Submerged chain conveyor liquid level measuring method and device, storage medium and electronic equipment

Abstract

The invention discloses a submerged chain conveyor liquid level measuring method and device, a storage medium and electronic equipment, and relates to the technical field of data processing.The method comprises the steps that image data, collected by an industrial camera, of a liquid level ruler in a submerged chain conveyor slag pool is obtained; preprocessing the image data based on a bilateral filter to obtain recognizable image data; the recognizable image data are input into a preset deep learning model for image recognition, point location information of the liquid level ruler is obtained, and the preset deep learning model is used for recognizing the point location information, contained in the image, of the liquid level ruler; and the liquid level reading of the liquid level ruler is determined according to the point location information. Compared with the prior art, the real-time image can be processed by utilizing a computer image recognition technology, the working safety is greatly improved while the measurement accuracy is improved, the environmental pollution and corrosion conditions of measurement components are greatly reduced, the labor and equipment cost can be reduced, and the measurement accuracy is improved. And the accuracy of the measured liquid level can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, storage medium and electronic device for measuring the liquid level of a slag remover. Background Art

[0002] Slag Removal Machine is a mechanical device used to remove slag from the slag pool, usually used in thermal power plants, industrial boilers and other facilities. The level of the slag removal machine refers to the level of liquid (usually cooling water) in the slag pool. Monitoring the level of the slag removal machine is essential to ensure the normal operation and safe production of the equipment.

[0003] At present, the liquid level of the slag picker is mainly measured by the tuning fork method, the float level meter measurement method, the radio frequency admittance method, etc. However, the high temperature in the slag pool of the slag picker (generally 50°C to 70°C) and the large slag content cause serious difficulties in the slag pool level measurement. For example, the slag mud blocks the gap of the tuning fork level meter, making it impossible to measure the liquid level and requiring a large maintenance workload. The slag water adheres to the float and has a large corrosive effect, causing the float level meter to have a short service life. Similarly, the corrosiveness of the slag water damages the radio frequency admittance probe and the probe rod, resulting in the inability to accurately measure the liquid level in the slag pool of the slag picker, and also leading to an increase in the measurement cost. Summary of the invention

[0004] In view of this, the present application provides a method, device, storage medium and electronic device for measuring the liquid level of a slag scoop machine. The main purpose is to improve the technical problem that the current existing technology cannot accurately measure the liquid level in the slag pool of the slag scoop machine, and also leads to an increase in measurement costs.

[0005] In a first aspect, the present application provides a method for measuring the liquid level of a slag scoop machine, comprising:

[0006] Obtain image data of a liquid level scale in a slag pool of a slag dredger collected by an industrial camera;

[0007] Preprocessing the image data based on a bilateral filter to obtain recognizable image data;

[0008] Inputting the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, wherein the preset deep learning model is used to recognize the point information of the liquid level scale contained in the image;

[0009] The liquid level reading of the liquid level scale is determined based on the point information.

[0010] Optionally, the preprocessing the image data based on a bilateral filter to obtain recognizable image data includes:

[0011] Determining a target area in the image data that meets a noise reduction condition;

[0012] The target area is smoothed and denoised based on a bilateral filter to obtain denoised image data.

[0013] Optionally, the preprocessing the image data based on a bilateral filter to obtain recognizable image data further includes:

[0014] Performing image boundary division on the denoised image data to determine the boundary of the denoised image data;

[0015] The image data after the noise reduction is subjected to image interference removal processing, and the image data after the image data boundary is removed is obtained.

[0016] Optionally, the preprocessing the image data based on a bilateral filter to obtain recognizable image data further includes:

[0017] Performing image enhancement processing on the de-interferenced image data by using a single-scale Retinex algorithm;

[0018] The image after image enhancement processing is determined as the recognizable image.

[0019] Optionally, determining the liquid level reading of the liquid level scale according to the point information includes:

[0020] Performing reading modeling on the point information according to a predetermined transformation standard to obtain modeling data corresponding to the point information;

[0021] The liquid level reading of the liquid level scale is determined based on the modeling data corresponding to the point information.

[0022] Optionally, also include:

[0023] Based on a predetermined mapping relationship between the liquid level reading and the output current of the slag scooping machine, determining the output current corresponding to the liquid level reading of the liquid level scale;

[0024] The output current is connected to a display system, and the liquid level reading is displayed through the display system.

[0025] In a second aspect, the present application provides a device for measuring the liquid level of a slag scoop machine, comprising:

[0026] An acquisition module is configured to acquire image data of a liquid level scale in a slag pool of a slag dredger collected by an industrial camera;

[0027] a processing module, configured to pre-process the image data based on a bilateral filter to obtain recognizable image data;

[0028] A recognition module is configured to input the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, wherein the preset deep learning model is used to recognize the point information of the liquid level scale contained in the image;

[0029] The determination module is configured to determine the liquid level reading of the liquid level scale according to the point information. In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for measuring the liquid level of the slag scoop machine described in the first aspect is implemented.

[0030] In a fourth aspect, the present application provides an electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the method for measuring the liquid level of a slag remover as described in the first aspect when executing the computer program.

[0031] In a fifth aspect, the present application provides a computer program product, which includes a computer program, characterized in that when the computer program is executed by a processor, the method for measuring the liquid level of a slag remover described in the first aspect is implemented.

[0032] By means of the above technical scheme, the present application provides a method, device, storage medium and electronic device for measuring the liquid level of a slag scoop machine. Compared with the current existing technology, the present application obtains the image data of the liquid level scale in the slag pool of the slag scoop machine collected by an industrial camera; and pre-processes the image data based on a bilateral filter to obtain recognizable image data; inputs the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, and the preset deep learning model is used to identify the point information of the liquid level scale contained in the image; and determines the liquid level reading of the liquid level scale based on the point information. Computer image recognition technology can be used to process real-time images. Compared with directly measuring the liquid level of the slag pool of the slag scoop machine in an environmentally hazardous area, the measurement accuracy is improved while the work safety is greatly improved, and the environmental pollution and corrosion of the measuring components are greatly reduced, which can not only reduce labor and equipment costs, but also improve the accuracy of the measured liquid level. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0035] Figure 1 A schematic flow chart of a method for measuring the liquid level of a slag scooping machine provided in an embodiment of the present application is shown;

[0036] Figure 2 A schematic flow chart of a method for measuring the liquid level of a slag scooping machine provided in an embodiment of the present application is shown;

[0037] Figure 3 A schematic structural diagram of a device for measuring the liquid level of a slag scooping machine provided in an embodiment of the present application is shown;

[0038] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0039] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0040] In order to improve the current existing technology, the slag pool of the slag machine has high temperature (generally 50℃ to 70℃) and large slag content, which cause serious difficulties in measuring the liquid level in the slag pool. For example, the slag mud blocks the gap of the tuning fork level meter, making it impossible to measure the liquid level and requiring a lot of maintenance. The slag water adheres to the float and has a large corrosive effect, which causes the float level meter to have a short service life. Similarly, the corrosiveness of the slag water damages the radio frequency admittance probe and the probe rod, resulting in the inability to accurately measure the liquid level in the slag pool of the slag machine. This embodiment provides a method for measuring the liquid level of a slag machine, such as Figure 1 As shown, the method includes:

[0041] Step 101: Acquire image data of a liquid level scale in a slag pool of a slag dredger collected by an industrial camera.

[0042] In the embodiment of the present application, an industrial camera is a high-performance camera designed for industrial automation and machine vision applications. This type of camera has the characteristics of high resolution, high speed, and high precision, and is widely used in manufacturing, logistics, medical treatment, scientific research and other fields. The purpose of designing an industrial camera is to meet the special needs of image acquisition in industrial environments, such as high-speed shooting, high-precision measurement, and stability in harsh environments.

[0043] In some examples, a slag removal machine is a mechanical device specifically used to remove industrial slag, which is usually used in thermal power plants, industrial boilers and other facilities. The purpose of the slag removal machine is to remove the slag produced during the combustion process from the furnace or ash hopper and transport it to a designated location for treatment or disposal.

[0044] Specifically, a slag scraper is usually installed at the bottom of the furnace or at the ash hopper to collect the slag produced during the combustion process. The slag enters the slag scraper through gravity or a conveying device. The slag scraper is equipped with a conveying device such as a chain or a scraper to transport the slag from the collection point to the processing point. The conveying device is usually driven by a motor and the speed can be adjusted as needed. In order to prevent the high-temperature slag from damaging the equipment, a cooling system is usually provided inside the slag scraper. The cooling system can use water cooling or air cooling to reduce the temperature of the slag. The cooled slag can be transported to a designated location for further processing, including but not limited to composting, landfilling, recycling, etc.

[0045] For this embodiment, the level gauge or level indicator in the slag pool is a device used to monitor the liquid level height of the liquid (usually cooling water) in the slag pool. This monitoring is essential to ensure the normal operation and safety of the equipment. Too high or too low a liquid level in the slag pool may cause a series of problems, so it is very important to accurately monitor and control the liquid level.

[0046] In the embodiment of the present application, the image data is image data of a liquid level scale in a slag pool of a slag dredger collected by an industrial camera.

[0047] Step 102: pre-process the image data based on a bilateral filter to obtain recognizable image data.

[0048] In some examples, a bilateral filter is an advanced filtering technique used in image processing that can smooth an image while preserving edge details. The bilateral filter combines spatial proximity and intensity similarity, making it very suitable for removing noise without losing edge information of the image.

[0049] The bilateral filter calculates the new value of each pixel through two Gaussian functions, including: the spatial Gaussian function is used to control the spatial proximity of pixels, and the standard deviation is usually used to control the influence range of spatial proximity; the Gaussian function (Value Gaussian) is used to control the similarity of pixel values, and the standard deviation is usually used to control the influence range of pixel value similarity.

[0050] Specifically, the bilateral filter can preserve edge information well while smoothing the image, and can limit the weight of edge pixels by value Gaussian function to avoid edge blur; the bilateral filter can effectively remove random noise in the image, and has a good removal effect on salt and pepper noise and Gaussian noise.

[0051] In an embodiment of the present application, the recognizable image data is image data that can be recognized by the following preset deep learning model.

[0052] Step 103: input the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale.

[0053] Among them, the preset deep learning model is used to identify the point information of the liquid level scale contained in the image.

[0054] In an embodiment of the present application, the preset deep learning model can be a Mask Region-based Convolutional Neural Network (Mask R-CNN). Specifically, Mask R-CNN is an advanced deep learning model mainly used for instance segmentation. It is improved based on FasterR-CNN and can not only perform object detection, but also generate pixel-level segmentation masks for each detected object, thereby distinguishing different object instances in the image.

[0055] In some examples, Mask R-CNN can simultaneously perform object detection and pixel-level segmentation. The detection task determines the location and category of the object, and the segmentation task generates an accurate pixel-level mask for each object. Mask R-CNN inherits the Region Proposal Network (RPN) of Faster R-CNN, which improves the speed and accuracy of detection. The candidate regions (Region of Interest, RoI) generated by RPN are used for object classification and segmentation. Mask R-CNN can use different basic network architectures (such as ResNet, VGG, etc.). The model can adapt to different application scenarios by adjusting the network structure and training parameters. Through pixel-level segmentation, Mask R-CNN can accurately identify the boundaries of objects and is suitable for fine object segmentation tasks.

[0056] For this embodiment, the recognizable image can be recognized by the Mask R-CNN model to obtain the point information of the liquid level scale.

[0057] Specifically, a liquid level gauge is usually set with several points (also called scales, measuring points), which can help monitor whether the liquid level is within a safe range.

[0058] Step 104: Determine the liquid level reading of the liquid level scale according to the point information.

[0059] In the embodiment of the present application, the liquid level reading of the liquid level gauge can determine whether the liquid level in the slag pool of the slag remover is within a safe range.

[0060] Compared with the current existing technology, this embodiment obtains image data of the liquid level scale in the slag pool of the slag scavenger collected by an industrial camera; and pre-processes the image data based on a bilateral filter to obtain recognizable image data; inputs the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, and the preset deep learning model is used to identify the point information of the liquid level scale contained in the image; and determines the liquid level reading of the liquid level scale based on the point information. Computer image recognition technology can be used to process real-time images. Compared with directly measuring the liquid level in the slag pool of the slag scavenger in an environmentally hazardous area, the measurement accuracy is improved while the work safety is greatly improved, and the environmental pollution and corrosion of the measuring components are greatly reduced, which can not only reduce labor and equipment costs, but also improve the accuracy of the measured liquid level.

[0061] As a refinement and extension of the above embodiment, when performing preprocessing of the image data based on a bilateral filter to obtain recognizable image data, the following methods may be used but are not limited to: Figure 2 As shown, the method includes:

[0062] Step 201: Determine a target area in the image data that meets the noise reduction condition.

[0063] In some examples, image noise reduction refers to the process of removing noise from an image in digital image processing to improve image quality. The noise in the image may come from various factors in the imaging process, such as sensor noise, transmission errors, lighting conditions, etc. The purpose of noise reduction is to restore the true content of the image to make it clearer and more usable.

[0064] Specifically, the noise reduction conditions in the present application can be set according to actual conditions, and the specific content of the noise reduction conditions is not limited here.

[0065] Furthermore, the target area is an area in the image that meets the noise reduction condition.

[0066] Exemplarily, if the image data is image A, image B, and image C, target region A, target region B, and target region C meeting the noise reduction condition in image A, image B, and image C may be determined respectively.

[0067] Step 202: Perform regional smoothing and noise reduction on the target area based on a bilateral filter to obtain image data after noise reduction.

[0068] In the embodiment of the present application, regional smoothing denoising is an image processing technique that removes noise by applying a smoothing operation in a local area of ​​an image. This method is based on the assumption that within a certain area, the difference between adjacent pixels is not large, and the noise is random and discontinuous. Through smoothing, the impact of these random changes can be weakened, thereby achieving the purpose of noise reduction.

[0069] Specifically, the core idea of ​​regional smoothing denoising is to apply a smoothing operation in a local area of ​​the image. Common smoothing operations include mean filtering, median filtering, etc. These methods reduce the impact of noise by changing the value of each pixel while trying to preserve the edges and other important features of the image.

[0070] In some examples, the process of performing smoothing area denoising on a target area in the present application may include: determining a target area, wherein the target area may be a selection of a suitable window size that covers a local area in the image. The selection of the window size depends on the characteristics of the noise and the content of the image. Statistics of pixel values, such as mean, median, etc., are calculated in the target area. The value of the central pixel of the target area is updated using the calculated statistics. This step is repeated until the entire image is traversed. During the smoothing process, an appropriate method (such as bilateral filtering) is used to retain the edge information of the image, thereby obtaining the denoised image data.

[0071] Step 203: perform image boundary division on the denoised image data to determine the boundary of the denoised image data.

[0072] In this embodiment, image boundary division is performed on the denoised image data, and determining the boundary of the denoised image data may specifically be to effectively process interference in the image without confusing the image boundary.

[0073] Step 204: performing image interference removal processing on the image data after removing the image data boundary in the denoised image data to obtain image data after interference removal.

[0074] Exemplarily, boundary preservation is a key goal in image processing because boundaries usually represent important features in an image, such as the outline of an object. The embodiment of the present application can be processed using a bilateral filtering method. Specifically, bilateral filtering is a nonlinear filtering technique that can well preserve edges while smoothing an image. Bilateral filtering uses two Gaussian functions to calculate the new value of each pixel: one for spatial proximity and the other for pixel value similarity. Using bilateral filtering for denoising can remove noise while maintaining edge information.

[0075] Exemplarily, in an embodiment of the present application, the noise-reduced data can be subjected to bilateral filtering, thereby effectively processing interference in the image without confusing the image boundaries, thereby obtaining de-interferenced image data.

[0076] Step 205: Perform image enhancement processing on the de-interferenced image data using a single-scale Retinex algorithm.

[0077] In some examples, Single Scale Retinex (SSR) is a technique for image enhancement that aims to simulate the way the human visual system processes images. Retinex theory states that the human visual system is able to adjust the ability to perceive brightness based on changes in lighting conditions. The algorithm is particularly suitable for enhancing image contrast, improving the performance of images under different lighting conditions, and effectively handling interference in images without confusing boundaries.

[0078] Specifically, the single-scale Retinex algorithm assumes that the reflection component and illumination component of the image can be separated. The image I(x, y) can be expressed as the product of the reflection component R(x, y) and the illumination component L(x, y); the goal of the single-scale Retinex algorithm is to estimate the reflection component R(x, y) from the image, thereby enhancing the contrast of the image. The algorithm achieves this goal by calculating the brightness ratio of each pixel to its surrounding pixels.

[0079] In an embodiment of the present application, since the image is polluted by various light waves and lighting in the environment, the image is enhanced using a single-scale Retinex algorithm. Specifically, the specific process of performing image enhancement processing on the de-interferenced image data using a single-scale Retinex algorithm may include: using an image processing library (such as OpenCV) to load the de-interferenced image data, filtering the image using a Gaussian kernel to obtain an illumination component, calculating a reflection component using the original image and the illumination component, and normalizing the calculated reflection component to display an enhanced image within the range of [0,255]. The enhanced image is the recognizable image in the present application.

[0080] Step 206: Determine the image after image enhancement processing as a recognizable image.

[0081] Further, when determining the liquid level reading of the liquid level scale according to the point information, the following method may be used but is not limited to, and the method includes:

[0082] Step 11: Model the point information according to a predetermined transformation standard to obtain modeling data corresponding to the point information.

[0083] In the embodiment of the present application, the predetermined transformation standard may be a Hough Transform. Specifically, the Hough Transform is a classic algorithm used in the field of image processing and computer vision, and is mainly used to detect regular shapes such as straight lines, circles, and ellipses in images. The Hough Transform is particularly effective in detecting straight lines in images, and can handle noise and incomplete line segments.

[0084] In some examples, the basic idea of ​​Hough transform is to detect specific shapes in an image through a voting mechanism in parameter space. For line detection, Hough transform uses parameters in polar coordinates to represent the line and finds the parameter combination that is most likely to represent the line through cumulative voting.

[0085] Step 12: Determine the liquid level reading of the liquid level scale based on the modeling data corresponding to the point information.

[0086] Exemplarily, the present application can perform reading modeling through algorithms such as Hough transform to correctly read the liquid level reading of the slag dredger liquid level scale.

[0087] After determining the liquid level reading of the liquid level scale according to the point information, the following method may be used but is not limited to:

[0088] Step 21: Based on a predetermined mapping relationship between the liquid level reading and the output current of the slag remover, determine the output current corresponding to the liquid level reading of the liquid level scale.

[0089] Step 22: Connect the output current to the display system, and display the liquid level reading through the display system.

[0090] Exemplarily, the present application can establish a mapping relationship table between readings and output current 4-20mA in a computer, complete the connection of the computer output signal to the 4-20mA circuit board, and connect the standard current signal 4-20mA to the DCS system or other meters to display the slag machine liquid level in real time.

[0091] Compared with the current existing technology, this embodiment obtains image data of the liquid level scale in the slag pool of the slag scavenger collected by an industrial camera; and pre-processes the image data based on a bilateral filter to obtain recognizable image data; inputs the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, and the preset deep learning model is used to identify the point information of the liquid level scale contained in the image; and determines the liquid level reading of the liquid level scale based on the point information. Computer image recognition technology can be used to process real-time images. Compared with directly measuring the liquid level in the slag pool of the slag scavenger in an environmentally hazardous area, the measurement accuracy is improved while the work safety is greatly improved, and the environmental pollution and corrosion of the measuring components are greatly reduced, which can not only reduce labor and equipment costs, but also improve the accuracy of the measured liquid level.

[0092] Further, as Figure 1 and Figure 2 The specific implementation of the method shown in the embodiment provides a device for measuring the liquid level of a slag dredger, such as Figure 3 As shown, the device includes: an acquisition module 31, a processing module 32, an identification module 33, and a determination module 34.

[0093] An acquisition module 31 is configured to acquire image data of a liquid level scale in a slag pool of a slag dredger collected by an industrial camera;

[0094] A processing module 32 is configured to pre-process the image data based on a bilateral filter to obtain recognizable image data;

[0095] The recognition module 33 is configured to input the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, wherein the preset deep learning model is used to recognize the point information of the liquid level scale contained in the image;

[0096] The determination module 34 is configured to determine the liquid level reading of the liquid level scale according to the point information. In some examples of this embodiment, the processing module 32 is specifically configured to determine a target area in the image data that meets the noise reduction condition; and perform regional smoothing and noise reduction on the target area based on a bilateral filter to obtain the noise-reduced image data.

[0097] In some examples of this embodiment, the processing module 32 is further configured to perform image boundary division on the denoised image data to determine the boundary of the denoised image data; perform image interference removal processing on the image data after removing the image data boundary from the denoised image data to obtain the de-interferenced image data.

[0098] In some examples of this embodiment, the processing module 32 is further configured to perform image enhancement processing on the recognizable image data through a single-scale Retinex algorithm; and determine the image after the image enhancement processing as the recognizable image.

[0099] In some examples of this embodiment, the determination module 34 is specifically configured to perform reading modeling on the point information according to a predetermined transformation standard to obtain modeling data corresponding to the point information; and determine the liquid level reading of the liquid level scale based on the modeling data corresponding to the point information.

[0100] In some examples of this embodiment, the determination module 34 is also configured to determine the output current corresponding to the liquid level reading of the liquid level scale based on a predetermined mapping relationship between the liquid level reading and the output current of the slag scooper; connect the output current to a display system, and display the liquid level reading through the display system.

[0101] It should be noted that for other corresponding descriptions of the functional units involved in the device for measuring the liquid level of a slag scoop provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0102] Based on the above Figure 1 and Figure 2 The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The method shown.

[0103] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0104] like Figure 4 The figure shows a hardware structure diagram of an electronic device of the present invention, including:

[0105] at least one processor 401; and,

[0106] A memory 402 is communicatively connected to at least one of the processors 401; wherein,

[0107] The memory 402 stores instructions that can be executed by at least one of the processors. The instructions are executed by at least one of the processors so that the at least one processor can execute the above-mentioned method for measuring the liquid level of the slag machine.

[0108] Figure 4 A processor 401 is taken as an example.

[0109] The electronic device may further include: an input device 403 and a display device 404 .

[0110] The processor 401, the memory 402, the input device 403 and the display device 404 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0111] The memory 402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the method for measuring the liquid level of a slag scoop machine in the embodiment of the present application, for example, Figure 1 and Figure 2 The processor 401 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 402, that is, the method for measuring the liquid level of the slag extractor in the above embodiment is implemented.

[0112] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the method for measuring the liquid level of the slag machine, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 402 may optionally include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to the device for executing the method for measuring the liquid level of the slag machine via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0113] The input device 403 can receive user clicks and generate signal inputs related to user settings and function control of the slag machine liquid level measurement method. The display device 404 can include display devices such as a display screen.

[0114] The one or more modules are stored in the memory 402, and when being executed by the one or more processors 401, the method for measuring the liquid level of the slag machine in any of the above method embodiments is executed.

[0115] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0116] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0117] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0118] Through the description of the above implementation methods, the technical personnel in this field can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the scheme of this embodiment, compared with the current prior art, this embodiment obtains the image data of the liquid level scale in the slag pool of the slag dredger collected by the industrial camera; and pre-processes the image data based on the bilateral filter to obtain recognizable image data; inputs the recognizable image data into the preset deep learning model for image recognition to obtain the point information of the liquid level scale, and the preset deep learning model is used to identify the point information of the liquid level scale contained in the image; according to the point information, the liquid level reading of the liquid level scale is determined. Computer image recognition technology can be used to process real-time images. Compared with directly measuring the liquid level of the slag pool of the slag dredger in the environmentally dangerous area, the measurement accuracy is improved while the work safety is greatly improved, and the environmental pollution and corrosion of the measuring components are greatly reduced, which can not only reduce the labor and equipment costs, but also improve the accuracy of the measured liquid level.

[0119] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0120] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.

Claims

1. A method for measuring the liquid level of a slag dredger, characterized in that: include: Obtain image data of a liquid level scale in a slag pool of a slag dredger collected by an industrial camera; Preprocessing the image data based on a bilateral filter to obtain recognizable image data; Inputting the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, wherein the preset deep learning model is used to recognize the point information of the liquid level scale contained in the image; The liquid level reading of the liquid level scale is determined based on the point information.

2. The method according to claim 1, characterized in that: The preprocessing of the image data based on the bilateral filter to obtain recognizable image data includes: Determining a target area in the image data that meets a noise reduction condition; The target area is smoothed and denoised based on a bilateral filter to obtain denoised image data.

3. The method according to claim 2, characterized in that The preprocessing of the image data based on the bilateral filter to obtain recognizable image data also includes: Performing image boundary division on the denoised image data to determine the boundary of the denoised image data; The image data after the noise reduction is subjected to image interference removal processing, and the image data after the image data boundary is removed is obtained.

4. The method according to claim 3, characterized in that The preprocessing of the image data based on the bilateral filter to obtain recognizable image data also includes: Performing image enhancement processing on the de-interferenced image data by using a single-scale retinal Retinex algorithm; The image after image enhancement processing is determined as the recognizable image.

5. The method according to claim 4, characterized in that Determining the liquid level reading of the liquid level scale according to the point information includes: Performing reading modeling on the point information according to a predetermined transformation standard to obtain modeling data corresponding to the point information; The liquid level reading of the liquid level scale is determined based on the modeling data corresponding to the point information.

6. The method according to claim 5, characterized in that The method further comprises: Based on a predetermined mapping relationship between the liquid level reading and the output current of the slag scooping machine, determining the output current corresponding to the liquid level reading of the liquid level scale; The output current is connected to a display system, and the liquid level reading is displayed through the display system.

7. A device for measuring the liquid level of a slag dredger, characterized in that: include: An acquisition module is configured to acquire image data of a liquid level scale in a slag pool of a slag dredger collected by an industrial camera; a processing module, configured to pre-process the image data based on a bilateral filter to obtain recognizable image data; A recognition module is configured to input the recognizable image data into a preset deep learning model for image recognition to obtain the point information of the liquid level scale, wherein the preset deep learning model is used to recognize the point information of the liquid level scale contained in the image; The determination module is configured to determine the liquid level reading of the liquid level scale according to the point information.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images