CN116990381A

CN116990381A - Scraper machine fault determination method and device and scraper machine fault determination system

Info

Publication number: CN116990381A
Application number: CN202310968821.3A
Authority: CN
Inventors: 吴景红; 叶壮; 郭爱军; 张海峰; 刘军伟; 孙浩; 崔耀; 许联航; 温亮; 阮进林
Original assignee: Shendong Coal Branch of China Shenhua Energy Co Ltd; Guoneng Shendong Coal Group Co Ltd
Current assignee: Shendong Coal Branch of China Shenhua Energy Co Ltd; Guoneng Shendong Coal Group Co Ltd
Priority date: 2023-08-02
Filing date: 2023-08-02
Publication date: 2023-11-03

Abstract

The application provides a fault determination method and device of a scraper machine and a fault determination system of the scraper machine. The method comprises the following steps: and converting the magnetic induction signal of the target equipment into a target image, comparing the target image with the standard image, and determining whether the target equipment fails according to a comparison result. The method can collect magnetic induction signals of the chain of the scraper machine and/or magnetic induction signals of the scraper machine, whenever the operation of the chain and/or the scraper machine is changed, the magnetic field intensity of the chain and/or the scraper machine can be changed no matter whether the change is large or small, therefore, the collected magnetic induction signals can be obtained when the fault of the scraper machine is small, and the magnetic field intensity cannot be influenced by shielding of coal dust and coal mines, therefore, the magnetic induction signals are subjected to image conversion, the obtained target image is accurate, shielding is avoided, the fault of the scraper machine is identified according to the image comparison mode, so that the tiny fault can be identified, and the accuracy of image identification fault is improved.

Description

Scraper machine fault determination method and device and scraper machine fault determination system

Technical Field

The application relates to the technical field of scraper machine fault detection, in particular to a scraper machine fault determination method, a scraper machine fault determination device, a computer readable storage medium and a scraper machine fault determination system.

Background

At present, fault detection is carried out on the scraper machine through images, whether faults exist in the scraper machine or not is identified through manual monitoring of the images, the faults can be identified only when serious faults occur in the scraper machine, for example, the faults can be identified when a chain is deformed or broken in a macroscopic manner, the faults of the chain are serious when the chain is visible in the macroscopic manner, the vision of the image acquisition is blocked due to shielding of coal dust and coal mine when the image of the scraper machine is acquired, the acquired image is inaccurate, and the fault is identified by the subsequent images, so that the fault detection accuracy of the scraper machine is low at present.

Disclosure of Invention

The application aims to provide a fault determination method and device of a scraper machine, a computer readable storage medium and a fault determination system of the scraper machine, which at least solve the problem of lower accuracy of fault detection of the scraper machine in the prior art.

In order to achieve the above object, according to one aspect of the present application, there is provided a fault determining method of a scraper machine, comprising: acquiring a magnetic induction signal of target equipment of a scraper machine, wherein the target equipment is a chain and/or a scraper, and the magnetic induction signal is used for representing the intensity of energy of a magnetic field of the target equipment; converting the magnetic induction signal into an image to obtain a target image, wherein the target image is used for representing the distribution condition of the magnetic field intensity of the target equipment; and comparing the target image with a standard image to obtain a comparison result, and determining whether the target device fails according to the comparison result, wherein the standard image is an image generated by the magnetic induction signal when the target device fails.

Optionally, converting the magnetic induction signal into an image to obtain a target image, including: performing analog-to-digital conversion processing on the magnetic induction signal by adopting an analog-to-digital converter to obtain a first digital signal; and carrying out image reconstruction on the first digital signal according to an image reconstruction algorithm to obtain the target image, wherein the target image is a gray level image, and the image reconstruction algorithm is one or more of an interpolation algorithm, a Fourier transform algorithm, a wavelet transform algorithm and a dictionary learning algorithm.

Optionally, converting the magnetic induction signal into an image to obtain a target image, including: performing analog-to-digital conversion processing on the magnetic induction signal by adopting an analog-to-digital converter to obtain a second digital signal; and carrying out image reconstruction on the second digital signal according to an image segmentation algorithm to obtain the target image, wherein the target image is a binary image, and the image segmentation algorithm is one or more of a segmentation algorithm based on a threshold value, a segmentation algorithm based on an edge, a segmentation algorithm based on a region and a segmentation algorithm based on clustering.

Optionally, determining whether the target device is faulty according to the comparison result includes: determining that the target equipment is normal under the condition that the comparison result represents that the similarity between the target image and the standard image is greater than or equal to a similarity threshold value; and determining that the target equipment is faulty under the condition that the comparison result represents that the similarity of the target image and the standard image is smaller than the similarity threshold value.

Optionally, after converting the magnetic induction signal into an image, the method further comprises: constructing a fault recognition model, wherein the fault recognition model is obtained by training by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises a historical target image acquired in a historical time period, a historical standard image corresponding to the historical target image and a historical fault image corresponding to the historical target image; and inputting the target image into the fault recognition model to obtain a fault recognition result corresponding to the target image, wherein the fault recognition result is used for indicating whether the target equipment is faulty or not.

Optionally, in the case that the fault recognition result indicates that the target device is faulty, after the target image is input to the fault recognition model to obtain a fault recognition result corresponding to the target image, the method further includes: constructing a type recognition model, wherein the type recognition model is obtained by training by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises the historical target image of the fault acquired in a historical time period and a historical fault type corresponding to the historical target image of the fault; and inputting the target image into the type recognition model to obtain a fault type recognition result corresponding to the target image, wherein the fault type recognition result is used for representing the type of the fault of the target equipment.

Optionally, after determining whether the target device is faulty according to the comparison result, the method further includes: controlling an audible and visual alarm to alarm under the condition that the target equipment is determined to be in fault; and controlling the scraper to slow down or stop under the condition that the target equipment is determined to be in fault.

According to another aspect of the present application, there is provided a malfunction determining apparatus of a scraper machine, comprising: the acquisition unit is used for acquiring magnetic induction signals of target equipment of the scraper machine, wherein the target equipment is a chain and/or a scraper, and the magnetic induction signals are used for representing the intensity of energy of a magnetic field of the target equipment; the first processing unit is used for converting the magnetic induction signals into images to obtain target images, wherein the target images are used for representing the distribution condition of the magnetic field intensity of the target equipment; and the second processing unit is used for comparing the target image with a standard image to obtain a comparison result, and determining whether the target device fails according to the comparison result, wherein the standard image is an image generated by the magnetic induction signal when the target device fails.

According to still another aspect of the present application, there is provided a computer readable storage medium including a stored program, wherein the program, when run, controls a device in which the computer readable storage medium is located to execute any one of the fault determination methods of the scraper.

According to still another aspect of the present application, there is provided a scraper machine fault determination system comprising: the device comprises a scraper and a fault determining device of the scraper, wherein the scraper comprises target equipment, and the fault determining device of the scraper is used for executing any fault determining method of the scraper.

By the aid of the technical scheme, magnetic induction signals of the chain of the scraper machine or magnetic induction signals of the scraper can be collected, whenever the operation of the chain and/or the scraper is changed, the magnetic field intensity of the chain and/or the scraper can be changed, so that the collected magnetic induction signals can be obtained when the fault of the scraper machine is small, the magnetic field intensity is not influenced by shielding of coal dust and coal mines, accordingly, the magnetic induction signals are subjected to image conversion, the obtained target image is accurate, shielding is avoided, the fault of the scraper machine is identified according to the image comparison mode, tiny faults can be identified, and the accuracy of image identification faults is improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

fig. 1 is a block diagram showing a hardware configuration of a mobile terminal for performing a malfunction determination method of a scraper machine according to an embodiment of the present application;

fig. 2 shows a flow chart of a fault determination method of a scraper machine according to an embodiment of the present application;

fig. 3 shows a schematic structural diagram of a scraper machine fault monitoring system according to one embodiment;

FIG. 4 shows a schematic view of a part of the structure of a scraper machine fault monitoring system;

fig. 5 shows a block diagram of a malfunction determining apparatus of a scraper machine according to an embodiment of the present application.

Wherein the above figures include the following reference numerals:

102. a processor; 104. a memory; 106. a transmission device; 108. and an input/output device.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

As described in the background art, the accuracy of fault detection of a scraper in the prior art is low, and in order to solve the above problem, embodiments of the present application provide a fault determining method, device, computer readable storage medium and system for a scraper.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the operation on a mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of a mobile terminal of a fault determining method of a scraper according to an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a display method of device information in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-described method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

In the present embodiment, a fault determination method of a scraper machine operating on a mobile terminal, a computer terminal or the like is provided, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order different from that here.

Fig. 2 is a flow chart of a fault determining method of a scraper machine according to an embodiment of the present application. As shown in fig. 2, the method comprises the steps of:

step S201, obtaining a magnetic induction signal of target equipment of the scraper machine, wherein the target equipment is a chain and/or a scraper, and the magnetic induction signal is used for representing the intensity of energy of a magnetic field of the target equipment;

in particular, the magnetic induction signal may be derived from a magnetic sensor, which may be any presently available sensor, such as a GMI sensor, which may be mounted below the target device or at another location. The GMI magnetic sensor is adopted to collect magnetic induction signals, so that the stress concentration part of the magnetic field intensity can be rapidly and accurately detected, a special magnetizing device is not needed, and the surface is not required to be cleaned.

In addition, the magnetic induction signal can directly measure the intensity and direction of the magnetic field by using a magnetic induction sensor. Common magnetic induction sensors are hall sensors, magneto-resistive sensors, etc. Magnetometers, which are instruments for measuring the intensity of a magnetic field, can also be used for acquiring magnetic induction signals, or magnetic card readers, which are devices for indirectly obtaining magnetic field information by measuring the magnetic force experienced by an object, and generally comprise a magnetic induction sensor and associated circuitry. The magnetic card reader-writer can read data in the magnetic card, and magnetic induction signals are obtained by reading magnetic field information on the magnetic card.

Step S202, converting the magnetic induction signals into images to obtain target images, wherein the target images are used for representing the distribution condition of the magnetic field intensity of the target equipment;

specifically, the magnetic induction signal may be used for image conversion to obtain a target image, which may be a two-dimensional dynamic color magnetic map. The target image obtained through magnetic induction signal conversion can be free from interference of environmental dust, water mist and the like.

And step S203, comparing the target image with a standard image to obtain a comparison result, and determining whether the target device is faulty according to the comparison result, wherein the standard image is an image generated by the magnetic induction signal when the target device is not faulty.

Specifically, can carry out image recognition to the target image, and then carry out image comparison, can confirm like this whether scrape the chain of trigger and break down, also can confirm whether scrape the scraper blade of trigger and break down, and then guarantee that this scheme not only can monitor the visible trouble of scraper trigger, also can detect micro defect, early failure and damage.

Through this embodiment, can gather the magnetic induction signal of the chain of scraping the trigger or the magnetic induction signal of scraper blade, whenever chain and/or scraper blade operation change, no matter change is big or little, the magnetic field strength of chain and/or scraper blade can all change, consequently, the magnetic induction signal that gathers just can obtain when scraping the trigger trouble is less, and magnetic field strength can not receive the coal dust colliery to shelter from the influence yet, consequently, carry out image conversion with the magnetic induction signal, the target image that obtains is comparatively accurate, the condition that does not have to shelter from, and then discern the trouble of scraping the trigger according to the mode of image contrast, can discern tiny trouble like this, and then improved the rate of accuracy of image recognition trouble.

Specifically, in some fault detection schemes, only faults which are easy to occur can be detected, namely faults which are visible to naked eyes can be detected, the faults can not be predicted in advance, and early warning can not be performed on the faults in advance.

There are various ways of converting the magnetically induced signals into images, for example, using thermal imaging techniques, magnetic resonance imaging techniques or magnetic field microscopy. Thermal imaging techniques can generate images by measuring the thermal distribution of the surface of an object, which changes in heat when the object is subjected to a magnetic field, and can be converted into images by thermal imaging techniques. Magnetic Resonance Imaging (MRI) is a technique that generates an image by measuring a magnetic field change in an object, in which an image is generated by generating a strong magnetic field around a target device and simultaneously applying pulsed magnetic fields of different directions, and then by measuring the generated magnetic field change. A magnetic field microscope is an instrument that uses magnetic induction signals to observe and measure the magnetism of a sample. The magnetic field changes in the sample are measured by placing the sample in a magnetic field microscope and using a magnetic induction sensor, and these changes are then converted into images.

The image type of magnetic induction signal conversion is not limited, for example, the magnetic induction signal can be converted into a gray image, in a specific implementation process, the magnetic induction signal is converted into an image, and a target image is obtained, which can be realized by the following steps: performing analog-to-digital conversion processing on the magnetic induction signals by adopting an analog-to-digital converter to obtain first digital signals; and carrying out image reconstruction on the first digital signal according to an image reconstruction algorithm to obtain the target image, wherein the target image is a gray level image, and the image reconstruction algorithm is one or more of an interpolation algorithm, a Fourier transform algorithm, a wavelet transform algorithm and a dictionary learning algorithm.

In the scheme, the magnetic induction signals can be subjected to analog-to-digital conversion, the digital signals are further processed, and the high-resolution image can be extracted from the first digital signals through an image reconstruction algorithm, so that the target image can be ensured to comprise richer details or information, and the accuracy of the follow-up fault identification can be ensured to be higher.

The analog-to-digital conversion of the magnetic induction signal may be implemented using an analog-to-digital converter.

Specifically, the interpolation algorithm may be a linear interpolation algorithm, a nearest neighbor interpolation algorithm, a bilinear interpolation algorithm, or a Lanczos interpolation algorithm. The linear interpolation algorithm obtains the gray value of the pixel to be reconstructed by calculating the gray value of the known pixel around the pixel to be reconstructed and then carrying out weighted summation according to the distance between the position of the gray value and the known pixel. And comparing the position of the pixel to be reconstructed with the position of the known pixel by using the nearest neighbor interpolation algorithm, and selecting the gray value of the known pixel closest to the position as the gray value of the pixel to be reconstructed. The bilinear interpolation algorithm obtains the gray value of the pixel to be reconstructed by calculating the gray value of the known pixel around the pixel to be reconstructed and carrying out weighted summation according to the distance between the position of the gray value and the known pixel, and the bilinear interpolation algorithm is different from the linear interpolation algorithm in that the bilinear interpolation algorithm considers the situation that the position of the pixel to be reconstructed is between two known pixels. The Lanczos interpolation algorithm obtains the gray value of the pixel to be rebuilt by calculating the gray value of the known pixel around the pixel to be rebuilt and carrying out weighted summation according to the distance between the position of the gray value and the known pixel, and the Lanczos interpolation algorithm uses Lanczos window function to smooth the interpolation process, unlike the linear interpolation algorithm and the bilinear interpolation algorithm, so as to obtain a smoother image.

Specifically, the specific steps of converting the first digital signal into a gray scale image by the interpolation algorithm are as follows: step 1, firstly, determining interpolation methods, wherein the common interpolation methods comprise nearest neighbor interpolation, bilinear interpolation, bicubic interpolation and the like, and selecting a proper interpolation method depends on specific application scenes and requirements; step 2, determining the size and resolution of the image, namely the width and the height of the gray level image; step 3, creating an empty gray image matrix, wherein the size of the empty gray image matrix is the same as that of the target image; step 4, for each pixel in the target image, calculating a corresponding gray value according to an interpolation method, wherein the specific calculation method depends on the selected interpolation method; step 5, assigning the calculated gray value to the corresponding pixel in the target image; step 6, repeating the step 4 and the step 5 until all pixels in the target image are calculated and assigned.

The specific steps of converting the first digital signal into a gray scale image by a fourier transform algorithm are as follows: performing Fourier transform on the first digital signal to convert the first digital signal into a frequency domain signal; filtering the frequency domain signal, wherein the filter can be selected to enhance or inhibit specific frequency components; performing inverse Fourier transform on the filtered frequency domain signal, and converting the frequency domain signal back to a space domain signal; amplitude adjustment is carried out on the signals after the inverse transformation so as to ensure that the numerical range of the signals is within the range which can be represented by the gray level image; and mapping the adjusted signals into the pixel value range of the gray level image to obtain a final gray level image.

The specific steps of converting the first digital signal into a gray scale image by the wavelet transform algorithm are as follows: s1, performing wavelet transformation on a first digital signal, and converting the first digital signal into a wavelet domain signal; step S2, filtering and downsampling the wavelet domain signals, and selecting different wavelet filters and downsampling methods; step S3, repeating the step S2 until the interesting wavelet coefficient is obtained; s4, performing inverse wavelet transformation on the selected wavelet coefficient, and converting the wavelet coefficient back to a space domain signal; s5, amplitude adjustment is carried out on the signals after the inverse transformation to ensure that the numerical range of the signals is within the range which can be represented by the gray level image; and S6, mapping the adjusted signals into the pixel value range of the gray level image to obtain a final gray level image.

The specific steps of converting the first digital signal into a gray scale image by the dictionary learning algorithm are as follows: constructing a dictionary, wherein each element in the dictionary is an atom, and can be a group of basis vectors or atoms; initializing a dictionary, which may use random initialization or other methods; sparse coding the first digital signal, i.e. representing the signal as a linear combination of atoms in a dictionary; through iterative optimization dictionary and sparse coding, errors of the sparse coding are minimized; reconstructing the optimized sparse codes to obtain converted signals; amplitude adjustment is carried out on the reconstructed signal so as to ensure that the numerical range of the reconstructed signal is in a range which can be represented by a gray level image; and mapping the adjusted signals into the pixel value range of the gray level image to obtain a final gray level image.

The image type of magnetic induction signal conversion is not limited, for example, the magnetic induction signal can be converted into a binary image, in a specific implementation process, the magnetic induction signal is converted into an image, and a target image is obtained, which can be realized by the following steps: performing analog-to-digital conversion processing on the magnetic induction signals by adopting an analog-to-digital converter to obtain second digital signals; and carrying out image reconstruction on the second digital signal according to an image segmentation algorithm to obtain the target image, wherein the target image is a binary image, and the image segmentation algorithm is one or more of a segmentation algorithm based on a threshold value, a segmentation algorithm based on an edge, a segmentation algorithm based on a region and a segmentation algorithm based on clustering.

In the scheme, the magnetic induction signal can be subjected to analog-to-digital conversion, the digital signal is further processed, the second digital signal can be converted into a binary image through image segmentation calculation, each pixel point in the binary image has only two pixel values, namely black or white, so that the algorithm and operation of image processing can be simplified, the complexity and the calculated amount of subsequent calculation are reduced, if the binary image is used for extracting the characteristics, the characteristics and the analysis characteristics are extracted more easily because only two pixel values are used, the contrast ratio of the image can be enhanced, the magnetic field intensity can be displayed more prominently, the accuracy of image identification can be improved during subsequent image identification, and the accuracy of subsequent fault identification can be ensured to be higher.

Specifically, the specific steps of converting the second digital signal into a binary image by a threshold-based segmentation algorithm are as follows: the second digital signal is subjected to preprocessing, such as smoothing, filtering, etc., to reduce the interference of noise. The selection of an appropriate threshold may be obtained by histogram analysis, experimentation, or the like. The signal is thresholded, and pixels above the threshold are set to white and pixels below the threshold are set to black.

Specifically, the specific steps of converting the second digital signal into a binary image by the edge-based segmentation algorithm are as follows: the second digital signal is preprocessed, e.g. smoothed, filtered, etc. Edge detection algorithms, such as Canny's algorithm, sobel's algorithm, etc., are used to detect edges in the signal. The edges are further processed to remove unwanted edges, broken edges of the connection, etc. According to the information obtained by the edge, the second digital signal is converted into a binary image, which can be realized by thresholding, binarization and other methods.

Specifically, the specific steps of converting the second digital signal into a binary image by the region-based segmentation algorithm are as follows: the second digital signal is preprocessed, e.g. smoothed, filtered, etc. Pixels in the signal are grouped according to similarity using a region growing algorithm or a region splitting and merging algorithm. According to the grouping result, the second digital signal is converted into a binary image, which can be realized by thresholding, binarization and the like.

Specifically, the specific steps of converting the second digital signal into a binary image by a cluster-based segmentation algorithm are as follows: the second digital signal is preprocessed, e.g. smoothed, filtered, etc. The pixels in the signal are divided into different clusters using clustering algorithms, such as K-means clustering, spectral clustering, etc. According to the clustering result, the second digital signal is converted into a binary image, which can be realized by thresholding, binarization and other methods.

Because the chain wear is difficult to identify through naked eyes, the magnetic flaw detection sensor of the scraper conveyor arranged in front of the fully-mechanized mining face is independent of a photographic instrument, can be used for independently monitoring and early warning the chain wear, monitoring the degree of the chain wear, sending alarm information when the degree of the chain wear exceeds a threshold value, sending an alarm signal through a mining monitoring alarm device, and providing out that the chain wear exceeds the threshold value information on an information display platform of an industrial personal computer. Therefore, the monitoring of the working face scraper by the camera and the magnetic flaw detection sensor is carried out independently, but the monitoring is displayed together through the topmost information display platform.

The magnetic sensing technology mainly aims at the detection of a scraper chain, and adopts a double-loop time difference magnetic balance principle to detect chain breakage, abrasion, stretching, deformation and the like.

The image processing technology applied by the special camera and constant current source light supplementing device and the magnetic flaw detection technology adopted by the magnetic flaw detection sensor are indispensable. The image recognition technology mainly comprises four stages of image acquisition, processing, recognition and output. The method comprises the steps of shooting a picture by using a special camera, further processing the picture according to the gray level difference of the picture, classifying and extracting important features of the picture to realize the identification of the picture, and finally outputting a result through feature comparison. Therefore, the image recognition technology is mainly used for comparing the characteristics obviously and is used for recognizing the lost plate, the chain pull inclination and the chain breakage of the scraper.

At present, due to the limitation of an edge extraction technology in image processing, an image recognition technology cannot detect finer chain abrasion and cannot recognize internal defects of a chain, so that a magnetic flaw detection sensor is added, and whether the chain of the scraper machine is abraded, stretched, deformed or damaged internally is judged according to a waveform chart through the change of magnetic flux of the chain.

In order to further solve the problem of lower accuracy of fault detection of the scraper in the prior art, the method for determining whether the target equipment is faulty according to the comparison result can be realized by the following steps: determining that the target equipment is normal under the condition that the comparison result represents that the similarity between the target image and the standard image is greater than or equal to a similarity threshold value; and determining that the target equipment fails under the condition that the comparison result indicates that the similarity between the target image and the standard image is smaller than the similarity threshold value.

In the scheme, fault judgment can be carried out through an image recognition mode, fault judgment is carried out through a similarity comparison mode, manual fault judgment is not needed, and because the mode accuracy of manual fault judgment is low, the scheme automatically judges whether the target equipment is faulty or not through an intelligent mode, and the accuracy of the fault can be further improved.

Specifically, the similarity threshold may be 95%, 98%, 99%, or any other similarity threshold, and those skilled in the art may select an appropriate similarity threshold according to actual situations.

In some schemes, although the fault of the scraper can be detected, auxiliary judgment is needed manually, and the scheme adopts image recognition intelligence to judge, so that the fault is not needed to be judged manually, and the fault can be identified autonomously and early warned.

The specific steps for calculating the similarity between the target image and the standard image are as follows: the two images are preprocessed, for example, adjusted to the same size, graying, denoising, etc. Features are extracted from the two images for representing key information of the images. Common feature extraction methods include color histograms, texture features, edge features, and the like. And matching the features of the two images to find out similar feature points or feature areas. Common feature matching algorithms include SIFT, SURF, ORB, etc. And calculating the similarity between the two images according to the result of the feature matching. Common similarity calculation methods include euclidean distance, cosine similarity, structural Similarity (SSIM), and the like. And evaluating the similarity between the two images according to the calculation result of the similarity. Threshold determinations may be used, or the classification of similarity may be based on specific needs.

The above method for determining whether the target device is faulty can use an image recognition algorithm to determine whether the target device is faulty or not through stress variation.

In addition to determining whether the scraper is faulty by using image similarity comparison, the intelligent model may also be used to determine whether the scraper is faulty, and in some embodiments, after converting the magnetic induction signal into an image to obtain the target image, the method further includes the following steps: constructing a fault recognition model, wherein the fault recognition model is trained by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises a historical target image acquired in a historical time period, a historical standard image corresponding to the historical target image and a historical fault image corresponding to the historical target image; and inputting the target image into the fault recognition model to obtain a fault recognition result corresponding to the target image, wherein the fault recognition result is used for indicating whether the target device is faulty or not.

In the scheme, whether the target equipment of the scraper machine fails or not is determined through the constructed failure recognition model, and the failure recognition model is obtained through machine learning advanced training, so that the failure recognition model is high in failure recognition accuracy, whether the target equipment fails or not can be accurately determined, and the failure accuracy can be further improved.

In some solutions, only whether the chain and/or the scraper of the scraper machine is faulty or not can be detected, but the specific fault type cannot be determined, in order to further determine the fault type in the case of a faulty chain or a faulty scraper of the scraper machine, in the case that the fault recognition result indicates that the target device is faulty, after the target image is input into the fault recognition model to obtain the fault recognition result corresponding to the target image, the method further includes the following steps: constructing a type recognition model, wherein the type recognition model is trained by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises the historical target image of the fault acquired in a historical time period and a historical fault type corresponding to the historical target image of the fault; and inputting the target image into the type recognition model to obtain a fault type recognition result corresponding to the target image, wherein the fault type recognition result is used for representing the type of the fault of the target equipment.

In the scheme, the specific type of the fault is determined through the constructed type recognition model, and the type recognition model is obtained through machine learning training in advance, so that the accuracy of the type recognition model in recognizing the fault type is higher, the fault type can be further determined under the condition that the chain of the scraper machine breaks down or the scraper plate breaks down, and a corresponding repair scheme can be formulated according to the fault type.

Of course, there are also some schemes in which the broken chain and the chain jump are detected through manual naked eye identification, the obtained fault types are fewer, and in the scheme, the broken defects of the chain and the scraping plate can be determined, and the loosening condition of the bolts and the nuts can be determined.

In addition, in the scheme, whether the target equipment of the current scraper machine is faulty or not can be determined through the collected magnetic induction signals, and whether the fault occurs in a future period of time can be predicted through an LSTM model.

In some embodiments, after determining whether the target device is malfunctioning based on the comparison result, the method further includes the steps of: under the condition that the fault of the target equipment is determined, controlling an audible and visual alarm to alarm; and controlling the scraper to slow down or stop under the condition that the target equipment is determined to be in fault.

In the scheme, under the condition that the fault of the target equipment is determined, the audible and visual alarm can be controlled to give an alarm to prompt the staff for maintenance in time, and the scraper can be controlled to reduce the speed or stop, so that the further damage of the target equipment caused by the continuous operation of the scraper is avoided.

In addition, besides the magnetic induction signal of the scraper machine, whether the target equipment is faulty or not can be determined according to parameters such as tension, abrasion degree, temperature, noise, vibration and the like of the target equipment.

Determining whether the target device is malfunctioning by tension:

the chain or scraper of the scraper machine needs to be kept under proper tension during operation, and too high or too low a tension may cause failure. By detecting a change in tension of the chain or blade, it can be determined whether the chain or blade has a failure. For example, if the tension suddenly increases or decreases beyond the normal range, it may indicate that the chain or flight is malfunctioning.

Judging whether the fault occurs according to two parameters of the magnetic induction signal and the tension of the chain or the scraper of the scraper machine, and analyzing the change trend of the two parameters and the relation between the two parameters can be combined. The following is an example to illustrate how to determine a fault. It is assumed that the chain of the scraper is monitored by means of magnetic induction signals, the higher the value of the chain magnetic induction signals is, the greater the degree of wear of the chain. In addition, the chain tension of the scraper is monitored by a tension sensor, and the lower the tension value is, the greater the degree of slackening of the chain is.

Under normal working conditions, the magnetic induction signal and tension of the chain of the scraper machine can be kept in a relatively stable range. However, if the value of the scraper chain magnetic induction signal suddenly increases and at the same time the value of the chain tension suddenly decreases, it may indicate that the chain is severely worn and slackened, and that there may be a fault.

For example, assume at some point that the value of the scraper chain magnetic induction signal suddenly increases from 10 to 50, while the value of the chain tension suddenly decreases from 100 to 50. According to the change trend of the two parameters and the relation between the two parameters, the chain abrasion of the scraper machine can be primarily judged to be serious and loose, and faults possibly exist.

Determining whether the target device is malfunctioning by the degree of wear:

the chain or the blade is gradually worn out during a long period of operation, and when the wear exceeds a certain level, malfunction may be caused. By detecting the degree of wear of the chain or blade, it can be determined whether it needs replacement or repair. For example, it may be determined whether maintenance is required by periodically checking the wear of the chain or flight.

The chain of the scraper machine can be worn out due to long-term friction in the running process, and if the chain is worn seriously, the chain can be broken or loosened, so that the normal running of the scraper machine is affected. Therefore, observing the degree of wear of the chain is one of the important indicators for judging whether the scraper machine is malfunctioning. If the abrasion degree of the chain exceeds the normal range, such as obvious dent, fracture or loosening of the chain on the surface of the chain, the scraper machine can be judged to have faults.

The scraper of a scraper is usually made of magnetic material, and the position and the running state of the scraper can be detected by a magnetic induction sensor. If the magnetic induction signal of the scraper machine is abnormal, if no signal is output or the signal is abnormally fluctuated, the scraper machine may be indicated to have faults. For example, if the blade magnetic induction signal is continuously 0 or continuously unstable, it may mean that the blade is stuck or not functioning properly, thereby requiring maintenance or replacement of the blade.

For example, it is assumed that the chain wear degree of the scraper exceeds the normal range, and the magnetic induction signal of the scraper is continuously 0. At this time, the scraper can be judged to have a fault, and the fault is probably caused by chain breakage or loosening due to chain abrasion, so that the scraper cannot work normally. In this case, it is necessary to repair the chain and replace the scraper in time to resume the normal operation of the scraper.

Determining whether the target device is malfunctioning by temperature:

the chain or scraper of the scraper machine generates certain friction and heat during normal operation. By detecting the temperature change of the chain or the scraper, whether the faults such as excessive friction and poor lubrication exist or not can be judged. For example, if the temperature of the chain or flight is abnormally elevated, a fault may be indicated.

When the scraper chain is abnormal during operation, abnormal magnetic induction signals or abnormal temperature rise of the chain can be caused. For example, if the chain is loose, broken or worn, etc., it may cause abnormality in the magnetic induction signal of the chain or increase in temperature. Thus, if the chain magnetic induction signal is abnormal or the temperature rises beyond the normal range, it may mean that the chain is malfunctioning.

Magnetic induction signals and temperature anomalies of the blade may also indicate a blade failure. For example, problems such as severe wear of the blade surface, uneven blade pressure, etc. may cause abnormal blade magnetic induction signals. In addition, the abnormal rise in temperature of the scraper may be caused by excessive friction between the scraper and the scraped material, or the scraper itself is not suitable for the high-temperature environment of the scraped material, or the like.

Illustrating: the magnetic induction signals and the temperature of the chain and the scraper are parameters for monitoring the malfunction of the scraper, assuming that the scraper is used for cleaning solid waste in a high temperature furnace. If the magnetic induction signal of the chain is abnormal or the temperature rises beyond the normal range, the chain may be indicated to have faults such as loosening, breakage or sprocket abrasion. If the magnetic induction signal of the scraper blade is abnormal or the temperature is abnormally raised, the abrasion of the surface of the scraper blade or the excessive friction between the scraper blade and the scraped material can be caused. By monitoring the two parameters, whether the scraper machine has faults or not can be timely judged, and corresponding maintenance measures are adopted.

Determining whether the target device is malfunctioning by noise:

the chain or blade may produce some noise when in operation, but excessive or abnormal noise may indicate that the chain or blade is malfunctioning. By detecting the noise variation of the chain or the scraper, it can be judged whether there is a failure. For example, if the noise suddenly increases or becomes abnormally harsh, it may indicate that the chain or flight is malfunctioning.

Under normal operating conditions, the chain or flight will produce a stable magnetic induction signal. If a fault occurs, such as a chain break or a blade failure, the magnetically induced signal may appear abnormal, such as a surge or disappearance. Thus, monitoring the stability and frequency variation of the magnetically induced signal can be used to determine if a fault exists.

In normal operation, the blade may generate some noise, but once it fails, the noise will often become abnormal. For example, chain breakage or blade damage may cause the chain to rub against the transmission, creating a harsh metal friction or cracking sound. Therefore, monitoring noise changes and anomalies can be an important indicator for determining faults.

Illustrating: under the condition that one scraper machine is in a normal working state, magnetic induction signals of the chain are stable and noise is normal. Suddenly, the noise of the scraper machine becomes abnormally large, and the magnetic induction signal fluctuates. This may indicate breakage of the chain of the scraper or damage to the scraper, causing friction between the chain and the transmission, generating abnormal noise. Meanwhile, the magnetic induction signal also fluctuates or disappears due to chain breakage or scratch board damage.

Determining whether the target device is malfunctioning by vibration:

the chain or blade may vibrate somewhat during operation, but excessive or abnormal vibration may indicate a failure of the chain or blade. By detecting the vibration change of the chain or the blade, it can be judged whether or not there is a failure. For example, if the vibrations suddenly increase or become abnormally severe, it may indicate that the chain or blade is malfunctioning.

Under normal operating conditions, the magnetic induction signal of the chain and/or the blade should remain stable. If the signal suddenly becomes unstable, fluctuates greatly or disappears, it may mean a chain break or a blade failure. The magnetic induction signals of the chain and/or the scraper blade are monitored and recorded in real time by using a magnetic induction sensor or a magnetic induction detecting instrument, and whether faults exist can be judged by comparing the real-time data with the reference data in a normal working state.

When the scraper machine works normally, the vibration should be kept in a reasonable range, and the change is stable. If the vibration suddenly increases, the frequency variation is large, or abnormal vibration occurs, it may mean that the scraper machine malfunctions. Vibration parameters of the scraper machine are monitored and recorded in real time by using a vibration sensor or a vibration detection instrument, and whether faults exist can be judged by comparing real-time data with reference data in a normal working state.

Illustrating: it is assumed that, in the operation state monitoring of a scraper, the following is detected: the magnetic induction signal of the chain and/or the blade suddenly becomes unstable and a situation occurs in which the signal fluctuation is large. Meanwhile, the vibration of the scraper machine is suddenly increased, the frequency change is large, obvious abnormal vibration occurs, and the fault of target equipment of the scraper machine can be determined.

In the scheme, the fault type of the scraper is not needed to be manually participated in judging whether the fault occurs, the state of the scraper is directly judged through an image recognition algorithm, and the traditional scraper fault monitoring method can monitor the change of a certain measured value of the scraper so as to manually judge whether the fault occurs or not, but the attention, the reaction force and the experience of people are required to be higher because people are needed to participate in resolution.

In order to make the technical solution of the present application more clearly known to the person skilled in the art, the implementation process of the fault determining method of the scraper machine of the present application will be described in detail below with reference to specific embodiments.

The embodiment relates to a specific scraper machine fault monitoring system, as shown in FIG. 3, comprising a chain flaw detection unit, a scraper flaw detection unit and a monitoring unit

The system comprises a control platform, a server, a controller and an audible and visual alarm.

The two flaw detection units transmit detected magnetic induction signals to a server, an image recognition model is deployed on the server, the magnetic induction signals are processed into two-dimensional dynamic color magnetic patterns through preprocessing on the server, faults of the scraper machine are recognized and predicted through the image recognition model, recognition prediction results are sent to a monitoring platform to be convenient for workers to check, when the faults of the scraper machine are recognized or predicted, signals are sent to an audible and visual alarm to alarm, and control decisions are output to a controller to control the scraper conveyor.

The structure of the chain flaw detection unit and the scraper flaw detection unit is shown in fig. 4, and the transmission chain and the scraper flaw detection unit respectively consist of a GMI magnetic sensor array, an A/D converter, an Ethernet communication module, a power supply module and the like.

The installation position of the chain flaw detection unit is a gear, and the chain flaw detection unit has the advantages of stable running, small swing amplitude, basically unchanged chain in horizontal and vertical directions, and large interference and background magnetic field intensity; secondly, select the chain bottom, its advantage is little interference, background magnetic field is weak. The scraper flaw detection unit is arranged below the scraper and mainly used for measuring the defects of the upper surface of the scraper, and can be made into a ring shape when necessary, so that the upper surface or the bottom of the scraper flaw detection unit can be measured simultaneously, an external magnetic field can be conveniently shielded, and larger measurement resolution can be obtained.

The measurement precision and the measurement speed are comprehensively considered, for a chain and a scraper, GMI magnetic sensors with the measurement resolution of nT are selected, the number of the sensors in the array is determined according to the structural form of the measured object, the diameter of the measured object, the defect angle-fixing precision and the installation mode, the number of the chain flaw detection is 4, and the scraper flaw detection is provided with a GMI magnetic sensor array side by side along the length direction of the scraper at intervals of 3-6 cm according to the length of the scraper.

When a ferromagnetic component in a geomagnetic field environment is subjected to external load, magnetic domain tissue orientation and irreversible reorientation with magnetostriction property are generated in a stress concentration area, fixed nodes of magnetic domains are generated at the position, magnetic poles are generated, a demagnetizing field is formed, the magnetic permeability of ferromagnetic metal at the position is minimized, and a leakage magnetic field is formed on the surface of the metal. This irreversible change in magnetic state remains memorized after the work load is removed. The chain flaw detection unit and the scraper flaw detection unit manufactured based on the basic principle of the metal magnetic memory effect can evaluate the stress concentration degree of the component and whether microscopic defects exist or not by recording the distribution condition of the magnetic field intensity component perpendicular to the surface of the metal component along a certain direction, and can diagnose the stress concentration area inside the ferromagnetic metal component, namely microscopic defects, early failure, damage and the like.

The servers are arranged at the positions of the machine heads, each scraper machine server is provided with 1 set of intelligent AI system, and the intelligent analysis can be carried out on the magnetic induction data of the chains and the scrapers, which are measured by the chain flaw detection unit and the scraper flaw detection unit.

The whole scheme flow is as follows: the chain flaw detection unit and the scraper flaw detection unit measure the magnetic field intensity distribution of the installation position in real time, data are transmitted to a server installed on a machine head through an underground industrial Ethernet, the magnetic field signals measured in real time are processed into two-dimensional dynamic color magnetic patterns at the server, the state of the chain and the scraper at the moment is identified through an image identification algorithm (such as a convolutional neural network), whether the fault that bolts and nuts fall off or not can be obtained through the state monitoring of the chain and the scraper, and the state of the scraper is transmitted to a monitoring platform installed on a roadway for staff to read and review. When the abnormal increase speed of the broken, worn and deformed chain and scraper is detected, or when the broken defect of the chain and the scraper is detected to exceed a certain range, or after the screw bolt and the screw nut fall off, the audible and visual alarm is used for alarming, and related information and set control signals are given. When the chain or the scraping plate breaks suddenly and is in serious fault, the audible and visual alarm gives an alarm, and the scraper machine is automatically stopped.

The embodiment of the application also provides a fault determining device of the scraper machine, and the fault determining device of the scraper machine can be used for executing the fault determining method for the scraper machine. The device is used for realizing the above embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

The following describes a fault determining device of a scraper machine provided by an embodiment of the present application.

Fig. 5 is a block diagram showing a construction of a malfunction determining apparatus of a scraper machine according to an embodiment of the present application. As shown in fig. 5, the apparatus includes:

an acquisition unit 10 for acquiring a magnetic induction signal of a target device of the scraper, wherein the target device is a chain and/or a scraper, and the magnetic induction signal is used for representing the intensity of energy of a magnetic field of the target device;

a first processing unit 20, configured to convert the magnetic induction signal into an image, and obtain a target image, where the target image is used to represent a distribution situation of magnetic field intensity of the target device;

And a second processing unit 30, configured to compare the target image with a standard image, to obtain a comparison result, and determine whether the target device is faulty according to the comparison result, where the standard image is an image generated by the magnetic induction signal when the target device is not faulty.

The image type of the magnetic induction signal conversion is not limited, for example, the magnetic induction signal can be converted into a gray image, in a specific implementation process, the first processing unit comprises a first conversion module and a first reconstruction module, and the first conversion module is used for carrying out analog-digital conversion processing on the magnetic induction signal by adopting an analog-digital converter to obtain a first digital signal; the first reconstruction module is configured to reconstruct an image of the first digital signal according to an image reconstruction algorithm, so as to obtain the target image, where the target image is a gray scale image, and the image reconstruction algorithm is one or more of an interpolation algorithm, a fourier transform algorithm, a wavelet transform algorithm, and a dictionary learning algorithm.

The image type of magnetic induction signal conversion is not limited, for example, the magnetic induction signal can be converted into a binary image, in the specific implementation process, the first processing unit comprises a second conversion module and a second reconstruction module, and the second conversion module is used for carrying out analog-digital conversion processing on the magnetic induction signal by adopting an analog-digital converter to obtain a second digital signal; the second modeling block is configured to reconstruct an image of the second digital signal according to an image segmentation algorithm to obtain the target image, where the target image is a binary image, and the image segmentation algorithm is one or more of a segmentation algorithm based on a threshold, a segmentation algorithm based on an edge, a segmentation algorithm based on a region, and a segmentation algorithm based on a cluster.

In order to further solve the problem of lower accuracy of fault detection of the scraper in the prior art, the second processing unit of the application comprises a first determining module and a second determining module, wherein the first determining module is used for determining that the target equipment is normal under the condition that the similarity of the target image and the standard image represented by the comparison result is greater than or equal to a similarity threshold value; the second determining module is configured to determine that the target device fails when the comparison result indicates that the similarity between the target image and the standard image is less than the similarity threshold.

In addition to using the image similarity comparison mode to determine whether the scraper machine is faulty or not, the intelligent model may be used to determine whether the scraper machine is faulty or not, and in some embodiments, the apparatus further includes a first construction unit and a third processing unit, where the first construction unit is configured to construct a fault recognition model after converting the magnetic induction signal into an image to obtain a target image, where the fault recognition model is obtained by training using multiple sets of training data, and each set of training data in the multiple sets of training data includes a historical target image obtained in a historical time period, a historical standard image corresponding to the historical target image, and a historical fault image corresponding to the historical target image; and the third processing unit is used for inputting the target image into the fault recognition model to obtain a fault recognition result corresponding to the target image, wherein the fault recognition result is used for indicating whether the target equipment is faulty or not.

In some schemes, whether a chain and/or a scraper of the scraper machine is faulty or not can only be detected, but a specific fault type can not be determined, in order to further determine the fault type in the case of a fault of the chain or a fault of the scraper machine, the device further comprises a second construction unit and a fourth processing unit, wherein the second construction unit is used for inputting the target image into the fault recognition model to obtain a fault recognition result corresponding to the target image when the fault recognition result indicates that the target equipment is faulty, and constructing a type recognition model, wherein the type recognition model is obtained by training by using multiple sets of training data, and each set of training data in the multiple sets of training data comprises the historical target image of the fault obtained in a historical time period and the historical fault type corresponding to the historical target image of the fault; the fourth processing unit is configured to input the target image into the type recognition model, and obtain a fault type recognition result corresponding to the target image, where the fault type recognition result is used to represent a type of the fault of the target device.

In some embodiments, the apparatus further includes a first control unit and a second control unit, where the first control unit is configured to control the audible and visual alarm to alarm when it is determined that the target device fails after determining whether the target device fails according to the comparison result; and the second control unit is used for controlling the scraper machine to slow down or stop under the condition that the target equipment is determined to be in fault.

The fault determining device of the scraper comprises a processor and a memory, wherein the acquisition unit, the first processing unit, the second processing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions. The modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the accuracy of fault detection of the scraper is improved by adjusting kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application provides a computer readable storage medium, which comprises a stored program, wherein the program is used for controlling equipment where the computer readable storage medium is located to execute the fault determination method of the scraper machine.

The embodiment of the application provides a processor, which is used for running a program, wherein the fault determination method of the scraper machine is executed when the program runs.

The application also provides a scraper machine fault determining system, which comprises a scraper machine and a fault determining device of the scraper machine, wherein the scraper machine is in communication connection with the fault determining device of the scraper machine, the scraper machine comprises target equipment, and the fault determining device of the scraper machine is used for executing any fault determining method of the scraper machine.

The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize at least the following steps of a fault determination method of a scraper machine. The device herein may be a server, PC, PAD, cell phone, etc.

The application also provides a computer program product adapted to perform a program initialized with at least the following steps of a fault determination method of a scraper machine when executed on a data processing device.

It will be appreciated by those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

1) The fault determination method of the scraper machine can collect the magnetic induction signal of the chain of the scraper machine or the magnetic induction signal of the scraper machine, and only when the operation of the chain and/or the scraper machine is changed, the magnetic field intensity of the chain and/or the scraper machine can be changed no matter whether the change is large or small, so that the collected magnetic induction signal can be obtained when the fault of the scraper machine is small, and the magnetic field intensity is not influenced by shielding of coal dust and coal mines, therefore, the magnetic induction signal is subjected to image conversion, the obtained target image is more accurate and has no shielding condition, and the fault of the scraper machine is identified according to the image comparison mode, so that the tiny fault can be identified, and the accuracy of image identification fault is improved.

2) The fault determining device of the scraper machine can collect magnetic induction signals of the chain of the scraper machine or magnetic induction signals of the scraper machine, and only when the operation of the chain and/or the scraper machine is changed, the magnetic field intensity of the chain and/or the scraper machine can be changed no matter whether the change is large or small, so that the collected magnetic induction signals can be obtained when the fault of the scraper machine is small, and the magnetic field intensity cannot be influenced by shielding of coal dust and coal mines, therefore, the magnetic induction signals are subjected to image conversion, the obtained target image is accurate and has no shielding condition, and further, the fault of the scraper machine is identified according to the image comparison mode, so that the tiny fault can be identified, and the accuracy of image identification fault is improved.

The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for determining a failure of a scraper machine, comprising:

acquiring a magnetic induction signal of target equipment of a scraper machine, wherein the target equipment is a chain and/or a scraper, and the magnetic induction signal is used for representing the intensity of energy of a magnetic field of the target equipment;

converting the magnetic induction signal into an image to obtain a target image, wherein the target image is used for representing the distribution condition of the magnetic field intensity of the target equipment;

and comparing the target image with a standard image to obtain a comparison result, and determining whether the target device fails according to the comparison result, wherein the standard image is an image generated by the magnetic induction signal when the target device fails.

2. The method of claim 1, wherein converting the magnetically induced signal into an image to obtain a target image comprises:

Performing analog-to-digital conversion processing on the magnetic induction signal by adopting an analog-to-digital converter to obtain a first digital signal;

and carrying out image reconstruction on the first digital signal according to an image reconstruction algorithm to obtain the target image, wherein the target image is a gray level image, and the image reconstruction algorithm is one or more of an interpolation algorithm, a Fourier transform algorithm, a wavelet transform algorithm and a dictionary learning algorithm.

3. The method of claim 1, wherein converting the magnetically induced signal into an image to obtain a target image comprises:

performing analog-to-digital conversion processing on the magnetic induction signal by adopting an analog-to-digital converter to obtain a second digital signal;

and carrying out image reconstruction on the second digital signal according to an image segmentation algorithm to obtain the target image, wherein the target image is a binary image, and the image segmentation algorithm is one or more of a segmentation algorithm based on a threshold value, a segmentation algorithm based on an edge, a segmentation algorithm based on a region and a segmentation algorithm based on clustering.

4. The method of claim 1, wherein determining whether the target device is malfunctioning based on the comparison result comprises:

Determining that the target equipment is normal under the condition that the comparison result represents that the similarity between the target image and the standard image is greater than or equal to a similarity threshold value;

and determining that the target equipment is faulty under the condition that the comparison result represents that the similarity of the target image and the standard image is smaller than the similarity threshold value.

5. The method of claim 1, wherein after converting the magnetically induced signal into an image to obtain a target image, the method further comprises:

constructing a fault recognition model, wherein the fault recognition model is obtained by training by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises a historical target image acquired in a historical time period, a historical standard image corresponding to the historical target image and a historical fault image corresponding to the historical target image;

and inputting the target image into the fault recognition model to obtain a fault recognition result corresponding to the target image, wherein the fault recognition result is used for indicating whether the target equipment is faulty or not.

6. The method according to claim 5, wherein in the case where the failure recognition result indicates that the target device fails, after inputting the target image to the failure recognition model, the method further comprises:

Constructing a type recognition model, wherein the type recognition model is obtained by training by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises the historical target image of the fault acquired in a historical time period and a historical fault type corresponding to the historical target image of the fault;

and inputting the target image into the type recognition model to obtain a fault type recognition result corresponding to the target image, wherein the fault type recognition result is used for representing the type of the fault of the target equipment.

7. The method of claim 1, wherein after determining whether the target device is malfunctioning based on the comparison result, the method further comprises:

controlling an audible and visual alarm to alarm under the condition that the target equipment is determined to be in fault;

and controlling the scraper to slow down or stop under the condition that the target equipment is determined to be in fault.

8. A failure determination device of a scraper machine, characterized by comprising:

the acquisition unit is used for acquiring magnetic induction signals of target equipment of the scraper machine, wherein the target equipment is a chain and/or a scraper, and the magnetic induction signals are used for representing the intensity of energy of a magnetic field of the target equipment;

The first processing unit is used for converting the magnetic induction signals into images to obtain target images, wherein the target images are used for representing the distribution condition of the magnetic field intensity of the target equipment;

and the second processing unit is used for comparing the target image with a standard image to obtain a comparison result, and determining whether the target device fails according to the comparison result, wherein the standard image is an image generated by the magnetic induction signal when the target device fails.

9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the device in which the computer-readable storage medium is controlled to execute the fault determination method of the scraper machine according to any one of claims 1 to 7 when the program is run.

10. A scraper machine fault determination system, comprising: a scraper machine comprising a target device and a fault determination device of the scraper machine for performing the fault determination method of the scraper machine according to any one of claims 1 to 7.