlling the belt conveyor to enter a running state after the belt is tensioned;
[0009] When the belt conveyor is in operation, the first visual signal of the first visual identifier is collected multiple times, and a first dynamic distance between two identification points of the first visual identifier is calculated according to the first visual signal;
[0010] Calculating the elongation of the adhesive tape according to the first dynamic distance and the static distance, and determining the tension of the adhesive tape according to the elongation and a preset corresponding relationship between the elongation and the tension;
[0011] adjusting the tensioning mechanism of the belt conveyor according to the tensioning force;
[0012] When the belt conveyor is in operation, a sound signal of the belt conveyor is collected and a fault detection is performed using the sound signal.
[0013] In some embodiments of the present invention, the preset correspondence between elongation and tension force is obtained by:
[0014] The adhesive tape is stretched multiple times in advance with gradually increasing elongation rates, the tension of the adhesive tape is measured each time it is stretched, and a corresponding relationship is established between the elongation rate of each stretch and the tension; or
[0015] Other adhesive tapes of the same type as the adhesive tape are stretched multiple times in advance at gradually increasing elongation rates, the tension of the other adhesive tapes of the same type is measured each time they are stretched, and a corresponding relationship is established between the elongation rate and the tension of each stretch.
[0016] In some embodiments of the present invention, it further comprises:
[0017] A second visual mark including two identification points is provided on the adhesive tape, a line connecting the two identification points of the second visual mark is parallel to a line connecting the two identification points of the first visual mark, and when the adhesive tape is relaxed and flat, a distance between the two identification points of the second visual mark is the static distance; and a distance between the first visual mark and the second visual mark is greater than half of the width of the adhesive tape;
[0018] When the belt conveyor is in operation, the second visual signal of the second visual identifier is collected multiple times, and a second dynamic distance between two identification points of the second visual identifier is calculated according to the second visual signal;
[0019] Calculating a tension deviation rate of the adhesive tape according to the first dynamic distance, the second dynamic distance, and the static distance, and adjusting the adhesive tape according to the tension deviation rate;
[0020] The tension deviation rate is calculated according to the formula:
[0021] ,
[0022] in, G is the tension deviation rate, n is the total number of times the first visual signal is collected, For the i A first dynamic distance measured when the first visual signal is collected for the first time, m is the total number of times the second visual signal is collected, For the j A second dynamic distance measured when the second visual signal is collected for the first time, is the first static distance, is the second static distance.
[0023] In some embodiments of the present invention, the “using the sound signal to perform fault detection” specifically includes:
[0024] Performing noise reduction processing on the sound signal;
[0025] Input the processed sound signal into a pre-trained fault detection model to output a fault detection result;
[0026] If the fault detection result is that a fault exists, a device fault prompt is issued;
[0027] If the fault detection result is that there is no fault, a normal equipment prompt is issued.
[0028] In some embodiments of the present invention, a wavelet threshold denoising algorithm is used to perform denoising on the sound signal;
[0029] The decomposition layer number of the wavelet threshold denoising algorithm is 3 to 5 layers;
[0030] The wavelet function of the wavelet threshold denoising algorithm adopts any one of Haar function, Daubechies function, Symlets function or Morlet function;
[0031] The threshold of the wavelet threshold denoising algorithm adopts any one of a fixed threshold, an unbiased risk estimation threshold, a heuristic threshold or a maximum and minimum threshold.
[0032] In some embodiments of the present invention, the threshold of the wavelet threshold denoising algorithm is determined according to the following formula:
[0033] ,
[0034] in is the threshold, D1 is the detail coefficient of the first layer decomposition, The function is the median function, N is the signal length, L is the number of decomposition layers.
[0035] In some embodiments of the present invention, the threshold function of the wavelet threshold denoising algorithm is:
[0036] ,
[0037] in, is the wavelet coefficient after threshold processing, is the original wavelet coefficient, The function is a step function, is the threshold value, a To adjust the parameters.
[0038] The present invention also provides an intelligent belt conveyor debugging system, comprising:
[0039] an identification setting module, used for setting a first visual identification including two identification points on the belt of the belt conveyor, wherein a line connecting the two identification points of the first visual identification is parallel to a length direction of the belt, and when the belt is relaxed and flat, a distance between the two identification points of the first visual identification is a first static distance;
[0040] An operation control module, used for controlling the belt conveyor to enter an operation state after the belt is tensioned;
[0041] a visual measurement module, configured to collect a first visual signal of the first visual identifier for multiple times when the belt of the belt conveyor is tensioned and the belt conveyor is running, and to measure a first dynamic distance between two identification points of the first visual identifier based on the first visual signal;
[0042] a tension calculation module, configured to calculate the elongation of the adhesive tape according to the first dynamic distance and the static distance, and determine the tension of the adhesive tape according to the elongation and a preset corresponding relationship between the elongation and the tension;
[0043] A tensioning force adjustment module, used for adjusting the tensioning mechanism of the belt conveyor according to the tensioning force;
[0044] The fault detection module is used to collect the sound signal of the belt conveyor when the belt conveyor is in operation, and use the sound signal to perform fault detection.
[0045] The present invention also provides an intelligent belt conveyor debugging device, comprising:
[0046] processor;
[0047] a memory for storing processor-executable instructions;
[0048] The processor is configured to call the instructions stored in the memory to execute the method described in any one of the above embodiments.
[0049] The present invention also provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in any one of the above embodiments is implemented.
[0050] According to an intelligent belt conveyor debugging method, system, device and computer-readable storage medium of an embodiment of the present invention, visual recognition and sound recognition are used to conveniently and quickly perform tension force detection and debugging, as well as fault detection on the belt conveyor without affecting the main structure of the belt conveyor and without installing additional mechanical measuring equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 A schematic diagram showing, by way of example, a method for debugging a smart belt conveyor according to an embodiment of the present invention;
[0052] Figure 2 A block diagram of an intelligent belt conveyor debugging system according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0054] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.
[0055] It should be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0056] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.
[0057] It should be understood that in the present invention, "plurality" refers to two or more than two. "And / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.
[0058] It should be understood that in the present invention, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A and B can be determined based on A. Determining B based on A does not mean determining B based only on A, but B can also be determined based on A and / or other information. A and B match when the similarity between A and B is greater than or equal to a preset threshold.
[0059] Depending on the context, "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."
[0060] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
[0061] Figure 1 The flowchart of the intelligent belt conveyor debugging method according to the embodiment of the present invention is shown as an example. Figure 1 As shown, the method includes:
[0062] Step S101, setting a first visual identification including two identification points on the belt of the belt conveyor, the line connecting the two identification points of the first visual identification is parallel to the length direction of the belt, and when the belt is relaxed and flat, the distance between the two identification points of the first visual identification is a first static distance.
[0063] In this step, a set of first visual identifications is set on the tape, including two identification points, which can be set manually or using automated equipment. It can be achieved by marking the tape with a laser marker or using special stickers, patterns or paints. The line connecting the identification points should be parallel to the length of the tape, that is, parallel to the conveying direction of the belt conveyor. When the tape is relaxed but flat and wrinkle-free, the distance between the two identification points is measured and recorded as the static distance for the calculation of the tension in the subsequent steps.
[0064] Step S102, controlling the belt conveyor to enter a running state after the belt is tensioned.
[0065] After the first visual mark is set, the belt is initially tensioned to prevent the belt from slipping during operation, and the belt conveyor is controlled to enter the operating state.
[0066] Step S103, when the belt conveyor is in operation, collecting the first visual signal of the first visual identifier for multiple times, and calculating the first dynamic distance between two identification points of the first visual identifier according to the first visual signal.
[0067] Compared with measuring the first dynamic distance in the running state of the belt conveyor, measuring the first dynamic distance in the stopped state, on the one hand, the measurement result is closer to the state of the belt in the normal operation of the belt conveyor, and therefore has higher accuracy. On the other hand, if the first visual identifier is set at an appropriate position, for example, at the very edge of the belt, the first dynamic distance can also be measured simultaneously in the normal operation of the belt conveyor, and used to calculate the belt tension in subsequent steps, thereby realizing non-stop debugging of the belt conveyor.
[0068] The first visual signal can be collected using a camera or other type of image acquisition device, and then the image algorithm or artificial intelligence model calculates the distance between the identification points and records it as the first dynamic distance. Through multiple acquisitions and measurements, the measurement error of the first dynamic distance can be reduced. The specific image algorithm or deep learning model can adopt existing technology, which has been described in many existing technical materials and will not be repeated here.
[0069] Step S104, calculating the elongation of the adhesive tape according to the first dynamic distance and the static distance, and determining the tension of the adhesive tape according to the elongation and a preset correspondence relationship between the elongation and the tension.
[0070] According to the static distance and the first dynamic distance, the elongation of the tape between the two identification points of the first visual identification under the tensioned state of the tape can be calculated. The elongation is the percentage of the increase of the first dynamic distance relative to the static distance to the static distance, that is, , and then according to the elongation and the preset elongation and tension correspondence, for example, 5% elongation corresponds to 100 Newton tension, the tension of the tape can be determined. Different tapes may have different elongation and tension correspondences, and the elongation and tension correspondence can be established in advance through a tensile test experiment.
[0071] Step S105: adjusting the tensioning mechanism of the belt conveyor according to the tensioning force.
[0072] After calculating the current tension of the tape, the tension mechanism can be adjusted accordingly to adjust the tension of the tape to a suitable value. After adjusting the tension mechanism, the above steps S102 to S104 can be repeated to verify whether the tension has been adjusted to a suitable value. If it is still not suitable, step S105 can be performed again.
[0073] Step S106, when the belt conveyor is in operation, collecting the sound signal of the belt conveyor, and performing fault detection using the sound signal.
[0074] In the process of measuring the tension of the belt, the belt conveyor is in operation, and the sound signal of the belt conveyor can be collected at the same time, and the sound signal can be used for fault detection. A sound sensor, such as a microphone, can be used to collect the sound signal of the belt conveyor. After noise reduction or other preprocessing of the sound signal, a sound recognition algorithm or a deep learning model can be used for fault detection. For example, if the sound signal is analyzed to contain abnormal noise, it may be that a component of the conveyor has failed. The specific algorithm or deep learning model can adopt existing technology, which has been described in many existing technical materials and will not be repeated here.
[0075] Through the above method, the tensioning force detection and debugging of the belt conveyor and the fault detection can be conveniently and quickly performed without affecting the main structure of the belt conveyor and without installing mechanical measuring equipment.
[0076] In some embodiments of the present invention, the preset correspondence between elongation and tension force is obtained by:
[0077] The adhesive tape is stretched multiple times in advance with gradually increasing elongation rates, the tension of the adhesive tape is measured each time it is stretched, and a corresponding relationship is established between the elongation rate of each stretch and the tension; or
[0078] Other adhesive tapes of the same type as the adhesive tape are stretched multiple times in advance at gradually increasing elongation rates, the tension of the other adhesive tapes of the same type is measured each time they are stretched, and a corresponding relationship is established between the elongation rate and the tension of each stretch.
[0079] Different types of tapes may have different corresponding relationships between elongation and tension, so the tapes that need to be debugged can be tested in advance to establish the corresponding relationship between tension. The materials and specifications of the same type of tapes are often the same, so other tapes of the same type can also be tested in advance to establish the corresponding relationship between tension.
[0080] The tensile test can be conducted with the elongation gradually increasing. For example, 10 tests can be conducted, starting from 5%, and increasing by 5% each time until the elongation reaches 50%. During the tensile test, the tape can be stretched as a whole to measure the elongation and tension, but the tape is often very long, and this method requires a large experimental space. Therefore, only a part of the tape can be stretched, and the elongation and tension of this part can be measured to establish a corresponding relationship as the elongation and tension of the tape.
[0081] In some embodiments of the present invention, the intelligent belt conveyor debugging method further includes:
[0082] A second visual mark including two identification points is provided on the adhesive tape, a line connecting the two identification points of the second visual mark is parallel to a line connecting the two identification points of the first visual mark, and when the adhesive tape is relaxed and flat, a distance between the two identification points of the second visual mark is the static distance; and a distance between the first visual mark and the second visual mark is greater than half of the width of the adhesive tape;
[0083] When the belt conveyor is in operation, the second visual signal of the second visual identifier is collected multiple times, and a second dynamic distance between two identification points of the second visual identifier is calculated according to the second visual signal;
[0084] A tension deviation rate of the adhesive tape is calculated according to the first dynamic distance, the second dynamic distance, and the static distance, and the adhesive tape is adjusted according to the tension deviation rate.
[0085] Ideally, the axes of the rollers on the belt conveyor should be parallel to each other to ensure that the tension on both sides of the belt centerline is uniform. If the axes of some rollers are offset (especially the head roller or the tail roller), the tension on both sides of the belt centerline will be inconsistent. The inconsistent tension will lead to different elongation rates on both sides of the belt centerline. Therefore, the first visual mark and the second visual mark can be set on both sides of the belt centerline to measure the elongation rates on both sides, so as to determine the difference in tension on both sides of the belt centerline, that is, the tension deviation rate.
[0086] The second visual identification can adopt the same form and setting method as the first visual identification. The second dynamic distance between the two identification points of the second visual identification can be measured by collecting the second visual signal of the second visual identification multiple times. The specific method can be the same as the aforementioned first visual identification, which will not be repeated here.
[0087] The distance between the second visual mark and the first visual mark is greater than half of the width of the tape, so as to ensure that the two are located on both sides of the center line of the tape.
[0088] The tension deviation rate is calculated according to the following formula:
[0089] ,
[0090] in, G is the tension deviation rate, n is the total number of times the first visual signal is collected, For the i A first dynamic distance measured when the first visual signal is collected for the first time, m is the total number of times the second visual signal is collected, For the j A second dynamic distance measured when the second visual signal is collected for the first time, is the first static distance, is the second static distance.
[0091] Multiple collection and measurement can reduce the error of single collection and measurement. n and m The values may be inconsistent. For example, the first visual signal can be collected 20 times and the first dynamic distance can be measured, the second visual signal can be collected 10 times and the second dynamic distance can be measured, and then the arithmetic mean of the stretch rate on one side of the tape centerline can be calculated based on the 20 first dynamic distances, and the arithmetic mean of the stretch rate on the other side of the tape centerline can be calculated based on the 10 second dynamic distances. Subtracting the two can obtain the tension deviation rate. G , tension deviation rate G Can be negative, through G The value can be used to determine the difference in tension between the two sides of the belt centerline, thereby determining whether adjustment is needed. G The positive and negative value can determine which side of the center line of the tape is tighter and which side is looser, thereby deciding how to adjust it.
[0092] In some embodiments of the present invention, the “using the sound signal to perform fault detection” specifically includes:
[0093] Performing noise reduction processing on the sound signal;
[0094] Input the processed sound signal into a pre-trained fault detection model to output a fault detection result;
[0095] If the fault detection result is that a fault exists, a device fault prompt is issued;
[0096] If the fault detection result is that there is no fault, a normal equipment prompt is issued.
[0097] The purpose of noise reduction processing is to remove or reduce the noise introduced from the environment, equipment or other interference sources to improve the quality and clarity of the signal and highlight the fault sound. Noise reduction processing can use various digital signal processing techniques, such as filtering, spectral subtraction, wavelet function denoising algorithm or other methods. The appropriate noise reduction method can be selected according to the characteristics of the signal and the type of noise, and the signal can be processed through a filter or algorithm to reduce the interference of noise.
[0098] The fault detection model can be pre-trained by a machine learning algorithm, which can identify faults or anomalies in the sound signal. The model will analyze and compare the input signal and determine whether the signal indicates a device failure based on previous learning experience. The detection model can be built based on various algorithms, such as deep learning, support vector machines, random forests, etc.
[0099] When a fault is detected, a fault prompt is issued. This prompt can be in the form of sound, text or other forms to remind the operator or related personnel to take appropriate measures for maintenance and processing in time. The purpose of equipment fault prompt is to find and solve equipment faults in time to avoid further damage or production interruption. If no fault is detected, a normal equipment prompt is issued to remind the staff to start the machine normally.
[0100] In some embodiments of the present invention, a wavelet threshold denoising algorithm is used to perform denoising on the sound signal;
[0101] The decomposition layer number of the wavelet threshold denoising algorithm is 3 to 5 layers;
[0102] The wavelet function of the wavelet threshold denoising algorithm adopts any one of Haar function, Daubechies function, Symlets function or Morlet function;
[0103] The threshold of the wavelet threshold denoising algorithm adopts any one of a fixed threshold, an unbiased risk estimation threshold, a heuristic threshold or a maximum and minimum threshold.
[0104] The wavelet threshold denoising algorithm is a commonly used digital signal processing technology. It decomposes the signal into wavelet coefficients of different frequencies and processes these coefficients according to the threshold to remove noise and retain useful signal components. The general steps of wavelet threshold denoising belong to the existing technology, which has been documented in many literatures and can also be easily implemented through software such as MATLAB. We will not go into details here. Through wavelet threshold denoising, noise can be effectively removed, the quality and clarity of sound signals can be improved, and fault sounds can be highlighted.
[0105] In the wavelet threshold denoising algorithm, the number of decomposition layers indicates the level of wavelet decomposition of the signal. Decomposing the sound signal into lower frequency and high frequency wavelet coefficients can better capture the details and frequency characteristics of the signal. The selection of the appropriate number of decomposition layers is determined according to the characteristics and requirements of the signal. A decomposition layer number between 3 and 5 layers can achieve a better denoising effect.
[0106] Wavelet function is the basic function used for wavelet decomposition and reconstruction. You can select one from Haar function, Daubechies function, Symlets function and Morlet function as a wavelet function. The specific contents of these functions have been documented and can also be called in software such as MATLAB, so I will not go into details here. In the wavelet threshold denoising algorithm, selecting a suitable wavelet function can better adapt to the characteristics of the signal and the type of noise, thereby improving the noise reduction effect. Different wavelet functions have different frequency responses and time domain characteristics, so the selection of a suitable wavelet function is determined based on specific application requirements and signal characteristics.
[0107] In the wavelet threshold denoising algorithm, the choice of threshold is an important factor in determining the denoising effect. Different thresholds can cope with different signal characteristics and noise types. The threshold can be selected from the following categories: fixed threshold, unbiased risk estimation threshold, heuristic threshold, and maximum and minimum threshold. The specific contents of these thresholds have been described in many literatures and will not be elaborated here.
[0108] In some embodiments of the present invention, the threshold of the wavelet threshold denoising algorithm is determined according to the following formula:
[0109] ,
[0110] in is the threshold, D1 is the detail coefficient of the first layer decomposition, The function is the median function, N is the signal length, L is the number of decomposition layers.
[0111] By setting the threshold, the coefficient of the noise part can be reset to zero, thus achieving denoising.
[0112] The process of wavelet transform is to decompose the signal into a series of detail coefficients and approximate coefficients, which reflect the characteristics of the signal at different scales and positions. In the denoising process, the median of the detail coefficients of the first layer of decomposition can be used to effectively distinguish between signal and noise. Signal length refers to the number of sample points of the signal. When performing wavelet decomposition, the signal length will affect the number of decomposition layers. Generally speaking, the longer the signal length, the more decomposition layers can be performed. In the denoising process, the more decomposition layers there are, the richer the signal details can be obtained, so that the noise can be better removed. The number of decomposition layers determines the accuracy of wavelet transform. The more layers there are, the richer the signal details obtained by decomposition, and the better the characteristics of the signal can be captured. However, the number of decomposition layers cannot be too many, otherwise it will lead to overfitting, making the denoising effect worse. Therefore, it is necessary to reasonably select the number of decomposition layers according to the characteristics of the signal and the noise situation.
[0113] The threshold formula of the above wavelet threshold denoising algorithm takes into account the three parameters of the median value of the detail coefficient of the first layer decomposition, the signal length, and the number of decomposition layers to achieve the best denoising effect.
[0114] In some embodiments of the present invention, the threshold function of the wavelet threshold denoising algorithm is:
[0115] ,
[0116] in, is the wavelet coefficient after threshold processing, is the original wavelet coefficient, The function is a step function, is the threshold value, a To adjust the parameters.
[0117] There are two common types of threshold functions: hard threshold function and soft threshold function. Among them, the hard threshold function is defined as follows: if the absolute value of the wavelet coefficient is less than the threshold, it is set to zero, otherwise it remains unchanged. The soft threshold function is defined as follows: if the absolute value of the wavelet coefficient is less than the threshold, it is set to zero, otherwise it is subtracted from the threshold. The advantage of the hard threshold function is that the mean square error calculation effect is good after processing, but the disadvantage is that the signal will oscillate. The advantage of the soft threshold function is that the signal is smooth after processing, but it is easy to distort.
[0118] To solve the above problem, the threshold function of this embodiment combines the exponential function and the parameter a The soft threshold function is introduced to process the target signal more flexibly, with stronger adaptability and better processing effect.
[0119] The purpose of introducing the inverse of the exponential function is to ensure that the processed signal is more continuous and smooth. aThe main purpose is to more completely describe the smoothness of the curve, so that the error can be reduced to varying degrees, thus adapting to the sound signals in more situations. a The larger the value, the closer the threshold function image is to the hard threshold function, and the smaller the signal distortion is.
[0120] According to the intelligent belt conveyor debugging method of the embodiment of the present invention, through visual recognition and sound recognition, it is possible to conveniently and quickly detect and debug the tension of the belt conveyor, as well as detect faults, without affecting the main structure of the belt conveyor and without installing additional mechanical measuring equipment. It is also possible to detect whether the tension on both sides of the belt is uniform, so as to adjust the belt and improve the quality of the belt. The problems existing in the prior art are solved.
[0121] Figure 2 A block diagram of an intelligent belt conveyor debugging system according to an embodiment of the present invention is exemplarily shown, wherein the intelligent belt conveyor debugging system comprises:
[0122] The identification setting module 201 is used to set a first visual identification including two identification points on the belt of the belt conveyor. The line connecting the two identification points of the first visual identification is parallel to the length direction of the belt. When the belt is relaxed and flat, the distance between the two identification points of the first visual identification is a first static distance.
[0123] A set of first visual identification is set on the tape, including two identification points, which can be marked on the tape or achieved with special stickers, patterns or paints. The line connecting the identification points should be parallel to the length direction of the tape, that is, parallel to the conveying direction of the belt conveyor. When the tape is relaxed but flat and wrinkle-free, the distance between the two identification points is measured and recorded as the static distance for the calculation of the tension in the subsequent module.
[0124] The operation control module 202 is used to control the belt conveyor to enter the operation state after the belt is tensioned.
[0125] After the first visual mark is set, the belt is initially tensioned to prevent the belt from slipping during operation, and the belt conveyor is controlled to enter the operating state.
[0126] The visual measurement module 203 is used to collect the first visual signal of the first visual identification multiple times when the belt conveyor is in operation, and to measure the first dynamic distance between two identification points of the first visual identification according to the first visual signal.
[0127] Compared with measuring the first dynamic distance in the running state of the belt conveyor, measuring the first dynamic distance in the stopped state, on the one hand, the measurement result is closer to the state of the belt in the normal operation of the belt conveyor, and therefore has higher accuracy. On the other hand, if the first visual identifier is set at an appropriate position, for example, at the very edge of the belt, the first dynamic distance can also be measured simultaneously in the normal operation of the belt conveyor, and used to calculate the belt tension in subsequent modules, thereby realizing non-stop debugging of the belt conveyor.
[0128] The first visual signal can be collected using a camera or other type of image acquisition device, and then the image algorithm or artificial intelligence model calculates the distance between the identification points and records it as the first dynamic distance. Through multiple acquisitions and measurements, the measurement error of the first dynamic distance can be reduced. The specific image algorithm or deep learning model can adopt existing technology, which has been described in many existing technical materials and will not be repeated here.
[0129] The tension calculation module 204 is used to calculate the elongation of the tape according to the first dynamic distance and the static distance, and determine the tension of the tape according to the elongation and a preset correspondence between the elongation and the tension.
[0130] According to the static distance and the first dynamic distance, the elongation of the tape between the two identification points of the first visual identification under the tensioned state of the tape can be calculated. The elongation is the percentage of the increase of the first dynamic distance relative to the static distance to the static distance, that is, , and then according to the elongation and the preset elongation and tension correspondence, for example, 5% elongation corresponds to 100 Newton tension, the tension of the tape can be determined. Different tapes may have different elongation and tension correspondences, and the elongation and tension correspondence can be established in advance through a tensile test experiment.
[0131] The tensioning force adjustment module 205 is used to adjust the tensioning mechanism of the belt conveyor according to the tensioning force.
[0132] After calculating the current tension of the tape, the tension mechanism can be adjusted accordingly, so as to adjust the tension of the tape to an appropriate value. After adjusting the tension mechanism, the operation control module 202, the visual measurement module 203 and the tension calculation module 204 can be used to verify whether the tension has been adjusted to an appropriate value. If it is still not appropriate, the tension adjustment module 205 can be used to adjust the tension again.
[0133] The fault detection module 206 is used to collect the sound signal of the belt conveyor when the belt conveyor is in operation, and perform fault detection using the sound signal.
[0134] In the process of measuring the tension of the belt, the belt conveyor is in operation, and the sound signal of the belt conveyor can be collected at the same time, and the sound signal can be used for fault detection. A sound sensor, such as a microphone, can be used to collect the sound signal of the belt conveyor. After noise reduction or other preprocessing of the sound signal, a sound recognition algorithm or a deep learning model can be used for fault detection. For example, if the sound signal is analyzed to contain abnormal noise, it may be that a component of the conveyor has failed. The specific algorithm or deep learning model can adopt existing technology, which has been described in many existing technical materials and will not be repeated here.
[0135] Through the above system, the tensioning force detection and debugging of the belt conveyor, as well as fault detection can be conveniently and quickly carried out without affecting the main structure of the belt conveyor and without installing mechanical measuring equipment.
[0136] In some embodiments of the present invention, the preset correspondence between elongation and tension force is obtained by:
[0137] The adhesive tape is stretched multiple times in advance with gradually increasing elongation rates, the tension of the adhesive tape is measured each time it is stretched, and a corresponding relationship is established between the elongation rate of each stretch and the tension; or
[0138] Other adhesive tapes of the same type as the adhesive tape are stretched multiple times in advance at gradually increasing elongation rates, the tension of the other adhesive tapes of the same type is measured each time they are stretched, and a corresponding relationship is established between the elongation rate and the tension of each stretch.
[0139] Different types of tapes may have different corresponding relationships between elongation and tension, so the tapes that need to be debugged can be tested in advance to establish the corresponding relationship between tension. The materials and specifications of the same type of tapes are often the same, so other tapes of the same type can also be tested in advance to establish the corresponding relationship between tension.
[0140] The tensile test can be conducted with the elongation gradually increasing. For example, 10 tests can be conducted, starting from 5%, and increasing by 5% each time until the elongation reaches 50%. During the tensile test, the tape can be stretched as a whole to measure the elongation and tension, but the tape is often very long, and this method requires a large experimental space. Therefore, only a part of the tape can be stretched, and the elongation and tension of this part can be measured to establish a corresponding relationship as the elongation and tension of the tape.
[0141] In some embodiments of the present invention, the identification setting module is further used to: set a second visual identification including two identification points on the adhesive tape, the line connecting the two identification points of the second visual identification is parallel to the line connecting the two identification points of the first visual identification, and when the adhesive tape is relaxed and flat, the distance between the two identification points of the second visual identification is the static distance; the distance between the first visual identification and the second visual identification is greater than half of the width of the adhesive tape;
[0142] The visual measurement module is also used to: collect the second visual signal of the second visual identifier multiple times when the belt conveyor is in operation, and calculate the second dynamic distance between two identification points of the second visual identifier according to the second visual signal;
[0143] The tension calculation module is also used to: calculate the tension deviation rate of the adhesive tape according to the first dynamic distance, the second dynamic distance and the static distance;
[0144] Based on the tension offset rate, the tape may be adjusted manually or by automated equipment.
[0145] Ideally, the axes of the rollers on the belt conveyor should be parallel to each other to ensure that the tension on both sides of the belt centerline is uniform. If the axes of some rollers are offset (especially the head roller or the tail roller), the tension on both sides of the belt centerline will be inconsistent. The inconsistent tension will lead to different elongation rates on both sides of the belt centerline. Therefore, the first visual mark and the second visual mark can be set on both sides of the belt centerline to measure the elongation rates on both sides, so as to determine the difference in tension on both sides of the belt centerline, that is, the tension deviation rate.
[0146] The second visual identification can adopt the same form and setting method as the first visual identification. The second dynamic distance between the two identification points of the second visual identification can be measured by collecting the second visual signal of the second visual identification multiple times. The specific method can be the same as the aforementioned first visual identification, which will not be repeated here.
[0147] The distance between the second visual mark and the first visual mark is greater than half of the width of the tape, so as to ensure that the two are located on both sides of the center line of the tape.
[0148] The tension deviation rate is calculated according to the following formula:
[0149] ,
[0150] in, G is the tension deviation rate, n is the total number of times the first visual signal is collected, For the iA first dynamic distance measured when the first visual signal is collected for the first time, m is the total number of times the second visual signal is collected, For the j A second dynamic distance measured when the second visual signal is collected for the first time, is the first static distance, is the second static distance.
[0151] Multiple collection and measurement can reduce the error of single collection and measurement. n and m The values may be inconsistent. For example, the first visual signal can be collected 20 times and the first dynamic distance can be measured, the second visual signal can be collected 10 times and the second dynamic distance can be measured, and then the arithmetic mean of the stretch rate on one side of the tape centerline can be calculated based on the 20 first dynamic distances, and the arithmetic mean of the stretch rate on the other side of the tape centerline can be calculated based on the 10 second dynamic distances. Subtracting the two can obtain the tension deviation rate. G , tension deviation rate G Can be negative, through G The value can be used to determine the difference in tension between the two sides of the belt centerline, thereby determining whether adjustment is needed. G The positive and negative value can determine which side of the center line of the tape is tighter and which side is looser, thereby deciding how to adjust it.
[0152] In some embodiments of the present invention, the “using the sound signal to perform fault detection” specifically includes:
[0153] Performing noise reduction processing on the sound signal;
[0154] Input the processed sound signal into a pre-trained fault detection model to output a fault detection result;
[0155] If the fault detection result is that a fault exists, a device fault prompt is issued;
[0156] If the fault detection result is that there is no fault, a normal equipment prompt is issued.
[0157] The purpose of noise reduction processing is to remove or reduce the noise introduced from the environment, equipment or other interference sources to improve the quality and clarity of the signal and highlight the fault sound. Noise reduction processing can use various digital signal processing techniques, such as filtering, spectral subtraction, wavelet function denoising algorithm or other methods. The appropriate noise reduction method can be selected according to the characteristics of the signal and the type of noise, and the signal can be processed through a filter or algorithm to reduce the interference of noise.
[0158] The fault detection model can be pre-trained by a machine learning algorithm, which can identify faults or anomalies in the sound signal. The model will analyze and compare the input signal and determine whether the signal indicates a device failure based on previous learning experience. The detection model can be built based on various algorithms, such as deep learning, support vector machines, random forests, etc.
[0159] When a fault is detected, a fault prompt is issued. This prompt can be in the form of sound, text or other forms to remind the operator or related personnel to take appropriate measures for maintenance and processing in time. The purpose of equipment fault prompt is to find and solve equipment faults in time to avoid further damage or production interruption. If no fault is detected, a normal equipment prompt is issued to remind the staff to start the machine normally.
[0160] In some embodiments of the present invention, a wavelet threshold denoising algorithm is used to perform denoising on the sound signal;
[0161] The decomposition layer number of the wavelet threshold denoising algorithm is 3 to 5 layers;
[0162] The wavelet function of the wavelet threshold denoising algorithm adopts any one of Haar function, Daubechies function, Symlets function or Morlet function;
[0163] The threshold of the wavelet threshold denoising algorithm adopts any one of a fixed threshold, an unbiased risk estimation threshold, a heuristic threshold or a maximum and minimum threshold.
[0164] The wavelet threshold denoising algorithm is a commonly used digital signal processing technology. It decomposes the signal into wavelet coefficients of different frequencies and processes these coefficients according to the threshold to remove noise and retain useful signal components. The general steps of wavelet threshold denoising belong to the existing technology, which has been documented in many literatures and can also be easily implemented through software such as MATLAB. We will not go into details here. Through wavelet threshold denoising, noise can be effectively removed, the quality and clarity of sound signals can be improved, and fault sounds can be highlighted.
[0165] In the wavelet threshold denoising algorithm, the number of decomposition layers indicates the level of wavelet decomposition of the signal. Decomposing the sound signal into lower frequency and high frequency wavelet coefficients can better capture the details and frequency characteristics of the signal. The selection of the appropriate number of decomposition layers is determined according to the characteristics and requirements of the signal. A decomposition layer number between 3 and 5 layers can achieve a better denoising effect.
[0166] Wavelet function is the basic function used for wavelet decomposition and reconstruction. You can select one from Haar function, Daubechies function, Symlets function and Morlet function as a wavelet function. The specific contents of these functions have been documented and can also be called in software such as MATLAB, so I will not go into details here. In the wavelet threshold denoising algorithm, selecting a suitable wavelet function can better adapt to the characteristics of the signal and the type of noise, thereby improving the noise reduction effect. Different wavelet functions have different frequency responses and time domain characteristics, so the selection of a suitable wavelet function is determined based on specific application requirements and signal characteristics.
[0167] In the wavelet threshold denoising algorithm, the choice of threshold is an important factor in determining the denoising effect. Different thresholds can cope with different signal characteristics and noise types. The threshold can be selected from the following categories: fixed threshold, unbiased risk estimation threshold, heuristic threshold, and maximum and minimum threshold. The specific contents of these thresholds have been described in many literatures and will not be elaborated here.
[0168] In some embodiments of the present invention, the threshold of the wavelet threshold denoising algorithm is determined according to the following formula:
[0169] ,
[0170] in is the threshold, D1 is the detail coefficient of the first layer decomposition, The function is the median function, N is the signal length, L is the number of decomposition layers.
[0171] By setting the threshold, the coefficient of the noise part can be reset to zero, thus achieving denoising.
[0172] The process of wavelet transform is to decompose the signal into a series of detail coefficients and approximate coefficients, which reflect the characteristics of the signal at different scales and positions. In the denoising process, the median of the detail coefficients of the first layer of decomposition can be used to effectively distinguish between signal and noise. Signal length refers to the number of sample points of the signal. When performing wavelet decomposition, the signal length will affect the number of decomposition layers. Generally speaking, the longer the signal length, the more decomposition layers can be performed. In the denoising process, the more decomposition layers there are, the richer the signal details can be obtained, so that the noise can be better removed. The number of decomposition layers determines the accuracy of wavelet transform. The more layers there are, the richer the signal details obtained by decomposition, and the better the characteristics of the signal can be captured. However, the number of decomposition layers cannot be too many, otherwise it will lead to overfitting, making the denoising effect worse. Therefore, it is necessary to reasonably select the number of decomposition layers according to the characteristics of the signal and the noise situation.
[0173] The threshold formula of the above wavelet threshold denoising algorithm takes into account the three parameters of the median value of the detail coefficient of the first layer decomposition, the signal length, and the number of decomposition layers to achieve the best denoising effect.
[0174] In some embodiments of the present invention, the threshold function of the wavelet threshold denoising algorithm is:
[0175] ,
[0176] in, is the wavelet coefficient after threshold processing, is the original wavelet coefficient, The function is a step function, is the threshold value, a To adjust the parameters.
[0177] There are two common types of threshold functions: hard threshold function and soft threshold function. Among them, the hard threshold function is defined as follows: if the absolute value of the wavelet coefficient is less than the threshold, it is set to zero, otherwise it remains unchanged. The soft threshold function is defined as follows: if the absolute value of the wavelet coefficient is less than the threshold, it is set to zero, otherwise it is subtracted from the threshold. The advantage of the hard threshold function is that the mean square error calculation effect is good after processing, but the disadvantage is that the signal will oscillate. The advantage of the soft threshold function is that the signal is smooth after processing, but it is easy to distort.
[0178] To solve the above problem, the threshold function of this embodiment combines the exponential function and the parameter a The soft threshold function is introduced to process the target signal more flexibly, with stronger adaptability and better processing effect.
[0179] The purpose of introducing the inverse of the exponential function is to ensure that the processed signal is more continuous and smooth. a The main purpose is to more completely describe the smoothness of the curve, so that the error can be reduced to varying degrees, thus adapting to the sound signals in more situations. a The larger the value, the closer the threshold function image is to the hard threshold function, and the smaller the signal distortion is.
[0180] The embodiment of the present invention further provides an intelligent belt conveyor debugging device, comprising:
[0181] processor:
[0182] a memory for storing processor-executable instructions;
[0183] The processor is configured to call the instructions stored in the memory to execute the method described in any one of the above embodiments.
[0184] An embodiment of the present invention further provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in any one of the above embodiments is implemented.
[0185] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.
[0186] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0187] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0188] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present invention.
[0189] Various aspects of the present invention are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flowchart and / or block diagram and the combination of the boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0190] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0191] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0192] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.
[0193] Note that, unless otherwise directly stated, all features disclosed in this specification (including any attached claims, abstracts and drawings) may be replaced by alternative features for achieving the same, equivalent or similar purposes. Therefore, unless otherwise explicitly stated, each feature disclosed is only an example of a group of equivalent or similar features. Where used, further, preferably, further and more preferably are simple beginnings for elaborating another embodiment based on the aforementioned embodiment, and the content of the further, preferably, further or more preferably followed by the combination with the aforementioned embodiment constitutes a complete construction of another embodiment. Several further, preferably, further or more preferably settings following the same embodiment can be arbitrarily combined to form another embodiment.
[0194] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.
[0195] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A debugging method for an intelligent belt conveyor, It is characterized in that include: A first visual identification including two identification points is arranged on the belt of the belt conveyor, wherein a line connecting the two identification points of the first visual identification is parallel to a length direction of the belt, and when the belt is relaxed and flat, a distance between the two identification points of the first visual identification is a first static distance; Controlling the belt conveyor to enter a running state after the belt is tensioned; When the belt conveyor is in operation, the first visual signal of the first visual identifier is collected multiple times, and a first dynamic distance between two identification points of the first visual identifier is calculated according to the first visual signal; Calculating the elongation of the adhesive tape according to the first dynamic distance and the static distance, and determining the tension of the adhesive tape according to the elongation and a preset corresponding relationship between the elongation and the tension; adjusting the tensioning mechanism of the belt conveyor according to the tensioning force; When the belt conveyor is in operation, collecting a sound signal of the belt conveyor and performing fault detection using the sound signal; A second visual mark including two identification points is arranged on the adhesive tape, a line connecting the two identification points of the second visual mark is parallel to a line connecting the two identification points of the first visual mark, and when the adhesive tape is relaxed and flat, a distance between the two identification points of the second visual mark is a second static distance; The distance between the first visual mark and the second visual mark is greater than half of the width of the tape; When the belt conveyor is in operation, the second visual signal of the second visual identifier is collected multiple times, and a second dynamic distance between two identification points of the second visual identifier is calculated according to the second visual signal; Calculating a tension deviation rate of the adhesive tape according to the first dynamic distance, the second dynamic distance, and the static distance, and adjusting the adhesive tape according to the tension deviation rate; The tension deviation rate is calculated according to the formula: , in, G is the tension deviation rate, n is the total number of times the first visual signal is collected, For the i A first dynamic distance measured when the first visual signal is collected for the first time, m is the total number of times the second visual signal is collected, For the j A second dynamic distance measured when the second visual signal is collected for the first time, is the first static distance, is the second static distance.
2. The intelligent belt conveyor debugging method according to claim 1, It is characterized in that The preset corresponding relationship between elongation and tension force is obtained in the following manner: The adhesive tape is stretched multiple times in advance with gradually increasing elongation rates, the tension of the adhesive tape is measured each time it is stretched, and a corresponding relationship is established between the elongation rate of each stretch and the tension; or Other adhesive tapes of the same type as the adhesive tape are stretched multiple times in advance at gradually increasing elongation rates, the tension of the other adhesive tapes of the same type is measured each time they are stretched, and a corresponding relationship is established between the elongation rate and the tension of each stretch.
3. The intelligent belt conveyor debugging method according to claim 1, It is characterized in that The “using the sound signal to perform fault detection” specifically includes: Performing noise reduction processing on the sound signal; Input the processed sound signal into a pre-trained fault detection model to output a fault detection result; If the fault detection result is that a fault exists, a device fault prompt is issued; If the fault detection result is that there is no fault, a normal equipment prompt is issued.
4. The intelligent belt conveyor debugging method according to claim 3, It is characterized in that Using a wavelet threshold denoising algorithm to perform noise reduction processing on the sound signal; The decomposition layer number of the wavelet threshold denoising algorithm is 3 to 5 layers; The wavelet function of the wavelet threshold denoising algorithm adopts any one of Haar function, Daubechies function, Symlets function or Morlet function; The threshold of the wavelet threshold denoising algorithm adopts any one of a fixed threshold, an unbiased risk estimation threshold, a heuristic threshold or a maximum and minimum threshold.
5. The intelligent belt conveyor debugging method according to claim 4, It is characterized in that The threshold of the wavelet threshold denoising algorithm is determined according to the following formula: , in is the threshold, D1 is the detail coefficient of the first layer decomposition, The function is the median function, N is the signal length, L is the number of decomposition layers.
6. The intelligent belt conveyor debugging method according to claim 5, It is characterized in that The threshold function of the wavelet threshold denoising algorithm is: , in, is the wavelet coefficient after threshold processing, is the original wavelet coefficient, The function is a step function, is the threshold value, a To adjust the parameters.
7. An intelligent belt conveyor debugging system, It is characterized in that The intelligent belt conveyor debugging method applied to any one of claims 1 to 6 comprises: an identification setting module, used to set a first visual identification including two identification points on the belt of the belt conveyor, wherein the line connecting the two identification points of the first visual identification is parallel to the length direction of the belt, and when the belt is relaxed and flat, the distance between the two identification points of the first visual identification is a first static distance; An operation control module, used for controlling the belt conveyor to enter an operation state after the belt is tensioned; a visual measurement module, configured to collect a first visual signal of the first visual identifier for multiple times when the belt of the belt conveyor is tensioned and the belt conveyor is running, and to measure a first dynamic distance between two identification points of the first visual identifier based on the first visual signal; A tension calculation module, used for calculating the elongation of the adhesive tape according to the first dynamic distance and the static distance, and determining the tension of the adhesive tape according to the elongation and a preset correspondence between the elongation and the tension; A tensioning force adjustment module, used for adjusting the tensioning mechanism of the belt conveyor according to the tensioning force; The fault detection module is used to collect the sound signal of the belt conveyor when the belt conveyor is in operation, and use the sound signal to perform fault detection.
8. An intelligent belt conveyor debugging device, It is characterized in that include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, It is characterized in that Computer program instructions are stored thereon, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.
