CN116309506A

CN116309506A - Edge recognition algorithm-based coal conveying belt coal overflow detection method and system

Info

Publication number: CN116309506A
Application number: CN202310319673.2A
Authority: CN
Inventors: 钱韫辉; 高巍
Original assignee: Shanghai Qingce Electromechanical Engineering Technology Co ltd
Current assignee: Shanghai Qingce Electromechanical Engineering Technology Co ltd
Priority date: 2023-03-28
Filing date: 2023-03-28
Publication date: 2023-06-23

Abstract

The invention discloses a coal conveying belt coal overflow detection method and a system based on an edge recognition algorithm, wherein the method comprises the following steps: step 1: deploying high-definition camera equipment in a coal conveying belt monitoring area; step 2: the high-definition camera equipment acquires operation videos of the coal conveying belt in real time to obtain video stream data; step 3: performing frame extraction on the video stream data according to frequency to obtain frame extraction images and storing the frame extraction images; step 4: performing image recognition processing on the frame extraction image to obtain an edge characteristic curve of a designated area; step 5: comparing the edge characteristic curve of the designated area with the non-overflowed coal characteristic curve to obtain a comparison threshold; and if the comparison threshold exceeds the preset threshold, alarming, otherwise, returning to the step 2.

Description

Edge recognition algorithm-based coal conveying belt coal overflow detection method and system

Technical Field

The invention relates to the field of coal overflow detection, in particular to a coal conveying belt coal overflow detection method and system based on an edge recognition algorithm.

Background

In the actual operation process of a thermal power plant, a coal conveying system is the most critical equipment, coal continuously provides coal meeting the granularity requirement through a coal crusher, in the process of conveying the coal, as the coal is crushed, the problem of coal blockage can occur at a coal falling port at the tail part in the upward conveying process, particularly in the condition of wet coal quality, the problem is more likely to occur, when coal overflows, coal falling can occur from two sides of a coal conveying belt, the coal falling can clamp the coal conveying belt or other mechanical devices, the operation needs to be stopped urgently when the equipment is clamped by the coal falling, the equipment is easy to damage once the emergency stop, meanwhile, the coal falling is required to be cleaned by consuming manpower, unnecessary cost input is generated, and even the power generation efficiency is indirectly reduced;

the coal overflow sensor and the explosion-proof camera are adopted to monitor the transmission belt in real time in more for the coal overflow detection of the coal-fired conveying belt in the thermal power plant, but with the continuous development of artificial intelligence, the application of the mobile intelligent inspection robot in the thermal power plant becomes more popular. The traditional coal overflow sensor is based on contact detection and non-contact detection, but the two methods are easy to be touched by mistake or shielded by mistake to generate a false alarm phenomenon, meanwhile, the detection has no visualization, and staff cannot further confirm the authenticity of accidents, so that the production efficiency is affected. On the other hand, under the condition of long-time use, the contact type coal overflow sensor is continuously rubbed with equipment, so that the detection sensitivity is affected, and electric sparks are easily caused by friction, so that a great hidden danger is generated. The fixed-point real-time monitoring transmission belt of the explosion-proof camera can solve the problem that the coal overflow sensor cannot visualize the coal overflow detection, but can only be at a fixed position, depends on the responsibility of a safety officer, and has large executing randomness. The existing mobile inspection robots are also applied to some power plants, but have obvious defects, low inspection quality, missed inspection, hysteresis in information feedback and insufficient intelligence. .

Disclosure of Invention

The invention aims to solve the technical problems that in the process of conveying coal, coal is crushed, coal blocking occurs at a coal falling port at the tail part in the upward conveying process, particularly in the case of wet coal quality, the problem is more easy to occur, coal falling occurs from two sides of a coal conveying belt when coal overflow occurs, the coal falls off to clamp the coal conveying belt or other mechanical devices, the equipment needs to be stopped in an emergency mode when the equipment is clamped by the coal falling off, once the equipment is easy to damage due to the emergency stop, meanwhile, the coal falling cleaning is needed to be carried out, unnecessary cost investment is generated, and even the power generation efficiency is reduced indirectly.

The invention provides the following technical scheme for solving the technical problems:

in a first aspect, a method for detecting coal overflow of a coal conveying belt based on an edge recognition algorithm includes the following steps:

step 1: deploying high-definition camera equipment in a coal conveying belt monitoring area;

step 2: the high-definition camera equipment acquires operation videos of the coal conveying belt in real time to obtain video stream data;

step 3: performing frame extraction on the video stream data according to frequency to obtain frame extraction images and storing the frame extraction images;

step 4: performing image recognition processing on the frame extraction image to obtain an edge characteristic curve of a designated area;

step 5: comparing the edge characteristic curve of the designated area with the non-overflowed coal characteristic curve to obtain a comparison threshold;

and if the comparison threshold exceeds the preset threshold, alarming, otherwise, returning to the step 2.

According to the coal conveying belt coal overflow detection method based on the edge recognition algorithm, the high-definition camera is used as the high-definition camera.

The specific method for obtaining the edge characteristic curve of the specified area by performing image recognition processing on the frame extraction image in the step 4 is as follows:

step 41: defining a region of interest image on the frame-drawing image;

step 42: high-pass filtering is adopted to enhance the high-frequency signal of the region-of-interest image, so that an enhanced image is obtained;

step 43: performing edge detection on the enhanced image to obtain a binary image containing edge characteristics;

step 44: and performing curve fitting processing on the edge characteristics in the binary image to obtain the edge characteristic curve of the appointed region.

The specific method for obtaining the binary image containing the edge characteristics by carrying out the edge detection on the enhanced image in the step 43 is as follows:

performing edge detection on the enhanced image by adopting an edge operator to obtain a comprehensive binary image containing strong edge and weak edge characteristic information;

and removing weak edge features in the comprehensive binary image by using a hystersis_threshold operator to obtain the binary image only containing strong edge features.

The specific method for obtaining the edge characteristic curve of the specified area by performing curve fitting processing on the edge characteristic in the binary image in the step 44 is as follows:

performing non-maximum suppression on the binary image by using a skeleton operator, and extracting strong edge features in a non-coal overflow state;

performing key point labeling on the strong edge characteristics;

and performing curve fitting on the marked key points to obtain an edge characteristic curve of the designated area.

According to the coal conveying belt coal overflow detection method based on the edge recognition algorithm, the region-of-interest image is an image with obvious edge characteristics on the frame extraction image;

the high frequency signal is an edge feature.

The second aspect is a coal conveying belt coal overflow detection system based on an edge recognition algorithm, wherein the system comprises a data processing module, an image material caching pool, an image processing module and a comparison feedback module;

the data processing module is used for acquiring the operation video of the high-definition camera equipment for acquiring the coal conveying belt in real time to obtain video stream data; the video stream data is subjected to frame extraction according to frequency to obtain frame extraction images, and the frame extraction images are stored in the image material cache pool;

the image processing module is used for acquiring the frame extraction image from the image material cache pool and performing image recognition processing to obtain an edge characteristic curve of a designated area;

the comparison feedback module is used for comparing the edge characteristic curve of the designated area with the non-overflowed coal characteristic curve to obtain a comparison threshold; and if the comparison threshold exceeds a preset threshold, sending feedback data to the data processing module to acquire the video stream data again or give an alarm.

In a third aspect, a chip, includes: a processor for calling and running a computer program from a memory, causing a device on which the chip is mounted to execute: the method of any one of the first aspects.

According to the method and the system for detecting coal overflow of the coal conveying belt based on the edge recognition algorithm

The high-definition camera equipment is deployed in the monitoring area, so that the video of the running condition of the coal conveying belt is collected in real time, the edge of the collected video of the coal conveying belt is identified by utilizing the edge identification algorithm, and the occurrence of the coal overflow condition of the coal conveying belt is judged.

Drawings

FIG. 1 is a flow chart of a coal conveyor belt coal overflow detection method based on an edge recognition algorithm.

Detailed Description

In order to make the technical means, the inventive features, the achievement of the purpose and the effect of the implementation of the invention easy to understand, the technical solutions in the embodiments of the invention will be clearly and completely described in conjunction with the specific drawings, and it is obvious that the described embodiments are some embodiments of the invention, not all embodiments.

All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be understood that the structures, proportions, sizes, etc. shown in the drawings are for illustration purposes only and should not be construed as limiting the invention to the extent that it can be practiced, since modifications, changes in the proportions, or otherwise, used in the practice of the invention, are not intended to be critical to the essential characteristics of the invention, but are intended to fall within the spirit and scope of the invention.

Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.

As shown in fig. 1, in a first aspect, a method for detecting coal overflow of a coal conveying belt based on an edge recognition algorithm includes the following steps:

step 3: performing frame extraction on video stream data according to frequency to obtain frame extraction images and storing the frame extraction images;

step 4: performing image recognition processing on the frame extraction image to obtain an edge characteristic curve of the appointed region;

step 5: comparing the edge characteristic curve of the designated area with the non-spilled coal characteristic curve to obtain a comparison threshold;

The specific method for obtaining the edge characteristic curve of the designated area by carrying out image recognition processing on the frame drawing image in the step 4 is as follows:

step 41: the image of the region of interest is defined on the frame extraction image, so that the data dimension can be reduced, the calculated amount of an algorithm is reduced, and the processing speed is increased;

step 42: high-pass filtering is adopted to enhance the high-frequency signal of the region-of-interest image, so as to obtain an enhanced image;

step 44: and performing curve fitting treatment on the edge characteristic in the binary image to obtain an edge characteristic curve of the appointed region.

and removing weak edge features in the comprehensive binary image by using a hystersis_threshold operator to obtain a binary image only containing strong edge features.

The specific method for obtaining the edge characteristic curve of the designated area by performing curve fitting processing on the edge characteristic in the binary image in the step 44 is as follows:

marking key points of the strong edge features;

and performing curve fitting on the marked key points to obtain the edge characteristic curve of the designated area.

the high frequency signal is an edge feature.

the data processing module is used for acquiring the operation video of the high-definition camera equipment for acquiring the coal conveying belt in real time to obtain video stream data; the video streaming data is subjected to frame extraction according to the frequency to obtain an extracted frame image, and the extracted frame image is stored in an image material cache pool;

the image processing module is used for acquiring a frame extraction image from the image material cache pool and carrying out image identification processing to obtain an edge characteristic curve of the appointed region;

the comparison feedback module is used for comparing the edge characteristic curve of the designated area with the non-overflowed coal characteristic curve to obtain a comparison threshold; and if the comparison threshold exceeds the preset threshold, sending feedback data to the data processing module to acquire the video stream data again or alarm.

When the coal conveying belt is particularly used, a high-definition monitoring camera is arranged at the coal dropping port of a certain coal conveying belt, vertical frames at two sides of the coal dropping port of the coal conveying belt are selected as identification areas, and the edge characteristic change condition of the frames at two sides in the areas is monitored, so that the purpose of identifying spilled coal is achieved; collecting video stream information of a designated area in real time, extracting 25 frames of picture information every 10 seconds for edge recognition, and carrying out edge detection by adopting a Canny edge recognition operator on the frame extraction image information of the recognition area; and connecting the obtained edge detection results by using a fitting curve to obtain two linear function line segments, designating a curve slope threshold according to the slopes of the two linear function line segments, comparing each time, and sending out a coal overflow alarm when the fitting curve obtained by edge detection does not accord with the curve slope threshold.

In a third aspect, a chip, includes: a processor for calling and running a computer program from the memory, causing the chip-mounted device to execute: the method of any one of the first aspects.

For example, the memory may include random access memory, flash memory, read-only memory, programmable read-only memory, non-volatile memory, registers, or the like;

the processor may be a central processing unit (Central Processing Unit, CPU) or the like, or an image processor (Graphic Processing Unit, GPU) memory may store executable instructions;

the processor may execute the execution instructions stored in the memory to implement the various processes described herein.

It will be appreciated that the memory in this embodiment may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory;

the nonvolatile memory may be a ROM (Read-only memory), a PROM (programmable Read-only memory), an EPROM (erasablprom, erasable programmable Read-only memory), an EEPROM (electrically erasable EPROM), or a flash memory.

The volatile memory may be a RAM (random access memory) which serves as an external cache;

by way of example, and not limitation, many forms of RAM are available, such as SRAM (static RAM), DRAM (dynamic RAM), SDRAM (synchronous DRAM), ddr SDRAM (DoubleDataRate SDRAM, double data rate synchronous DRAM), ESDRAM (Enhanced SDRAM), SLDRAM (synclinkdram), and DRRAM (directrambus RAM). The memory described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some embodiments, the memory stores the following elements, an upgrade package, an executable unit, or a data structure, or a subset thereof, or an extended set thereof: an operating system and application programs;

the operating system comprises various system programs, such as a framework layer, a core library layer, a driving layer and the like, and is used for realizing various basic services and processing hardware-based tasks;

and the application programs comprise various application programs and are used for realizing various application services. The program for implementing the method of the embodiment of the invention can be contained in an application program.

Those of skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of software and electronic hardware;

whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution;

those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation is not intended to be limiting.

In the embodiments of the present application, the disclosed systems, apparatuses, and methods may be implemented in other ways;

for example, the division of units or modules is merely a logic function division, and there may be another division manner when actually implemented;

for example, multiple units or modules or components may be combined or may be integrated into another system;

in addition, each functional unit or module in the embodiments of the present application may be integrated in one processing unit or module, or may exist alone physically, or the like.

It should be understood that, in various embodiments of the present application, the size of the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

The functions, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored on a machine-readable storage medium;

thus, the present disclosure may be embodied in the form of a software product, which may be stored on a machine-readable storage medium, which may include instructions for causing an electronic device to perform all or part of the processes of the present disclosure as described herein;

the storage medium may include a ROM, a RAM, a removable disk, a hard disk, a magnetic disk, or an optical disk, etc. various media in which program codes can be stored.

In summary, according to the method and the system for detecting the coal overflow of the coal conveying belt based on the edge recognition algorithm, the high-definition camera equipment is deployed and fixed in a monitoring area, so that the video of the running condition of the coal conveying belt is collected in real time, the image characteristic change according to the edge side is recognized on the edge side of the collected video of the coal conveying belt by utilizing the edge recognition algorithm, and whether the coal overflow condition of the coal conveying belt occurs is judged.

The foregoing describes specific embodiments of the invention. It is to be understood that the invention is not limited to the specific embodiments described above, wherein devices and structures not described in detail are to be understood as being implemented in a manner common in the art; numerous variations, changes, or substitutions of light can be made by one skilled in the art without departing from the spirit of the invention and the scope of the claims.

Claims

1. The coal conveying belt coal overflow detection method based on the edge recognition algorithm is characterized by comprising the following steps of:

2. The method for detecting coal overflow of a coal conveying belt based on an edge recognition algorithm according to claim 1, wherein the high-definition camera is a high-definition camera.

3. The method for detecting coal overflow of a coal conveying belt based on an edge recognition algorithm as claimed in claim 2, wherein the specific method for obtaining the edge characteristic curve of the designated area by performing image recognition processing on the frame-extracted image in step 4 is as follows:

step 41: defining a region of interest image on the frame-drawing image;

4. The method for detecting coal overflow of a coal conveyor belt based on an edge recognition algorithm according to claim 3, wherein the specific method for performing edge detection on the enhanced image in step 43 to obtain a binary image containing edge features is as follows:

5. The method for detecting coal overflow of a coal conveyor belt based on an edge recognition algorithm as claimed in claim 4, wherein the specific method for performing curve fitting processing on the edge features in the binary image to obtain the edge feature curve of the specified area in step 44 is as follows:

performing key point labeling on the strong edge characteristics;

6. The method for detecting coal conveying belt coal overflow based on an edge recognition algorithm according to any one of claims 3-5, wherein the region of interest image is an image with obvious edge characteristics on the frame extraction image;

the high frequency signal is an edge feature.

7. The coal conveying belt coal overflow detection system based on the edge recognition algorithm is characterized by comprising a data processing module, an image material caching pool, an image processing module and a comparison feedback module;

8. A chip, comprising: a processor for calling and running a computer program from a memory, causing a device on which the chip is mounted to execute: the method of any one of claims 1-6.