Visual intelligent fluid monitoring method and device

Abstract

The invention provides a visual intelligent fluid monitoring method and device, and relates to the field of fluid monitoring, and the method comprises the steps: inputting an obtained strip steel quality image into a pre-constructed strip steel defect recognition model, and obtaining a strip steel quality monitoring result; inputting the obtained cleaning fluid state image into a pre-constructed cleaning fluid color difference recognition model to obtain a cleaning fluid health state monitoring result; performing image analysis on the obtained pipe valve event driving image to obtain a pipe valve image analysis result; and performing visual intelligent fluid monitoring according to the strip steel quality monitoring result, the cleaning fluid health state monitoring result and the pipe valve image analysis result. According to the system, the strip steel quality, the cleaning effect and pipe valve parameters can be checked through the industrial camera, the electric signal transmission quantity of the system is reduced, the system is more concise, and the monitoring content is richer.

Description

Technical Field

[0001] The present application relates to the field of fluid monitoring, and specifically to a visual intelligent fluid monitoring method and device. Background Art

[0002] In traditional factories, special sensors are needed to monitor parameters such as temperature, liquid level and pressure of fluid systems, and each sensor requires a set of cables to complete remote data transmission. Therefore, in order to achieve remote transmission intelligent monitoring, traditional factories need to configure a large number of sensors and cables, which has high investment and maintenance costs. In other words, traditional fluid monitoring uses sensors for data collection and analysis, which has the disadvantage of high production and maintenance costs.

[0003] For example, the existing technology "A fluid transport network automatic monitoring system" monitors the system by detecting information such as fluid pressure through an intelligent flow valve. It has many sensors, few detection items, and a complex system. In addition, its sensor detection items are single, and multiple sets of sensor modules need to be configured to output multiple data.

[0004] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section. Summary of the invention

[0005] In response to the problems in the prior art, the present application provides a visual intelligent fluid monitoring method and device, which can check the quality of strip steel, cleaning effect, and pipe and valve parameters through an industrial camera, reduce the system's electrical signal transmission volume, make the system simpler, and enrich the monitoring content.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] In a first aspect, the present application provides a visual intelligent fluid monitoring method, comprising:

[0008] The acquired strip quality image is input into a pre-built strip defect recognition model to obtain the strip quality monitoring result;

[0009] Input the acquired cleaning fluid status image into a pre-built cleaning fluid color difference recognition model to obtain the cleaning fluid health status monitoring result;

[0010] Performing image analysis on the acquired pipe valve event-driven image to obtain a pipe valve image analysis result;

[0011] Visual intelligent fluid monitoring is performed based on the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

[0012] Furthermore, the step of inputting the acquired strip steel quality image into a pre-trained strip steel defect recognition model to obtain a strip steel quality monitoring result includes:

[0013] Acquiring the strip steel quality image by using an image acquisition device disposed behind the cleaning fluid system dryer;

[0014] Defect features are extracted from the strip quality image, and the extracted defect features are input into the strip defect recognition model to obtain the strip quality monitoring result; wherein the strip defect recognition model is constructed based on a strip product defect data set.

[0015] Furthermore, the step of inputting the acquired cleaning fluid status image into a pre-trained cleaning fluid color difference recognition model to obtain a cleaning fluid health status monitoring result includes:

[0016] Using an image acquisition device disposed at a sampling port of the magnetic filtration device to acquire the cleaning fluid state image;

[0017] The color difference features of the cleaning fluid status image are extracted, and the extracted color difference features are input into the cleaning fluid color difference recognition model to obtain the cleaning fluid health status monitoring result; wherein, the cleaning fluid color difference recognition model is constructed based on the cleaning fluid color difference data set.

[0018] Furthermore, the image analysis of the acquired pipe valve event driven image to obtain the pipe valve image analysis result includes:

[0019] Acquiring the pipe valve event driven image by using an image acquisition device disposed in the pipe valve area;

[0020] If the pipe valve event driving image is a unit driving event, predict the change parameter according to the unit driving instruction, and compare the actual parameter obtained by analyzing the pipe valve event driving image with the change parameter to obtain the pipe valve image analysis result;

[0021] If the pipe valve event driving image is a human operation event, the actual parameters obtained by analyzing the pipe valve event driving image are compared with the preset parameters to obtain the pipe valve image analysis result;

[0022] If the pipe valve event-driven image is a dynamic picture change event, the pipe valve event-driven image is analyzed using a gray level co-occurrence matrix to determine whether the pipe valve vibrates or leaks, thereby obtaining the pipe valve image analysis result.

[0023] Furthermore, the visual intelligent fluid monitoring is performed according to the strip quality monitoring result, the cleaning fluid health status monitoring result and the pipe valve image analysis result, including:

[0024] Feedback the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results to the monitoring interface;

[0025] According to the flow value, temperature value and pressure value in the actual parameters, the liquid replenishing valve, the temperature control valve and the pressure valve are controlled respectively.

[0026] In a second aspect, the present application provides a visual intelligent fluid monitoring device, comprising:

[0027] The strip steel monitoring unit is used to input the acquired strip steel quality image into a pre-built strip steel defect recognition model to obtain the strip steel quality monitoring result;

[0028] A washing liquid monitoring unit, used to input the acquired washing liquid status image into a pre-built washing liquid color difference recognition model to obtain a washing liquid health status monitoring result;

[0029] A pipe valve monitoring unit, used for performing image analysis on the acquired pipe valve event driven image to obtain a pipe valve image analysis result;

[0030] The intelligent fluid monitoring unit is used to perform visual intelligent fluid monitoring based on the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

[0031] Furthermore, the strip steel monitoring unit comprises:

[0032] The strip steel image acquisition device is used to acquire the strip steel quality image by using the image acquisition device arranged after the cleaning fluid system dryer;

[0033] The strip steel monitoring device is used to extract defect features from the strip steel quality image and input the extracted defect features into the strip steel defect recognition model to obtain the strip steel quality monitoring result; wherein the strip steel defect recognition model is constructed based on a strip steel product defect data set.

[0034] Furthermore, the washing liquid monitoring unit comprises:

[0035] A washing liquid image acquisition device, used to acquire the washing liquid state image by using an image acquisition device arranged at the sampling port of the magnetic filtration device;

[0036] The cleaning liquid monitoring device is used to extract color difference features from the cleaning liquid status image, and input the extracted color difference features into the cleaning liquid color difference recognition model to obtain the cleaning liquid health status monitoring result; wherein the cleaning liquid color difference recognition model is constructed based on the cleaning liquid color difference data set.

[0037] Furthermore, the pipe valve monitoring unit comprises:

[0038] A driving image acquisition device, used for acquiring the pipe valve event driving image by using an image acquisition device arranged in the pipe valve area;

[0039] A unit drive monitoring device, for predicting a change parameter according to a unit drive instruction if the pipe valve event drive image is a unit drive event, and comparing an actual parameter obtained by analyzing the pipe valve event drive image with the change parameter to obtain an analysis result of the pipe valve image;

[0040] A human operation monitoring device, used for comparing actual parameters obtained by analyzing the pipe valve event driving image with preset parameters to obtain the pipe valve image analysis result if the pipe valve event driving image is a human operation event;

[0041] The dynamic change monitoring device is used to analyze the pipe valve event-driven image using a grayscale co-occurrence matrix if the pipe valve event-driven image is a dynamic picture change event, determine whether the pipe valve vibrates or leaks, and obtain the pipe valve image analysis result.

[0042] Furthermore, the intelligent fluid monitoring unit comprises:

[0043] A monitoring result feedback device, used for feeding back the strip quality monitoring result, the cleaning liquid health status monitoring result and the pipe valve image analysis result to the monitoring interface;

[0044] The pipe valve control device is used to control the liquid replenishing valve, the temperature control valve and the pressure valve respectively according to the flow value, temperature value and pressure value in the actual parameters.

[0045] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the visual intelligent fluid monitoring method when executing the program.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the visual intelligent fluid monitoring method when executed by a processor.

[0047] In a fifth aspect, the present application provides a computer program product, comprising a computer program / instruction, which implements the steps of the visual intelligent fluid monitoring method when executed by a processor.

[0048] In response to the problems in the prior art, the visual intelligent fluid monitoring method and device provided by this application can collect monitoring images through industrial cameras and lenses, and use artificial intelligence recognition systems to extract targets, and then perform color difference correction and grayscale processing to reduce the sampling data, and then analyze the data, and display the analyzed data on the monitoring interface for monitoring, alarm and automatic chain control. Among them, industrial cameras and lenses are set at the outlet of the cleaning system for strip quality monitoring; industrial cameras and lenses are set at the system sampling port for monitoring the health status of the cleaning fluid; and several industrial cameras and lenses are installed in the system area to view and transmit the status of valves, instruments and pipelines. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention 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, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 This is a flow chart of the visual intelligent fluid monitoring method in an embodiment of the present application;

[0051] Figure 2 This is a flow chart of obtaining the strip quality monitoring results in the embodiment of the present application;

[0052] Figure 3 A flow chart showing the cleaning fluid health status monitoring results obtained in an embodiment of the present application;

[0053] Figure 4 This is a flow chart of obtaining the pipe valve image analysis results in the embodiment of the present application;

[0054] Figure 5 This is a flow chart of visual intelligent fluid monitoring in an embodiment of the present application;

[0055] Figure 6 This is a structural diagram of a visual intelligent fluid monitoring device in an embodiment of the present application;

[0056] Figure 7 This is a structural diagram of a strip steel monitoring unit in an embodiment of the present application;

[0057] Figure 8 This is a structural diagram of a washing liquid monitoring unit in an embodiment of the present application;

[0058] Fig. 9 This is a structural diagram of a pipe valve monitoring unit in an embodiment of the present application;

[0059] Fig.10This is a structural diagram of the intelligent fluid monitoring unit in an embodiment of the present application;

[0060] Fig.11 A schematic diagram of the structure of an electronic device in an embodiment of the present application;

[0061] Fig.12 This is a structural diagram of a visual intelligent fluid monitoring system in an embodiment of the present application;

[0062] Fig.13 This is a structural diagram of the unit drive event processing in the embodiment of the present application;

[0063] Fig.14 This is one of the structural diagrams of human event processing in the embodiment of the present application;

[0064] Fig.15 This is the second structural diagram of the human event processing in the embodiment of the present application;

[0065] Fig.16 This is a schematic diagram of the structure of the dynamic screen change event in the embodiment of the present application;

[0066] Fig.17 This is a schematic diagram of the position of the steel strip monitoring camera in the embodiment of the present application;

[0067] Fig.18 This is a schematic diagram of the lens position in the healthy state of the cleaning fluid in an embodiment of the present application. DETAILED DESCRIPTION

[0068] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0069] The information collected in the technical solution of this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0070] Provide users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0071] In one embodiment, see Figure 1In order to be able to check the quality of strip steel, cleaning effect, and pipe valve parameters through industrial cameras, reduce the amount of electrical signal transmission in the system, make the system simpler, and make the monitoring content richer, the present application provides a visual intelligent fluid monitoring method, including:

[0072] S101: inputting the acquired strip steel quality image into a pre-built strip steel defect recognition model to obtain a strip steel quality monitoring result;

[0073] S102: inputting the acquired cleaning fluid status image into a pre-built cleaning fluid color difference recognition model to obtain a cleaning fluid health status monitoring result;

[0074] S103: performing image analysis on the acquired pipe valve event-driven image to obtain a pipe valve image analysis result;

[0075] S104: Perform visual intelligent fluid monitoring according to the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

[0076] It is understandable that for newly built production lines, the method provided by this application can be used to eliminate traditional fluid monitoring sensors and reduce the number of cables to facilitate system maintenance. For old production lines, the method provided by this application can be used to achieve intelligent upgrades of the factory by adding smart cameras and this monitoring system without making a large number of changes to the original factory equipment.

[0077] See also Fig.12 The embodiment of the present application provides a solution for monitoring the strip cleaning fluid system in the galvanizing, annealing and degreasing units. The monitoring scenarios may include: the quality of the strip after cleaning, the health status of the cleaning fluid, the status of the pipeline and valve instruments, etc.

[0078] First, the principle of strip quality monitoring is: through industrial cameras and lenses, images are provided to the visual system inside the monitoring system (which can be the execution subject of this application), and the defect type is fed back to the monitoring interface by comparing it with the defective product database inside the monitoring system. Among them, artificial intelligence models can be introduced into the comparison process.

[0079] Second, the implementation principle of the cleaning fluid health status monitoring is: because the color of healthy cleaning fluid is bright and clear, while the color of unhealthy cleaning fluid is dark. Therefore, the cleaning fluid is photographed through industrial cameras and lenses, and the health status of the cleaning fluid can be judged by the color, and the status can be fed back to the monitoring interface. Among them, the judgment process can introduce an artificial intelligence model.

[0080] For example, after an industrial camera and lens collect an image, it first passes through an AI recognition model to extract the target object, and then performs color correction and grayscale processing to reduce the sampled data. Then, the AI ​​recognition model outputs the recognition result. Finally, the processed data is displayed on the monitoring interface for monitoring, alarming, and automated chain control.

[0081] Third, the implementation principle of pipeline and instrument monitoring is: through industrial cameras and lenses, images are provided to the visual system inside the monitoring system. The captured microscopic images include: valve images, instrument panel images and panoramic pipeline images. Among them, the microscopic images of valves and instrument panels can be used to monitor the opening and closing status of valves and the readings or status of instruments. The monitoring results are displayed on the monitoring interface for production operations. The panoramic pipeline image can be used to monitor pipeline vibration and leakage. The monitoring results can be fed back to the monitoring interface.

[0082] Furthermore, the embodiment of the present application uses three levels of hardware processing devices at the hardware layer, namely, smart lens, local server and cloud server. Different types of data can be pre-processed at different locations to reduce the amount of data transmission and the amount of calculation. At the same time, at the software layer, different levels of processing solutions can be proposed according to different event types.

[0083] From the above description, it can be seen that the visual intelligent fluid monitoring method provided by the present application can collect monitoring images through industrial cameras and lenses, and use the artificial intelligence recognition system to extract the target object, and then perform color difference correction and grayscale processing to reduce the sampling data, and then analyze the data, and display the analyzed data on the monitoring interface for monitoring, alarm and automatic chain control. Among them, industrial cameras and lenses are set at the outlet of the cleaning system for strip quality monitoring; industrial cameras and lenses are set at the system sampling port for monitoring the health status of the cleaning fluid; and several industrial cameras and lenses are installed in the system area to view and transmit the status of valves, instruments and pipelines.

[0084] In one embodiment, see Figure 2 The step of inputting the acquired strip quality image into a pre-trained strip defect recognition model to obtain a strip quality monitoring result includes:

[0085] S201: Acquire the strip quality image by using an image acquisition device disposed behind the cleaning fluid system dryer;

[0086] S202: extracting defect features from the strip quality image, and inputting the extracted defect features into the strip defect recognition model to obtain the strip quality monitoring result; wherein the strip defect recognition model is constructed based on a strip product defect data set.

[0087] Understandably, see Fig.17 , the industrial camera and lens are installed after the cleaning fluid system dryer, which can be used to monitor the quality of the strip. In order to avoid the influence of environmental water vapor on the lens, a purge device can be set at the lens.

[0088] By using some existing image feature extraction methods, defect features can be extracted from these strip quality images. Next, the extracted defect features are input into the strip defect recognition model to obtain the strip quality monitoring results. It should be noted that the strip defect recognition model can be a pre-trained artificial intelligence model. The data used for model training can be a strip product defect data set. This data set usually records various defects of strip products. Therefore, the trained strip defect recognition model can identify various defects that may exist in the current strip quality image. Of course, in some cases, the strip may also have no defects. The above process can be seen in Fig.12 shown.

[0089] From the above description, it can be seen that the visual intelligent fluid monitoring method provided in the present application can input the acquired strip quality image into a pre-trained strip defect recognition model to obtain the strip quality monitoring result.

[0090] In one embodiment, see Figure 3 The step of inputting the acquired cleaning fluid status image into a pre-trained cleaning fluid color difference recognition model to obtain a cleaning fluid health status monitoring result includes:

[0091] S301: Acquire the cleaning liquid state image using an image acquisition device disposed at a sampling port of the magnetic filtration device;

[0092] S302: Extract color difference features from the cleaning fluid status image, and input the extracted color difference features into the cleaning fluid color difference recognition model to obtain the cleaning fluid health status monitoring result; wherein the cleaning fluid color difference recognition model is constructed based on the cleaning fluid color difference data set.

[0093] Understandably, see Fig.18 , install the industrial camera and lens in the sampling port area of ​​the magnetic filtration device, and judge the health status of the cleaning fluid according to the color of the outflowing liquid, and feedback it to the monitoring interface. The industrial camera and lens after the dryer can be used to check the cleaning effect of the strip steel, and make a comprehensive judgment based on the health status of the cleaning fluid, so as to delay the replacement of the cleaning fluid and reduce the consumption of the cleaning fluid.

[0094] By utilizing some existing image feature extraction methods, color difference features can be extracted from these cleaning fluid status images. Next, the extracted color difference features are input into the cleaning fluid color difference recognition model to obtain the cleaning fluid health status monitoring results. It should be noted that the cleaning fluid color difference recognition model can be a pre-trained artificial intelligence model. The data used for model training can be a cleaning fluid color difference data set. This data set usually records the corresponding colors of the cleaning fluid in different health states. Therefore, the trained cleaning fluid color difference recognition model can identify the color differences that may exist in the current cleaning fluid status image. Of course, in some cases, the color of the cleaning fluid to be monitored may have basically no color difference compared to the color of the cleaning fluid in a healthy state. The above process can be found in Fig.12 shown.

[0095] From the above description, it can be seen that the visual intelligent fluid monitoring method provided in the present application can input the acquired cleaning fluid status image into a pre-trained cleaning fluid color difference recognition model to obtain the cleaning fluid health status monitoring result.

[0096] In one embodiment, see Figure 4 The step of performing image analysis on the acquired pipe valve event driven image to obtain the pipe valve image analysis result includes:

[0097] S401: Acquire the pipe valve event driven image by using an image acquisition device disposed in the pipe valve area;

[0098] S402: If the pipe valve event driving image is a unit driving event, predict the change parameter according to the unit driving instruction, and compare the actual parameter obtained by analyzing the pipe valve event driving image with the change parameter to obtain the pipe valve image analysis result;

[0099] S403: If the pipe valve event driving image is a human operation event, compare the actual parameters obtained by analyzing the pipe valve event driving image with the preset parameters to obtain the pipe valve image analysis result;

[0100] S404: If the pipe valve event-driven image is a dynamic picture change event, the pipe valve event-driven image is analyzed using a gray level co-occurrence matrix to determine whether the pipe valve vibrates or leaks, thereby obtaining the pipe valve image analysis result.

[0101] It is understandable that the image acquisition device disposed in the pipe valve area is first used to obtain the pipe valve event driving image. Among them, the embodiment of the present application divides the events into "unit driving events", "human events" and "image dynamic change events".

[0102] ① "Unit drive events" are events caused by changes in unit process, including unit start and stop, unit speed changes, product specification changes, system set temperature, flow, pressure and other events. The above events can generally be understood as normal operating instructions. At this time, the unit issues a process setting command, and the production line equipment receives the command and acts. At the same time, the local server can estimate the equipment that may be affected. After issuing a command to the smart lens, the relevant industrial camera and lens will transmit the collected images to the local server, process them on the local server, and compare them with the system prediction values ​​for monitoring. For the specific process, please refer to Fig.13 shown.

[0103] ② “Human events” are system status change events caused by human factors (including but not limited to misoperation). Fig.14 As shown, the embodiment of the present application divides the intelligent lens group into a "starting lens group" and a "normal lens group". The starting lens group is set outside the system area and is always kept in an activated state. When someone enters the system area, the starting lens starts tracking, and predicts and starts the relevant normal lens to transmit images based on the route. Through the person tracking system, the parameters of the relevant area can be transmitted to analyze whether there are man-made production accidents or personal injury accidents. The above tracking process can be implemented using existing dynamic tracking technology. For the specific process, see Fig.15 shown.

[0104] ③ "Dynamic image change events" are abnormal events such as vibration and leakage in the system area pipeline caused by unknown reasons. Usually, the smart lens analyzes and processes the image at the local end of the lens. When the extracted features are abnormal, the communication module is started to transmit the relevant information to the local server, which analyzes and alarms and stores it in the accident system. At the lens, the gray level co-occurrence matrix (GLCM) is used to analyze pipeline vibration and leakage. For the specific process, see Fig.16 shown.

[0105] It can be seen from the above description that the visual intelligent fluid monitoring method provided by the present application can perform image analysis on the acquired pipe valve event-driven image to obtain the pipe valve image analysis result.

[0106] In one embodiment, see Figure 5 , the visual intelligent fluid monitoring is performed according to the strip quality monitoring result, the cleaning fluid health status monitoring result and the pipe valve image analysis result, including:

[0107] S501: Feedback the strip quality monitoring result, the cleaning fluid health status monitoring result and the pipe valve image analysis result to the monitoring interface;

[0108] S502: According to the flow value, temperature value and pressure value in the actual parameters, the liquid replenishing valve, the temperature control valve and the pressure valve are controlled respectively.

[0109] It can be understood that the embodiment of the present application can display the quality of the strip after cleaning, the health status of the cleaning liquid, the status of pipelines and instruments, etc. on the interface.

[0110] Furthermore, several industrial cameras and lenses can be installed in the system area to monitor valves, instruments and pipelines. In order to ensure that the lens can capture the valve status, a status indicator can be set on the top of the valve. When the valve is open, the indicator is yellow, and when the valve is closed, it is red. The instrument may include pointer instruments, digital instruments and status lights. Relevant monitoring information can be transmitted to the artificial intelligence recognition system through the lens, and after processing, it can be used for control, which may include:

[0111] The valve opening and closing information obtained by monitoring is displayed on the monitoring screen and can be interlocked with the pump to protect the pump.

[0112] The flow value obtained by monitoring is displayed on the monitoring screen and is automatically controlled by interlocking with the liquid replenishing valve.

[0113] The temperature value obtained by monitoring is displayed on the monitoring screen and is automatically controlled by the temperature control valve.

[0114] The pressure value obtained by monitoring is displayed on the monitoring screen and is interlocked with the pressure valve for automatic control or with the pump to protect the pump.

[0115] The flow value obtained by monitoring is displayed on the monitoring screen, and the accumulation and energy consumption statistics are performed.

[0116] The monitoring device can detect pipeline leakage. If leakage occurs, it can be displayed on the monitoring interface.

[0117] From the above description, it can be seen that the visual intelligent fluid monitoring method provided in the present application can perform visual intelligent fluid monitoring based on the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

[0118] In summary, the method provided by this application has the following advantages:

[0119] 1. As a monitoring system, it includes monitoring scenarios such as: strip quality after cleaning, cleaning fluid health status, pipeline and instrument status, etc. After collecting images through industrial cameras and lenses, the target object can be extracted through the artificial intelligence recognition system, and then color correction and grayscale processing are performed to reduce the sampling data. Then, the processed data is displayed on the monitoring interface for monitoring, alarm and automatic chain control.

[0120] 2. Install industrial cameras and lenses at the exit of the cleaning system to monitor the quality of the strip.

[0121] 3. Install industrial cameras and lenses at the system sampling port to monitor the health status of the cleaning fluid.

[0122] 4. Set up several industrial cameras and lenses in the system area to view and transmit the status of valves, instruments and pipelines. The parameters of related equipment are collected and used for system control and fault alarm.

[0123] Based on the same inventive concept, the embodiments of the present application also provide a visual intelligent fluid monitoring device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving the problem by the visual intelligent fluid monitoring device is similar to that of the visual intelligent fluid monitoring method, the implementation of the visual intelligent fluid monitoring device can refer to the implementation of the method based on the software performance benchmark determination, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0124] In one embodiment, see Figure 6 In order to be able to check the strip quality, cleaning effect, and pipe valve parameters through industrial cameras, reduce the system's electrical signal transmission volume, make the system simpler, and make the monitoring content richer, the present application provides a visual intelligent fluid monitoring device, including: a strip monitoring unit 601, a washing liquid monitoring unit 602, a pipe valve monitoring unit 603, and an intelligent fluid monitoring unit 604.

[0125] The strip steel monitoring unit 601 is used to input the acquired strip steel quality image into a pre-built strip steel defect recognition model to obtain a strip steel quality monitoring result;

[0126] The cleaning liquid monitoring unit 602 is used to input the acquired cleaning liquid state image into a pre-built cleaning liquid color difference recognition model to obtain a cleaning liquid health state monitoring result;

[0127] The pipe valve monitoring unit 603 is used to perform image analysis on the acquired pipe valve event driven image to obtain the pipe valve image analysis result;

[0128] The intelligent fluid monitoring unit 604 is used to perform visual intelligent fluid monitoring based on the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

[0129] In one embodiment, see Figure 7 The strip steel monitoring unit 601 includes: a strip steel image acquisition device 701 and a strip steel monitoring device 702.

[0130] The strip steel image acquisition device 701 is used to acquire the strip steel quality image by using an image acquisition device arranged after the drying machine of the cleaning fluid system;

[0131] The strip monitoring device 702 is used to extract defect features from the strip quality image, and input the extracted defect features into the strip defect recognition model to obtain the strip quality monitoring results; wherein the strip defect recognition model is constructed based on a strip product defect data set.

[0132] In one embodiment, see Figure 8 The washing liquid monitoring unit 602 includes: a washing liquid image acquisition device 801 and a washing liquid monitoring device 802.

[0133] The washing liquid image acquisition device 801 is used to acquire the washing liquid state image by using an image acquisition device arranged at the sampling port of the magnetic filtration device;

[0134] The cleaning liquid monitoring device 802 is used to extract color difference features from the cleaning liquid status image, and input the extracted color difference features into the cleaning liquid color difference recognition model to obtain the cleaning liquid health status monitoring result; wherein, the cleaning liquid color difference recognition model is constructed based on the cleaning liquid color difference data set.

[0135] In one embodiment, see Fig. 9 The pipe valve monitoring unit 603 includes: a drive image acquisition device 901, a unit drive monitoring device 902, a manual operation monitoring device 903 and a dynamic change monitoring device 904.

[0136] The driving image acquisition device 901 is used to acquire the pipe valve event driving image by using an image acquisition device arranged in the pipe valve area;

[0137] The unit drive monitoring device 902 is used for predicting the change parameter according to the unit drive instruction if the pipe valve event drive image is a unit drive event, and comparing the actual parameter obtained by analyzing the pipe valve event drive image with the change parameter to obtain the pipe valve image analysis result;

[0138] The human operation monitoring device 903 is used for comparing the actual parameters obtained by analyzing the pipe valve event driving image with the preset parameters to obtain the pipe valve image analysis result if the pipe valve event driving image is a human operation event;

[0139] The dynamic change monitoring device 904 is used to analyze the pipe valve event-driven image using a grayscale co-occurrence matrix if the pipe valve event-driven image is a dynamic picture change event, determine whether the pipe valve vibrates or leaks, and obtain the pipe valve image analysis result.

[0140] In one embodiment, see Fig.10The intelligent fluid monitoring unit 604 includes: a monitoring result feedback device 1001 and a pipe valve control device 1002.

[0141] The monitoring result feedback device 1001 is used to feed back the strip quality monitoring result, the cleaning liquid health status monitoring result and the pipe valve image analysis result to the monitoring interface;

[0142] The pipe valve control device 1002 is used to control the liquid replenishing valve, the temperature control valve and the pressure valve respectively according to the flow value, temperature value and pressure value in the actual parameters.

[0143] From the hardware level, in order to be able to check the quality of the strip steel, the cleaning effect, and the pipe valve parameters through the industrial camera, reduce the amount of electrical signal transmission of the system, make the system more concise, and make the monitoring content richer, the present application provides an embodiment of an electronic device for implementing all or part of the contents of the visual intelligent fluid monitoring method, and the electronic device specifically includes the following contents:

[0144] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the visual intelligent fluid monitoring device and related devices such as the core business system, user terminal and related database; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented with reference to the embodiment of the visual intelligent fluid monitoring method and the embodiment of the visual intelligent fluid monitoring device in the embodiment, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0145] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0146] In practical applications, part of the visual intelligent fluid monitoring method can be executed on the electronic device side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0147] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0148] Fig.11 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig.11 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.11 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0149] In one embodiment, the visual intelligent fluid monitoring method function can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0150] S101: inputting the acquired strip steel quality image into a pre-built strip steel defect recognition model to obtain a strip steel quality monitoring result;

[0151] S102: inputting the acquired cleaning fluid status image into a pre-built cleaning fluid color difference recognition model to obtain a cleaning fluid health status monitoring result;

[0152] S103: performing image analysis on the acquired pipe valve event-driven image to obtain a pipe valve image analysis result;

[0153] S104: Perform visual intelligent fluid monitoring according to the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

[0154] From the above description, it can be seen that the visual intelligent fluid monitoring method provided by the present application can collect monitoring images through industrial cameras and lenses, and use the artificial intelligence recognition system to extract the target object, and then perform color difference correction and grayscale processing to reduce the sampling data, and then analyze the data, and display the analyzed data on the monitoring interface for monitoring, alarm and automatic chain control. Among them, industrial cameras and lenses are set at the outlet of the cleaning system for strip quality monitoring; industrial cameras and lenses are set at the system sampling port for monitoring the health status of the cleaning fluid; and several industrial cameras and lenses are installed in the system area to view and transmit the status of valves, instruments and pipelines.

[0155] In another embodiment, the visual intelligent fluid monitoring device can be configured separately from the central processing unit 9100. For example, the data composite transmission device visual intelligent fluid monitoring device can be configured as a chip connected to the central processing unit 9100, and the functions of the visual intelligent fluid monitoring method can be realized through the control of the central processing unit.

[0156] like Fig.11 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.11 In addition, the electronic device 9600 may also include Fig.11 For components not shown, reference may be made to the prior art.

[0157] like Fig.11 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0158] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0159] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0160] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0161] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0162] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0163] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0164] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the visual intelligent fluid monitoring method in the above embodiments, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, all the steps of the visual intelligent fluid monitoring method in the above embodiments are implemented, where the execution subject is a server or a client. For example, when the processor executes the computer program, the following steps are implemented:

[0165] S101: inputting the acquired strip steel quality image into a pre-built strip steel defect recognition model to obtain a strip steel quality monitoring result;

[0166] S102: inputting the acquired cleaning fluid status image into a pre-built cleaning fluid color difference recognition model to obtain a cleaning fluid health status monitoring result;

[0167] S103: performing image analysis on the acquired pipe valve event-driven image to obtain a pipe valve image analysis result;

[0168] S104: Perform visual intelligent fluid monitoring according to the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

[0169] From the above description, it can be seen that the visual intelligent fluid monitoring method provided by the present application can collect monitoring images through industrial cameras and lenses, and use the artificial intelligence recognition system to extract the target object, and then perform color difference correction and grayscale processing to reduce the sampling data, and then analyze the data, and display the analyzed data on the monitoring interface for monitoring, alarm and automatic chain control. Among them, industrial cameras and lenses are set at the outlet of the cleaning system for strip quality monitoring; industrial cameras and lenses are set at the system sampling port for monitoring the health status of the cleaning fluid; and several industrial cameras and lenses are installed in the system area to view and transmit the status of valves, instruments and pipelines.

[0170] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0171] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0172] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0173] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0174] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A visual intelligent fluid monitoring method, characterized in that: include: The acquired strip quality image is input into a pre-built strip defect recognition model to obtain the strip quality monitoring result; Input the acquired cleaning fluid status image into a pre-built cleaning fluid color difference recognition model to obtain the cleaning fluid health status monitoring result; Performing image analysis on the acquired pipe valve event-driven image to obtain a pipe valve image analysis result; Visual intelligent fluid monitoring is performed based on the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

2. The visual intelligent fluid monitoring method according to claim 1, characterized in that: The step of inputting the acquired strip steel quality image into a pre-trained strip steel defect recognition model to obtain a strip steel quality monitoring result includes: Acquiring the strip steel quality image by using an image acquisition device disposed at a drying machine of a cleaning fluid system; Defect features are extracted from the strip quality image, and the extracted defect features are input into the strip defect recognition model to obtain the strip quality monitoring result; wherein the strip defect recognition model is constructed based on a strip product defect data set.

3. The visual intelligent fluid monitoring method according to claim 1, characterized in that: The step of inputting the acquired cleaning fluid status image into a pre-trained cleaning fluid color difference recognition model to obtain a cleaning fluid health status monitoring result includes: Using an image acquisition device disposed at a sampling port of the magnetic filtration device to acquire the cleaning fluid state image; The color difference features of the cleaning fluid status image are extracted, and the extracted color difference features are input into the cleaning fluid color difference recognition model to obtain the cleaning fluid health status monitoring result; wherein, the cleaning fluid color difference recognition model is constructed based on the cleaning fluid color difference data set.

4. The visual intelligent fluid monitoring method according to claim 1, characterized in that: The step of performing image analysis on the acquired pipe valve event driven image to obtain the pipe valve image analysis result includes: Acquiring the pipe valve event driven image by using an image acquisition device disposed in the pipe valve area; If the pipe valve event driving image is a unit driving event, predict the change parameter according to the unit driving instruction, and compare the actual parameter obtained by analyzing the pipe valve event driving image with the change parameter to obtain the pipe valve image analysis result; If the pipe valve event driving image is a human operation event, the actual parameters obtained by analyzing the pipe valve event driving image are compared with the preset parameters to obtain the pipe valve image analysis result; If the pipe valve event-driven image is a dynamic picture change event, the pipe valve event-driven image is analyzed using a gray level co-occurrence matrix to determine whether the pipe valve vibrates or leaks, thereby obtaining the pipe valve image analysis result.

5. The visual intelligent fluid monitoring method according to claim 4, characterized in that: The visual intelligent fluid monitoring is performed according to the strip quality monitoring result, the cleaning fluid health status monitoring result and the pipe valve image analysis result, including: Feedback the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results to the monitoring interface; According to the flow value, temperature value and pressure value in the actual parameters, the liquid replenishing valve, the temperature control valve and the pressure valve are controlled respectively.

6. A visual intelligent fluid monitoring device, characterized in that: include: The strip steel monitoring unit is used to input the acquired strip steel quality image into a pre-built strip steel defect recognition model to obtain the strip steel quality monitoring result; A washing liquid monitoring unit, used to input the acquired washing liquid status image into a pre-built washing liquid color difference recognition model to obtain a washing liquid health status monitoring result; A pipe valve monitoring unit, used for performing image analysis on the acquired pipe valve event driven image to obtain a pipe valve image analysis result; The intelligent fluid monitoring unit is used to perform visual intelligent fluid monitoring based on the strip quality monitoring results, the cleaning fluid health status monitoring results and the pipe valve image analysis results.

7. The visual intelligent fluid monitoring device according to claim 6, characterized in that: The strip steel monitoring unit comprises: A strip steel image acquisition device, used to acquire the strip steel quality image by using an image acquisition device arranged at the dryer of the cleaning fluid system; The strip steel monitoring device is used to extract defect features from the strip steel quality image and input the extracted defect features into the strip steel defect recognition model to obtain the strip steel quality monitoring result; wherein the strip steel defect recognition model is constructed based on a strip steel product defect data set.

8. The visual intelligent fluid monitoring device according to claim 6, characterized in that: The washing liquid monitoring unit comprises: A washing liquid image acquisition device, used to acquire the washing liquid state image by using an image acquisition device arranged at the sampling port of the magnetic filtration device; The cleaning liquid monitoring device is used to extract color difference features from the cleaning liquid status image, and input the extracted color difference features into the cleaning liquid color difference recognition model to obtain the cleaning liquid health status monitoring result; wherein the cleaning liquid color difference recognition model is constructed based on the cleaning liquid color difference data set.

9. The visual intelligent fluid monitoring device according to claim 6, characterized in that: The pipe valve monitoring unit comprises: A driving image acquisition device, used for acquiring the pipe valve event driving image by using an image acquisition device arranged in the pipe valve area; A unit drive monitoring device, for predicting a change parameter according to a unit drive instruction if the pipe valve event drive image is a unit drive event, and comparing an actual parameter obtained by analyzing the pipe valve event drive image with the change parameter to obtain an analysis result of the pipe valve image; A human operation monitoring device, used for comparing actual parameters obtained by analyzing the pipe valve event driving image with preset parameters to obtain the pipe valve image analysis result if the pipe valve event driving image is a human operation event; The dynamic change monitoring device is used to analyze the pipe valve event-driven image using a grayscale co-occurrence matrix if the pipe valve event-driven image is a dynamic picture change event, determine whether the pipe valve vibrates or leaks, and obtain the pipe valve image analysis result.

10. The visual intelligent fluid monitoring device according to claim 9, characterized in that: The intelligent fluid monitoring unit comprises: A monitoring result feedback device, used for feeding back the strip quality monitoring result, the cleaning liquid health status monitoring result and the pipe valve image analysis result to the monitoring interface; The pipe valve control device is used to control the liquid replenishing valve, the temperature control valve and the pressure valve respectively according to the flow value, temperature value and pressure value in the actual parameters.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the visual intelligent fluid monitoring method according to any one of claims 1 to 5 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the visual intelligent fluid monitoring method according to any one of claims 1 to 5 are implemented.

13. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the visual intelligent fluid monitoring method according to any one of claims 1 to 5 are implemented.

Images