CN116086677A - A multi-wire rope tension balance monitoring method, system and electronic equipment - Google Patents

Abstract

The invention discloses a multi-wire rope tension balance monitoring method, system and electronic equipment. The AI visual tension detection module collects the surface image of the steel wire rope and inputs it to the large model for state evaluation. The large state assessment model conducts reasoning and analysis on the collected images, and inputs the surface health image into the tension balance assessment model, and at the same time identifies surface damage and judges the cumulative damage; if the steel wire rope exceeds the service condition, the tension balance assessment model is stopped. According to the structural characteristics of the uneven twisted strands on the surface of the steel wire rope, the magnetic flux density detection module runs regularly according to the visual detection results to realize the tension detection of each steel wire rope. According to the DS evidence theory, the tension balance of the multi-rope hoisting wire rope is integrated and analyzed, and the tension difference between the wire ropes is calculated. The invention integrates AI vision and magnetic flux density detection technology, realizes accurate and efficient monitoring of tension balance, and ensures safe and reliable operation of the hoisting wire rope.

Description

A multi-wire rope tension balance monitoring method, system and electronic equipment

technical field

The invention belongs to the technical field of equipment monitoring and safety, and in particular relates to a multi-wire rope tension balance monitoring method, system and electronic equipment.

Background technique

In the process of my country's economic construction and development, steel wire ropes have been widely used. Especially in non-ferrous metals, coal industry, transportation and other industries, steel wire ropes are often used as key components for the load and traction of equipment such as hoists, elevators and winches, and play an irreplaceable role. Therefore, the reliable and stable application of wire ropes in equipment is closely related to the state performance of equipment and the safety of operators.

Due to the phenomenon of personal injury and death accidents and enterprise production loss caused by steel wire rope safety problems still exist, the safe and reliable use of steel wire ropes has attracted more and more attention. The main reason for the safety problem of steel wire rope is that the steel wire rope bears dynamic and uncertain loads, so the tension on it changes. Especially for equipment or systems with multi-rope hoisting wire ropes, if there are manufacturing errors in friction grooves, friction coefficient changes caused by drum liner wear, manufacturing errors in wire ropes, uneven load distribution in load containers, and installation tension, etc. When there is a problem, it will inevitably lead to unbalanced tension of the multi-rope hoisting wire rope. And when the tension difference of a certain steel wire rope and the average tension difference of the steel wire rope are too large, it will seriously affect the life of the steel wire rope and the friction lining, and even operating accidents such as broken strands and broken ropes will occur. my country's "Coal Mine Safety Regulations" requires that "the tension difference between the wire ropes and the average tension difference should not exceed ±10%". Then, timely and effective monitoring of each steel wire rope in the multi-rope hoisting wire rope is an important means to ensure the tension balance of the multi-rope hoisting wire rope and comply with the specified tension difference. Therefore, it is necessary to develop an accurate and reliable tension balance monitoring system for multi-rope hoisting wire ropes.

At present, there are many methods for detecting the tension of steel wire ropes, and various tension detection methods can be roughly divided into two parts: contact tension detection methods and non-contact tension detection methods. Among them, the research and application of contact tension detection method is earlier. Contact tension detection methods include: series method, three-point or five-point bending method, contact vibration measurement and other tension detection methods. Among them, the series method refers to a force sensor connected in series between the wire rope and the lifting object to directly measure the tension of the wire rope; the three-point or five-point bending method refers to the synthesis and decomposition of the measurement of the tension of the wire rope according to the principles of mechanics. Contact vibration measurement refers to tapping the steel wire rope to force it to vibrate, and using the vibration characteristics of the steel wire rope to measure the tension of the steel wire rope. The non-contact tension detection method refers to the method of detecting the tension of the steel wire rope based on non-destructive testing technologies such as light, electricity, magnetism, and ultrasound. Non-contact tension detection methods include electrical parameter method, electromagnetic method, visual vibration measurement method, etc. Among them, the electrical parameter method refers to the use of detection devices to convert the tension to be measured into the measurement of electrical parameters such as capacitance and inductance related to it. The visual vibration measurement method refers to the use of image processing to analyze the vibration characteristics of the steel wire rope, and then combine the vibration equation of the steel wire rope to calculate the tension of the steel wire rope. The electromagnetic method refers to the method of using the principle of electromagnetic induction to measure the electromagnetic parameters of the conductive and magnetic steel wire rope when it is under force, and then detect the tension.

Nowadays, the requirements for wire rope tension testing are getting higher and higher. Some contact detection methods and their devices have manual errors. During long-term use, sensors and strain elements are prone to plastic deformation and other factors. The detection accuracy is greatly affected, and it cannot meet the dynamic and real-time online detection. The non-contact detection method has made great progress with the development of new technologies, but there are still some insurmountable defects, which cannot meet the detection requirements for the tension and balance of multi-rope hoisting wire ropes.

After searching, for example, the application publication number is CN 101726383 A. The multi-rope hoist wire rope tension detection method utilizes an acceleration sensor to detect the propagation period t of the vibration wave of the lateral vibration of the wire rope, and indirectly measures the tension of the wire rope. The invention can accurately and synchronously detect the tension of multi-cable steel wire ropes and the uniformity of tension, but cannot perform dynamic and online detection. For example, the non-contact cable force testing method of CN 111044197 A adopts the method of visual vibration measurement to indirectly detect the steel cable tension of the bridge, and its defect is that it cannot perform dynamic real-time detection of the steel cable tension. For example, the application publication number is CN109341927 A, which uses bypass coil excitation to detect the tension of the wire rope to be inspected according to the principle of electromagnetic induction, but its device structure and method cannot meet the synchronous detection of multi-rope hoisting wire ropes. Therefore, the current non-contact detection method for steel wire ropes has obvious shortcomings when applied to the tension detection of multi-rope hoisting steel wire ropes. Therefore, there is an urgent need for an accurate and reliable online monitoring method and system.

Contents of the invention

In order to solve the technical problems mentioned above in the background technology, the present invention proposes a multi-wire rope tension balance monitoring method, system and electronic equipment.

In order to realize above-mentioned technical purpose, technical scheme of the present invention is:

A method for monitoring tension balance of multiple steel wire ropes comprises the following steps:

S1, collecting the surface image of the steel wire rope, and preprocessing the collected surface image of the steel wire rope;

S2. Recognize the preprocessed image in step S1; identify the broken wire, broken strand, wear and deformation features in the image as damage features, and mark the category, damage location frame and confidence level in the image; according to the damage features The occurrence frequency is accumulated to evaluate the damage of the steel wire rope, and then the lifting tension balance judgment is made; when the surface health diagnosis model judges that the damage of the steel wire rope exceeds the service condition, an alarm is sent to the outside, prompting to replace the steel wire rope, stop the lifting tension balance judgment of the steel wire rope and return to Step S1;

S3. According to the judgment conclusion of the balance of the steel wire rope hoisting tension that has service conditions in step S2, use the principle of electromagnetic induction to detect the tension of the steel wire rope in the form of eddy current detection; collect the electromagnetic signal on the surface of the steel wire rope and remove the noise part in the signal. The remaining part is amplified to obtain the preprocessed signal;

S4, according to the preprocessing signal that obtains in the step S3; Analysis steel wire rope is subjected to the fitting relation of the distance Δd between the tension F effect and the steel wire rope twisting strand, calculates the tension force that steel wire rope is subjected to;

S5. According to the DS evidence fusion theory, combined with the balance judgment result of image recognition and the tension value of each steel wire rope obtained by electromagnetic detection, the final balance conclusion of the multi-rope hoisting wire rope is obtained.

Preferably, step S1 specifically refers to: establishing a visual detection module, the front and rear cameras of the visual detection module should completely cover all steel wire ropes, control the light intensity and uniformity of light on site, collect the surface image of the steel wire rope, and perform noise reduction on the collected steel wire rope image and deblurring.

Preferably, in step S2, the image recognition uses the one-stage target detection algorithm YOLO series as the backbone network; the tension balance evaluation uses the two-stage target detection algorithm Faster R-CNN series model as the backbone network, and adds the Attention attention mechanism to segment out Detect the steel wire rope part in the image, and then use the color depth of the steel wire rope in the image as the attention direction of the attention mechanism, identify the darkest part of it, and mark the recognition frame in the image and output it.

Preferably, step S3 specifically refers to: using an eddy current probe to detect along the surface of the steel wire rope, the probe has a built-in Hall element, senses the magnetic flux density on the surface of the steel wire rope, converts the magnetic flux density into a corresponding electromagnetic signal, and removes the noise part in the signal , and amplify the remaining part to obtain the preprocessed signal.

Preferably, step S4 specifically refers to:

Obtain the time node t of the trough of n electrical signals, denoted as Obtain the time node t of the peak of n electrical signals, denoted as First obtain the position of the trough, and then obtain the time node t of the peak, and then obtain it sequentially; and the time node t with the same subscript number is the time node of the adjacent peak and trough; the average time interval ΔT between the peak and trough of the electrical signal is expressed as follows :

The average distance between twisted strands of the steel wire rope under a certain tension F is obtained from the average time interval ΔT of the peak and trough of the electrical signal Δd=ΔT·V, where V is the running speed of the steel wire rope; The average time interval is ΔT _i ;

Then through the fitting relationship between the average distance Δd between the twisted strands of the steel wire rope and the tension F, the value of the tension F is obtained; wherein the fitting relationship F=g(Δd), g(x) is a function of the fitting curve relational formula;

The formula for calculating the tension of the i-th wire rope in the multi-rope hoisting wire rope is F _i =g(Δd _i )=g(ΔT _i ·V).

Preferably, the tension difference between any two steel wire ropes in step S5 is in total Among them, F _i and F _j are the hoisting tension values of the i and j steel wire ropes in the n steel wire ropes respectively, and i≠j; calculate the average tension difference in is the sum of the tension differences between any two wire ropes; to judge the tension difference, if It is considered that the tension difference exceeds the specified limit, and the tension of the wire rope exceeds the service condition; if It is considered that the tension difference meets the specified limit, and the tension of the wire rope meets the service conditions.

A multi-wire rope tension balance monitoring system, comprising:

The visual detection module includes a pair of industrial cameras and their wireless signal transmission devices. The industrial cameras are respectively located at the front and rear ends of the plane where the steel wire ropes are located, and are arranged symmetrically; the collection range of the industrial cameras completely covers all the steel wire ropes;

Magnetic flux density detection module, including electromagnetic detection device and its wireless signal transmission device;

Wire rope status evaluation module, including image preprocessing module, image surface diagnosis module and wire rope hoisting tension evaluation module;

The steel wire rope state evaluation module is connected with the visual detection module and the magnetic flux density detection module through a wireless signal transmission device. The flux density information is transmitted to the steel wire rope state evaluation module; the steel wire rope state evaluation module judges the tension balance of the steel wire rope according to the surface image information of the steel wire rope and the magnetic flux density information of the steel wire rope.

Preferably, the electromagnetic detection device is in a non-contact relationship with the steel wire rope, and the electromagnetic detection device is fixedly connected to the ground or the wall.

Preferably, the electromagnetic detection device has built-in multiple eddy current probes with adjustable spacing; the probes have built-in Hall elements.

An electronic device for monitoring the tension balance of multiple steel wire ropes, comprising: a memory and a processor, the memory stores a computer program executable by the processor, and when the processor executes the computer program, the above method for monitoring the tension balance of multiple steel wire ropes is realized .

The beneficial effect brought by adopting the above-mentioned technical scheme:

(1) Compared with the traditional contact tension detection method, the multi-steel wire rope tension balance monitoring method, system and electronic equipment of the present invention, the sensor does not need to be in direct contact with the hoisting wire rope to be inspected, which can avoid the deformation of the sensor during long-term contact and stress Or failure, affecting the detection accuracy; and the deep learning image processing model of the visual inspection system completes pre-training before it is put into use. DS evidence fusion theory combined with electromagnetic detection makes the results more accurate and avoids errors caused by artificial factors.

(2) Compared with the traditional visual tension detection method, the multi-wire rope tension balance monitoring method, system and electronic equipment of the present invention realize the The qualitative analysis of the tension balance of the multi-rope hoisting wire rope is essentially the differential recognition of the horizontal contrast of the image target, the calculation amount of the image recognition is greatly reduced, and the processing speed is significantly improved. Compared with it, no higher image imaging is required. quality. And combined with the tension quantitative detection results of electromagnetic detection, the visual tension evaluation model is enhanced by feedback based on DS evidence fusion theory, so that the online detection visual model is continuously updated and evolved.

(3) Compared with the traditional electromagnetic tension detection method, the multi-wire rope tension balance monitoring method, system and electronic equipment of the present invention can realize the detection of the synchronous tension value of multiple steel wire ropes; the electromagnetic detection part adopts a detachable installation structure , easy to install and debug; the electromagnetic detection module does not need real-time online detection, it can regularly realize quantitative tension detection according to the tension balance evaluation model instructions, and keep the real-time online monitoring of the visual detection module, which does not hinder the normal operation of the lifting system and meets the actual situation of the production enterprise It is highly practical for the requirements of production conditions.

(4) Compared with the vibration measuring tension detection method, the multi-steel wire rope tension balance monitoring method, system and electronic equipment of the present invention do not need to analyze the dynamic model of the lifting wire rope, and have higher adaptability to complex working conditions. The detection system Deployment is quick and easy.

(5) The deep learning model applied in the multi-wire rope tension balance monitoring method of the present invention adopts a modular organizational structure, so that the model obtains feedback enhancement information more targeted and efficient. Different models are established according to different application functions, and there is a feedback and control relationship between the models, and the model connection interface with other functions is reserved to make the detection system more efficient and intelligent.

(6) In the multi-wire rope tension balance monitoring method of the present invention, the electromagnetic detection module utilizes the structural characteristics of uneven twisted strands on the surface of the steel wire rope, and only needs to obtain the peak value and valley signal nodes of the signal in the signal processing stage, which can effectively reduce The vibration and swing of the steel wire rope will affect the collection of fluctuating signals; there is no need to add additional structures to the electromagnetic detection device to reduce the impact of vibration on the collection signal.

Description of drawings

Fig. 1 is multi-wire rope tension balance monitoring method of the present invention, system frame diagram;

Fig. 2 is a schematic layout diagram of the multi-wire rope tension balance monitoring system of the present invention;

In Figure 2, 1- hoisting wire rope, 2- industrial camera, 3- wireless signal transmission device, 4- high-performance workstation, 5- electromagnetic detection device;

Fig. 3 is the schematic diagram of magnetic flux density electromagnetic detection work of the present invention; Among Fig. 3, 1-eddy current probe, 2-lift wire rope;

Fig. 4 is the frame diagram of the large model of deep learning steel wire rope state evaluation of the present invention;

Fig. 5 is a structural diagram of a tension balance evaluation model of the present invention;

Fig. 6 is a demonstration diagram of the visualization results of the monitoring method and system of the present invention.

Detailed ways

The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings.

As shown in Figure 1, an automatic configuration method for a centralized control layer monitoring system applied to an energy enterprise includes the following steps:

Step 1: Convert the custom format file of the original configuration screen into an svg image file; among them, the conversion is generally completed by the configuration tool provided by the original control system manufacturer, and the common configuration tools on the market currently have this function. That is to realize the function of exporting the custom format configuration screen of this system to the standard general svg format picture, and the naming of each configuration screen file in the exported svg format remains unchanged.

Step 2: According to the xml format information of the svg image file, the detailed information of the graphic elements of the original configuration screen is extracted, and the category judgment is carried out on the extracted detailed information of the graphic elements of the original configuration screen, to obtain static graphic entities and dynamic graphic entities; wherein, a Take a configuration screen as an example. After the original configuration screen file is converted into an svg format file, its description language is standard xml. Based on the xml format information of the svg file, all internal graphic element detailed information is extracted according to keywords to form a configuration screen. The list of primitives, which describes in detail the identifier, type, x-coordinate value and y-coordinate value of each primitive on the configuration screen, the size of the primitive body (such as height, width, radius, etc.), border Thickness, border color, fill color, transparency, associated measurement points, etc. The method for judging the graphic element detailed information category in the original configuration screen is: match the graphic element detailed information with the information in the dynamic graphic element model conversion library in the system, when the graphic element detailed information is consistent with the information in the dynamic graphic element model conversion library , the primitive is judged as a dynamic primitive, otherwise it is a static primitive.

Step 3: Carry out mapping transformation between static primitives and dynamic primitives, use the point table to verify the dynamic primitives after mapping conversion, reorganize the verified dynamic primitives and static primitives after mapping conversion, and obtain The configuration file in svg format; among them, the mapping conversion method of the static graphic element is to carry out information matching and format conversion between the static graphic entity and the corresponding static graphic entity conversion library, and obtain the static graphic element of the configuration screen matched by the centralized control layer monitoring system . The point table includes: measuring point identifier, detailed description, unit and other information. The verification work is to process the identifier and detailed description of each measurement point in svg (including special character replacement, increase or decrease prefix, increase or decrease suffix, etc.), and then match them with the point table library one by one. If the converted The measurement point can be queried from the point table library to get the result (the identifier matches exactly), then the measurement point verification passes, otherwise the measurement point verification fails. After verification, the correct measuring point is confirmed, and the wrong measuring point is marked with an abnormal mark on the position of the measuring point on the configuration screen for subsequent manual inspection and correction.

Step 4: Batch convert the obtained configuration files in svg format into files adapted to the monitoring system of the centralized control layer, and obtain a complete configuration screen adapted to the monitoring system of the centralized control layer. The configuration screen obtained at this time can complete the drawing of most of the main screen information and the association of measuring point information. For the dynamic and static graphics that cannot be locally adapted, they can continue to be added or modified through manual verification and review. To finally complete the verification and correction of the configuration screen, so as to meet the release conditions of the centralized control layer monitoring system.

The accuracy and comprehensiveness of the system dynamic primitive model conversion library are very important. The configuration tools of different automation control system manufacturers have different dynamic primitive model conversion libraries, and it is necessary to complete the configuration tools for each important automation manufacturer in advance. Recognition and determination of exported files to obtain their corresponding dynamic metamodel transformation libraries. Fig. 2 is a schematic layout diagram of the multi-wire rope tension balance monitoring system of the present invention, and the steps of the method for obtaining the dynamic graphic element model conversion library are as follows:

Step 1: Convert the configuration screen to an svg format file;

Step 2: Search the measurement point information associated with the dynamic primitive according to the keyword, record the associated dynamic primitive information, and obtain the preliminary version of the dynamic primitive model conversion library;

Step 3: Use multi-configuration screens for verification and recognition, and the verification results are fed back to the preliminary version of the dynamic primitive model conversion library and improved to obtain the dynamic primitive model conversion library.

For an automation manufacturer, its dynamic graphic element model conversion library is relatively fixed. After the manual matching is completed, it can be reused for the dynamic graphic element determination and format conversion of all subsequent configuration screens of the automation manufacturer.

The invention also discloses an automatic configuration device applied to the centralized control layer monitoring system of an energy enterprise, including:

A format conversion module, which is configured to convert the custom format file of the original configuration screen into an svg image file;

The category judgment module is configured to extract the detailed information of the graphic elements of the original configuration screen according to the xml format information of the svg image file, and perform category judgment on the extracted detailed information of the graphic elements of the original configuration screen to obtain static graphic elements and dynamic graphics Yuan;

A mapping reorganization module, which is configured to perform mapping transformation on static primitives and dynamic primitives, uses a point table to verify the dynamic primitives after mapping conversion, and converts the dynamic primitives after verification to the static primitives after mapping conversion The graphic elements are reorganized to obtain the configuration file in svg format;

The batch conversion module is configured to batch convert the obtained configuration files in svg format into files adapted to the monitoring system of the centralized control layer to obtain a complete configuration screen adapted to the monitoring system of the centralized control layer.

The present disclosure also provides a computer-readable storage medium, the storage medium stores a computer program, and the computer program is used to execute the automatic configuration method applied to the centralized control layer monitoring system of an energy enterprise described in the present disclosure.

Another aspect of the present disclosure provides an electronic device, including:

processor;

memory for storing said processor-executable instructions;

The processor is configured to read the executable instructions from the memory, and execute the instructions to implement the automatic configuration method applied to the energy enterprise centralized control layer monitoring system described in the present disclosure.

In addition to the above-mentioned methods and devices, the embodiments of the present application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the above-mentioned "exemplary method" of this specification. Steps in methods according to various embodiments of the application described in section.

The computer program product can be written in any combination of one or more programming languages for executing the program codes for the operations of the embodiments of the present application, and the programming languages include object-oriented programming languages, such as Java, C++, etc. , also includes conventional procedural programming languages, such as the "C" language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute.

In addition, the embodiments of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the processor executes the above-mentioned "Exemplary Method" section of this specification. Steps in methods according to various embodiments of the application described in .

The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof, for example. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

The basic principles of the present application have been described above in conjunction with specific embodiments, but it should be pointed out that the advantages, advantages, effects, etc. mentioned in the application are only examples rather than limitations, and these advantages, advantages, effects, etc. Various embodiments of this application must have. In addition, the specific details disclosed above are only for the purpose of illustration and understanding, rather than limitation, and the above details do not limit the application to be implemented by using the above specific details.

The block diagrams of devices, devices, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, devices, systems may be connected, arranged, configured in any manner. Words such as "including", "comprising", "having" and the like are open-ended words meaning "including but not limited to" and may be used interchangeably therewith. As used herein, the words "or" and "and" refer to the word "and/or" and are used interchangeably therewith, unless the context clearly dictates otherwise. As used herein, the word "such as" refers to and is used interchangeably with the phrase "such as but not limited to".

It should also be pointed out that in the devices, equipment and methods of the present application, each component or each step can be decomposed and/or reassembled. These decompositions and/or recombinations should be considered equivalents of this application.

The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The embodiment is only to illustrate the technical idea of the present invention, and can not limit the scope of protection of the present invention with this. All technical ideas proposed in the present invention, any changes made on the basis of technical solutions, all fall within the scope of protection of the present invention .

Claims (10)

1. The multi-wire rope tension balance monitoring method is characterized by comprising the following steps of:

s1, acquiring a steel wire rope surface image, and preprocessing the acquired steel wire rope surface image;

s2, recognizing the image preprocessed in the step S1; identifying broken wires, broken strands, abrasion and deformation characteristics in the image as damage characteristics, and marking categories, damage positioning frames and confidence in the image; according to the frequency of occurrence of the damage characteristic, the damage condition of the steel wire rope is evaluated in an accumulated mode, and then the balance judgment of the lifting tension is carried out; when the surface health diagnosis model judges that the damage condition of the steel wire rope exceeds the service condition, the steel wire rope is externally alarmed, the replacement of the steel wire rope is prompted, the judgment of the lifting tension balance of the steel wire rope is stopped, and the step S1 is repeated;

s3, detecting the tension of the steel wire rope in an eddy current detection mode by utilizing an electromagnetic induction principle according to a balance judgment conclusion of the lifting tension of the steel wire rope with service conditions in the step S2; collecting electromagnetic signals on the surface of the steel wire rope, removing noise parts in the signals, and amplifying the rest parts to obtain preprocessed signals;

s4, according to the preprocessing signals obtained in the step S3; analyzing the fitting relation of the tension F acting on the steel wire rope and the distance delta d between twisted strands of the steel wire rope, and calculating the tension acting on the steel wire rope;

and S5, according to a DS evidence fusion theory, combining a balance judgment result of image recognition and tension values of all the steel wire ropes obtained through electromagnetic detection to obtain a final balance conclusion of the multi-rope hoisting steel wire rope.

2. The method for monitoring tension balance of multiple steel wires according to claim 1, wherein step S1 specifically refers to: and establishing a visual detection module, wherein front and rear cameras of the visual detection module are required to completely cover all the steel wire ropes, the illumination intensity and illumination uniformity of the scene are controlled, the surface images of the steel wire ropes are collected, and noise reduction and deblurring treatment are carried out on the collected steel wire rope images.

3. The method for monitoring tension balance of multiple steel wires according to claim 1, wherein in step S2, image recognition uses YOLO series as a backbone network; the tension balance improving assessment uses a two-stage target detection algorithm Faster R-CNN series model as a main network, an Attention mechanism is added, a steel wire rope part in a detection image is segmented, the color depth degree of the steel wire rope in the image is taken as the Attention direction of the Attention mechanism, the part with the deepest color is identified, and an identification frame is marked in the image and output.

4. The method for monitoring tension balance of multiple steel wires according to claim 1, wherein step S3 specifically refers to: the method comprises the steps of detecting along the surface of a steel wire rope by using an eddy current probe, arranging a Hall element in the probe, sensing the magnetic flux density on the surface of the steel wire rope, converting the magnetic flux density into corresponding electromagnetic signals, removing noise parts in the signals, and amplifying the rest parts to obtain preprocessed signals.

5. The method for monitoring tension balance of multiple steel wires according to claim 1, wherein step S4 specifically refers to:

a time node t for acquiring the trough of n electric signals is recorded as

A time node t for acquiring peaks of n electrical signals is recorded as

Firstly, acquiring the position of a trough, and then acquiring a time node t of a peak, and sequentially acquiring the time node t; and the time nodes t with the same subscript number are the time nodes of adjacent wave crests and wave troughs; the peak-to-valley average time interval deltat of the electrical signal is expressed as follows:

obtaining the average distance delta d=delta T.V between twisted strands of the steel wire rope under the action of a certain tension F according to the average time interval delta T of the wave peaks and the wave troughs of the electric signal, wherein V is the running speed of the steel wire rope; the average time interval of the peak and trough of the electric signal of the ith steel wire rope is delta T _i ；

Obtaining a value of the tension F through a fitting relation between the average distance delta d among twisted strands of the steel wire rope and the tension F; wherein the fitting relation f=g (Δd), g (x) is a functional relation of the fitting curve;

the tension calculation formula of the ith steel wire rope in the multi-rope lifting steel wire rope is F _i ＝g(Δd _i )＝g(ΔT _i ·V)。

6. The method for monitoring tension balance of multiple steel wire ropes according to claim 4, wherein the tension difference between any two steel wire ropes in step S5 is

Common->

And F, wherein _i 、F _j The hoisting tension values of the ith steel wire rope and the jth steel wire rope in the n steel wire ropes are respectively equal to i & gtj; calculating the average tension difference +.>

Wherein->

Is the sum of the tension difference values between any two steel wire ropes; to distinguish the tension difference, if +.>

The tension difference is regarded as exceeding the regulation limit, and the tension of the steel wire rope exceeds the service condition; if->

The tension difference is considered to meet the regulation limit, and the tension of the steel wire rope meets the service condition.

7. A system based on the multi-wire rope tension balance monitoring method of any one of claims 1-6, comprising:

the visual detection module comprises a pair of industrial cameras and wireless signal transmission devices thereof, wherein the industrial cameras are respectively positioned at the front end and the rear end of a plane where the steel wire rope is positioned and are symmetrically arranged; the acquisition range of the industrial camera completely covers all the steel wire ropes;

the magnetic flux density detection module comprises an electromagnetic detection device and a wireless signal transmission device thereof;

the steel wire rope state evaluation module comprises an image preprocessing module, an image surface diagnosis module and a steel wire rope lifting tension evaluation module;

the visual detection module transmits the acquired image information of the surface of the steel wire rope to the steel wire rope state evaluation module, and the magnetic flux density detection module transmits the acquired magnetic flux density information of the steel wire rope to the steel wire rope state evaluation module; the steel wire rope state evaluation module judges the tension balance of the steel wire rope according to the image information of the surface of the steel wire rope and the magnetic flux density information of the steel wire rope.

8. The multi-wire rope tension balance monitoring system of claim 7, wherein the electromagnetic detection device is in non-contact relationship with the wire rope, and the electromagnetic detection device is fixedly connected with the ground or the wall surface.

9. The multi-wire rope tension balance monitoring system according to claim 7, wherein the electromagnetic detection device is internally provided with a plurality of paths of eddy current probes with adjustable intervals; the probe is internally provided with a Hall element.

10. A multi-wire rope tension balance monitoring electronic device, comprising: a memory and a processor, the memory storing a computer program executable by the processor, the processor implementing the multi-wire rope tension balance monitoring method of any one of the preceding claims 1-6 when the computer program is executed.

Images