Method and device for automatically selecting multiple working condition models based on video signals

Abstract

The present invention provides a method and device for automatically selecting multiple operating condition models based on video signals. The method involves acquiring a captured video signal to be analyzed in real time while executing a business process involving multiple operating conditions. The method then analyzes the video signal based on a pre-established visual model to obtain an operating condition model corresponding to the operating condition of the video signal to be analyzed. The operating condition model is then used to perform predictions to obtain predicted operating condition parameters. In this solution, after pre-establishing a visual model, the visual model is used to analyze the video signal to be analyzed. After determining the operating condition model corresponding to the operating condition of the video signal to be analyzed, the determined operating condition model is used to predict the operating condition parameters, thereby improving the generalizability and reliability of each operating condition model.

Description

Technical Field

[0001] The present invention relates to the technical field of signal processing, and in particular to a method and device for automatically selecting multiple working condition models based on video signals. Background Art

[0002] Multi-operating condition scenarios are common in various industries. During the simulation modeling process, most views integrate multiple operating condition changes into one model to reduce the complexity of the model.

[0003] In the existing technology, multiple models are usually integrated under the characteristics of multiple working conditions, multiple environments, and multiple stages to obtain a single model. However, for scenarios with large differences in working conditions and stages, it is difficult to guarantee reliability and accuracy by using only a single model for prediction, and it cannot be widely used. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a method and apparatus for automatically selecting multiple operating condition models based on video signals, so as to achieve the purpose of improving the scalability and reliability of each operating condition model.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A first aspect of an embodiment of the present invention discloses a method for automatically selecting a multi-operating condition model based on a video signal, the method comprising:

[0007] Acquire the captured video signals to be analyzed in real time during the execution of business operations involving various working conditions;

[0008] Analyzing the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed;

[0009] The operating condition model is called to perform prediction to obtain predicted operating condition parameters.

[0010] Preferably, the analyzing the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed includes:

[0011] Performing image processing on the video signal to be analyzed based on a pre-established visual model to obtain a color image;

[0012] Calculating the total pixel area of ​​the color image;

[0013] The total pixel area is used to determine a working condition model of the working condition corresponding to the video signal to be analyzed; there is a preset corresponding relationship between the total pixel area and the working condition model.

[0014] Preferably, the calling of the operating condition model for prediction to obtain predicted operating condition parameters includes:

[0015] The operating condition model is called, and prediction is performed using the total pixel area to obtain predicted operating condition parameters.

[0016] Preferably, the process of pre-establishing a visual model includes:

[0017] adding marks to monitoring areas in the video signals of the different working conditions, and acquiring color images of the monitoring areas;

[0018] Calculating the brightness of the three components in the color image, taking the maximum value of the brightness of the three components as the grayscale value of the grayscale image, and obtaining a grayscale image represented by pixels;

[0019] Performing mean filtering on the grayscale image using Kernel data to obtain a filtered grayscale image;

[0020] Based on a preset threshold, performing image binarization processing on the filtered grayscale image to obtain grayscale values ​​of pixels in the filtered grayscale image;

[0021] Calculating the total pixel area of ​​all the grayscale values, and dividing the total pixel area to obtain pixel area ranges corresponding to the different types of working conditions;

[0022] Determining the operating condition models corresponding to the different types of operating conditions based on the pixel area ranges corresponding to the different types of operating conditions;

[0023] A visual model is established based on the scheduling logic between the working condition models.

[0024] Preferably, if the operating conditions include a no-load operating condition, a continuously changing operating condition, and a full-load operating condition, the analyzing the video signal to be analyzed based on a pre-established visual model to obtain an operating condition model corresponding to the operating condition of the video signal to be analyzed includes:

[0025] Performing image processing on the video signal to be analyzed based on a pre-established visual model to obtain a color image;

[0026] Calculating the total pixel area of ​​the color image;

[0027] If the total pixel area is smaller than R1, determining that the working condition model corresponding to the working condition of the video signal to be analyzed is the no-load working condition model;

[0028] If the total pixel area is greater than R1 and less than R2, determining that the working condition model corresponding to the working condition of the video signal to be analyzed is the continuously changing working condition model;

[0029] If the total pixel area is greater than R2, it is determined that the working condition model corresponding to the working condition of the video signal to be analyzed is the full-load working condition model; R1 and R2 are positive integers, and R1 is less than R2.

[0030] Preferably, it is characterized in that if the currently executed business including multiple working conditions is a rubber discharge amount monitoring business, the working conditions include no-load working conditions, continuously changing working conditions and fully loaded working conditions, the calling of the working condition model for prediction to obtain the predicted working condition parameters includes:

[0031] If the working condition model corresponding to the working condition of the video signal to be analyzed is the no-load working condition model, calling the scheduling logic corresponding to the no-load working condition model, and using the total pixel area corresponding to the no-load working condition to predict the feeding amount of the rubber feeding conveyor belt, to obtain the predicted feeding amount A;

[0032] If the working condition model corresponding to the working condition of the video signal to be analyzed is the continuously changing working condition model, calling the scheduling logic corresponding to the continuously changing working condition model, and using the total pixel area corresponding to the continuously changing working condition to predict the feeding amount of the rubber feeding conveyor belt, to obtain the predicted feeding amount B;

[0033] If the working condition model corresponding to the working condition of the video signal to be analyzed is the full-load working condition model, the scheduling logic corresponding to the full-load working condition model is called, and the feeding amount of the rubber feeding conveyor belt is predicted using the total pixel area corresponding to the full-load working condition and the working state parameters of the downstream extruder to obtain the predicted feeding amount C; A, B and C are positive integers.

[0034] A second aspect of an embodiment of the present invention discloses a device for automatically selecting multiple working condition models based on video signals, the device comprising:

[0035] An acquisition module is used to acquire the captured video signals to be analyzed in real time during the execution of a business process involving multiple working conditions;

[0036] An analysis module, configured to analyze the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed;

[0037] The prediction module is used to call the operating condition model to perform prediction and obtain predicted operating condition parameters.

[0038] Preferably, the analysis module is specifically used for:

[0039] The video signal to be analyzed is subjected to image processing based on a pre-established visual model to obtain a color image; the total pixel area of ​​the color image is calculated; the working condition model of the working condition corresponding to the video signal to be analyzed is determined using the total pixel area; and a preset corresponding relationship exists between the total pixel area and the working condition model.

[0040] Preferably, the prediction module is specifically used for:

[0041] The operating condition model is called, and prediction is performed using the total pixel area to obtain predicted operating condition parameters.

[0042] Preferably, it further comprises: a building module;

[0043] The building module includes: an acquisition unit, a grayscale unit, a mean filtering unit, an image binarization processing unit, a division unit, a determination unit and a creation unit;

[0044] The acquisition unit is configured to add a mark to the monitoring area in the video signal of the different working conditions and acquire a color image in the monitoring area;

[0045] The grayscale unit is used to calculate the brightness of the three components in the color image, and use the maximum value of the brightness of the three components as the grayscale value of the grayscale image to obtain a grayscale image represented by pixels;

[0046] The mean filtering unit is used to perform mean filtering on the grayscale image using Kernel data to obtain a filtered grayscale image;

[0047] The image binarization processing unit is used to perform image binarization processing on the filtered grayscale image based on a preset threshold value to obtain the grayscale values ​​of the pixels of the filtered grayscale image;

[0048] The division unit is used to calculate the total pixel area of ​​all the grayscale values ​​and divide the total pixel area to obtain the pixel area ranges corresponding to the different types of working conditions;

[0049] The determining unit is configured to determine the operating condition models corresponding to the different types of operating conditions based on the pixel area ranges corresponding to the different types of operating conditions;

[0050] The establishing unit is used to establish a visual model based on the scheduling logic between the working condition models.

[0051] Based on the above-mentioned embodiment of the present invention, a method and device for automatically selecting multiple working condition models based on video signals are provided. The method includes: acquiring a captured video signal to be analyzed in real time during the execution of a business process involving multiple working conditions; analyzing the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed; and calling the working condition model to perform prediction to obtain predicted working condition parameters. In this solution, after pre-establishing a visual model, the visual model is used to analyze the video signal to be analyzed. After determining the working condition model corresponding to the working condition of the video signal to be analyzed, the determined working condition model is called to predict the working condition parameters, thereby improving the generalizability and reliability of each working condition model. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0053] Figure 1 A flowchart of a method for automatically selecting a multi-operating-condition model based on a video signal provided by an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of a process for analyzing a video signal to be analyzed provided by an embodiment of the present invention;

[0055] Figure 3 An interactive schematic diagram of automatic selection of multiple working condition models based on video signals provided by an embodiment of the present invention;

[0056] Figure 4 A schematic diagram of a process for pre-establishing a visual model according to an embodiment of the present invention;

[0057] Figure 5 A schematic diagram of a calculation formula for Kernel data provided by an embodiment of the present invention;

[0058] Figure 6 A schematic diagram of a flow chart for determining a working condition model corresponding to a working condition of a video signal to be analyzed provided by an embodiment of the present invention;

[0059] Figure 7 A schematic diagram of a process for calling a working condition model for prediction in a rubber material discharge monitoring service provided by an embodiment of the present invention;

[0060] Figure 8 A schematic diagram of a rubber process flow provided by an embodiment of the present invention;

[0061] Figure 9 A characteristic schematic diagram of a neural network modeling under full load conditions provided by an embodiment of the present invention;

[0062] FIG10( a ) and FIG10 ( b ) are comparative diagrams of a rubber unloading conveyor belt provided by an embodiment of the present invention in an empty working condition and a fully loaded working condition;

[0063] FIG11( a ) and FIG11 ( b ) are schematic diagrams showing the effects of machine vision processing on a rubber unloading conveyor belt in an empty working condition and a fully loaded working condition, respectively, provided by an embodiment of the present invention;

[0064] Figure 12 A schematic structural diagram of a device for automatically selecting multiple working condition models based on video signals provided by an embodiment of the present invention;

[0065] Figure 13 A schematic structural diagram of another apparatus for automatically selecting multiple working condition models based on video signals provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0067] In this application, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0068] As can be seen from the background technology, in the existing technology, for scenarios with large differences in different working conditions and stages, only a single model is used for prediction, and its reliability and accuracy are difficult to guarantee. Moreover, it cannot be widely used.

[0069] Therefore, an embodiment of the present invention provides a method and device for automatically selecting multiple working condition models based on video signals. In this solution, after a visual model is established in advance, the visual model is used to analyze the video signal to be analyzed, and after determining the working condition model corresponding to the working condition of the video signal to be analyzed, the determined working condition model is called to predict the working condition parameters, thereby improving the scalability and reliability of each working condition model.

[0070] like Figure 1 FIG. 1 is a flow chart of a method for automatically selecting a multi-operating-condition model based on a video signal according to an embodiment of the present invention. The method mainly includes the following steps:

[0071] Step S101: in the process of executing a business involving multiple working conditions, a captured video signal to be analyzed is acquired in real time.

[0072] In the specific implementation of step S101, when performing business processing, the business may include multiple working conditions. In the process of executing the business including multiple working conditions, the image acquisition device is used to obtain the captured video signal to be analyzed in real time.

[0073] It should be noted that an industrial computer can be used to execute services involving various working conditions, and the industrial computer can be connected to an image acquisition device.

[0074] Preferably, the image acquisition device is connected to the industrial computer via the network, the corresponding driver is installed and debugged, and after successful debugging, the image acquisition device normally displays the monitoring screen (the captured video signal to be analyzed) and saves the monitoring screen in real time to the local industrial computer.

[0075] Optionally, the hardware configuration of the industrial computer is shown in Table 1.

[0076] Table 1:

[0077] CPU I5-7500 Memory 8G harddisk 1T Network card Dual network cards operating system Ubuntu 16.04

[0078] In the embodiment of the present invention, the image acquisition device includes but is not limited to a camera device.

[0079] It should be noted that the camera equipment includes but is not limited to equipment with shooting functions, such as a camera.

[0080] Optionally, in an embodiment of the present invention, the camera is a network camera, and the selected model is a Dahua security camera.

[0081] Step S102: Analyze the video signal to be analyzed based on the pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed.

[0082] In the specific implementation of step S102, a visual model is pre-established, and the video signal to be analyzed is input into the pre-established visual model for analysis to obtain a working condition model corresponding to the working condition of the video signal to be analyzed, and output the working condition model corresponding to the working condition of the video signal to be analyzed.

[0083] Optionally, step S102 is performed to analyze the video signal to be analyzed based on the pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed, such as Figure 2 FIG. 1 is a flow chart of analyzing a video signal to be analyzed according to an embodiment of the present invention, which mainly includes the following steps:

[0084] Step S201: performing image processing on the video signal to be analyzed based on a pre-established visual model to obtain a color image.

[0085] In the specific implementation of step S201 , a visual model is pre-established, and the video signal to be analyzed is input into the pre-established visual model for image processing to obtain a color image.

[0086] Step S202: Calculate the total pixel area of ​​the color image.

[0087] In the specific implementation of step S202 , the brightness of the three components in the color image is first calculated, and the maximum value of the brightness of the three components is used as the grayscale value of the grayscale image to obtain a grayscale image represented by pixels.

[0088] Next, the grayscale image is processed by mean filtering using the kernel data to obtain a filtered grayscale image.

[0089] Next, based on a preset threshold, the filtered grayscale image is subjected to image binarization processing to obtain the grayscale values ​​of the pixels of the filtered grayscale image.

[0090] Finally, the total pixel area of ​​all grayscale values ​​is calculated to obtain the total pixel area of ​​the color image.

[0091] Step S203: using the total pixel area to determine the working condition model corresponding to the working condition of the video signal to be analyzed.

[0092] In step S203 , there is a preset corresponding relationship between the total pixel area and the working condition model.

[0093] In the specific implementation of step S203 , the operating condition model of the operating condition corresponding to the video signal to be analyzed is determined according to a preset corresponding relationship between the total pixel area of ​​the color image and the operating condition model.

[0094] Step S103: calling the operating condition model to perform prediction and obtain predicted operating condition parameters.

[0095] In the specific implementation of step S103 , the working condition model of the working condition corresponding to the output video signal to be analyzed is called, and the working condition parameters of the working condition model of the working condition corresponding to the video signal to be analyzed are predicted to obtain the predicted working condition parameters.

[0096] Optionally, the process of executing step S103 to call the operating condition model for prediction and obtain predicted operating condition parameters includes:

[0097] The working condition model is called and the total pixel area is used for prediction to obtain the predicted working condition parameters.

[0098] In order to better understand the above description, Figure 3 FIG. 1 is a schematic diagram of an interaction for automatically selecting a multi-operating-condition model based on a video signal according to an embodiment of the present invention.

[0099] exist Figure 3 In the process of executing a business involving multiple working conditions, first, the captured video signal to be analyzed is acquired in real time. Then, the video signal to be analyzed is analyzed using a pre-established visual model to obtain a working condition model of the working condition corresponding to the video signal to be analyzed. Then, the working condition model is called to make a prediction, the predicted working condition parameters are obtained, and the predicted working condition parameters are output.

[0100] An embodiment of the present invention provides a method for automatically selecting multiple operating condition models based on video signals. While executing a business process involving multiple operating conditions, the method captures a captured video signal to be analyzed in real time. The method analyzes the video signal to be analyzed based on a pre-established visual model to obtain an operating condition model corresponding to the operating condition of the video signal to be analyzed. The operating condition model is then used to perform predictions to obtain predicted operating condition parameters. In this solution, after pre-establishing a visual model, the visual model is used to analyze the video signal to be analyzed. After determining the operating condition model corresponding to the operating condition of the video signal to be analyzed, the determined operating condition model is used to predict the operating condition parameters, thereby improving the generalizability and reliability of each operating condition model.

[0101] Based on the above-mentioned embodiment of the present invention, a method for automatically selecting multiple working condition models based on video signals is provided. Step S102 is executed to analyze the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed. Figure 4 FIG. 1 is a flow chart of pre-establishing a visual model according to an embodiment of the present invention, which mainly includes the following steps:

[0102] Step S401: adding marks to monitoring areas in video signals of different working conditions, and acquiring color images in the monitoring areas.

[0103] In step S401 , the monitoring area refers to a designated area in the video signal, which may refer to a carrier.

[0104] In the specific implementation of step S401 , video signals of different working conditions are obtained, and monitoring areas in the video signals of different working conditions are marked, thereby eliminating other environmental interference factors and obtaining a color image in the monitoring area.

[0105] Step S402: Calculate the brightness of the three components in the color image, use the maximum value of the brightness of the three components as the grayscale value of the grayscale image, and obtain a grayscale image represented by pixels.

[0106] In the embodiment of the present invention, the grayscale image is a grayscale image with pixel points of [0, 255], which is converted from the original image (color image).

[0107] In the specific implementation process of step S402, the three-component brightness in the color image is calculated, and the values ​​of all the three-component brightness are compared to obtain the maximum value of the three-component brightness. The maximum value of the three-component brightness is used as the grayscale value of the grayscale image, thereby enhancing the contrast between the target element and the surface of the carrier, and obtaining a grayscale image represented by pixel points.

[0108] Specifically, the calculation formula for the three-component brightness in a color image is as follows:

[0109] Gary(i,j)=max{R(i,j),G(i,j),B(i,j)}, (1),

[0110] Among them, Gary(i,j) represents the calculated grayscale value of the pixel; R(i,j) represents the red brightness value of the original pixel; G(i,j) represents the green brightness value of the original pixel; B(i,j) represents the blue brightness value of the original pixel.

[0111] Step S403: performing mean filtering on the grayscale image using the kernel data to obtain a filtered grayscale image.

[0112] In step S303, mean filtering is performed to eliminate image noise.

[0113] Kernel data is a 3*3 matrix, and its calculation formula is as follows Figure 5 , as shown in formula (2) and formula (3):

[0114]

[0115]

[0116] Among them, f(i,j) is the original image (color image); g(i,j) is the grayscale image after filtering;

[0117]

[0118] In the specific implementation of step S403 , each pixel of the grayscale image is calculated from left to right and from top to bottom using the kernel data, and a filtered grayscale image is obtained based on each pixel of all the grayscale images.

[0119] Step S404: performing image binarization processing on the filtered grayscale image based on a preset threshold value to obtain grayscale values ​​of pixels in the filtered grayscale image.

[0120] In the embodiment of the present invention, the threshold value may be represented by threshold, and the preset threshold value is threshold=160, but is not limited thereto.

[0121] In the specific implementation of step S404, a threshold is set, and the filtered grayscale image is binarized using the set threshold to further distinguish the target element from the surface of the carrier and other interferences. The pixel points of the target element in the grayscale image can be effectively screened out, and the grayscale value of the pixel points of the filtered grayscale image is obtained to be 255.

[0122] The calculation formula for binarizing the filtered grayscale image using the set threshold is as follows:

[0123]

[0124] Step S405: Calculate the total pixel area of ​​all grayscale values, and divide the total pixel area to obtain pixel area ranges corresponding to different types of working conditions.

[0125] In the specific implementation of step S405 , the total pixel area of ​​all pixels with a grayscale value of 255 is calculated, and the total pixel area is divided to obtain pixel area ranges corresponding to different types of working conditions.

[0126] Optionally, different types of operating conditions include but are not limited to no-load operating conditions, continuously changing operating conditions, and full-load operating conditions.

[0127] Optionally, in an embodiment of the present invention, the pixel area ranges corresponding to the no-load condition, the continuously changing condition, and the full-load condition are (0, R1), (R1, R2), and (R2, ∞), respectively.

[0128] Step S406: determining the operating condition models corresponding to the different types of operating conditions based on the pixel area ranges corresponding to the different types of operating conditions.

[0129] In the process of specifically implementing step S406, if the total pixel area of ​​the color image in the current video signal to be analyzed is in (0, R1), then the operating condition model of the working condition corresponding to the video signal to be analyzed is determined to be a no-load operating condition model; if the total pixel area of ​​the color image in the current video signal to be analyzed is in (R1, R2), then the operating condition model of the working condition corresponding to the video signal to be analyzed is determined to be a continuously changing operating condition model; if the total pixel area of ​​the color image in the current video signal to be analyzed is in (R2, ∞), then the operating condition model of the working condition corresponding to the video signal to be analyzed is determined to be a fully loaded operating condition model.

[0130] Step S407: establishing a visual model based on the scheduling logic between the working condition models.

[0131] In step S407 , the scheduling logic of the working condition model refers to calling the working condition model corresponding to the working condition in the pixel area range where the total pixel area of ​​the color image in the video signal to be currently analyzed is located.

[0132] In the process of specifically implementing step S407, according to the pixel area range of the total pixel area of ​​the color image in the current video signal to be analyzed being (0, R1), and the working condition corresponding to (0, R1) being the no-load condition, the working condition model of the no-load condition (no-load working condition model) is called; according to the pixel area range of the total pixel area of ​​the color image in the current video signal to be analyzed being (R1, R2), and the working condition corresponding to (R1, R2) being the continuously changing condition, the working condition model of the continuously changing condition (continuously changing working condition model) is called; according to the pixel area range of the total pixel area of ​​the color image in the current video signal to be analyzed being (R2, ∞), and the working condition corresponding to (R2, ∞) being the full-load condition, the working condition model of the full-load condition (full-load working condition model) is called; a visual model is established based on the above content.

[0133] According to an embodiment of the present invention, a method for automatically selecting multiple working condition models based on video signals is provided. By training visual models on video signals of different working conditions, a visual model is obtained. The visual model is then used to analyze the video signals to be analyzed, thereby improving the scalability and reliability of each working condition model.

[0134] Based on the above-mentioned embodiment of the present invention, a method for automatically selecting multiple working condition models based on video signals is provided. If the working conditions include no-load working conditions, continuously changing working conditions, and full-load working conditions, step S102 is executed to analyze the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed, such as Figure 6 FIG. 1 is a flow chart of determining a working condition model corresponding to a working condition of a video signal to be analyzed according to an embodiment of the present invention, which mainly includes the following steps:

[0135] Step S601: performing image processing on the video signal to be analyzed based on a pre-established visual model to obtain a color image.

[0136] In the specific implementation of step S601 , the video signal to be analyzed is input into the above-established visual model for image processing to obtain a color image.

[0137] Step S602: Calculate the total pixel area of ​​the color image.

[0138] In the specific implementation of step S602 , the brightness of the three components in the color image is first calculated, and the maximum value of the brightness of the three components is used as the grayscale value of the grayscale image to obtain a grayscale image represented by pixels.

[0139] Next, the grayscale image is processed by mean filtering using the kernel data to obtain a filtered grayscale image.

[0140] Next, based on a preset threshold, the filtered grayscale image is subjected to image binarization processing to obtain the grayscale values ​​of the pixels of the filtered grayscale image.

[0141] Finally, the total pixel area of ​​all grayscale values ​​is calculated to obtain the total pixel area of ​​the color image.

[0142] Step S603: Determine whether the total pixel area is smaller than R1. If so, execute step S604; if not, execute step S605.

[0143] In step S503, R1 is a positive integer.

[0144] In the process of implementing step S603, determine whether the total pixel area is smaller than R1. If so, it means that the total pixel area of ​​the color image is smaller than R1, and execute step S604. If not, it means that the total pixel area of ​​the color image is larger than R1, but the total pixel area of ​​the color image may be smaller than R2, and execute step S605.

[0145] Step S604: Determine that the working condition model corresponding to the working condition of the video signal to be analyzed is a no-load working condition model.

[0146] In the specific implementation process of step S604, the calculated total pixel area of ​​the color image is compared with R1 to determine that the total pixel area of ​​the color image is smaller than R1. From the above visual model, it can be seen that the total pixel area of ​​the color image is at (0, R1). It can be determined that the working condition corresponding to the video signal to be analyzed is the no-load working condition, and it can be further determined that the working condition model of the working condition corresponding to the video signal to be analyzed is the no-load working condition model.

[0147] Step S605: Determine whether the total pixel area is greater than R1 and smaller than R2. If so, execute step S606; if not, execute step S607.

[0148] In step S603 , R2 is a positive integer, and R1 is smaller than R2.

[0149] In the process of implementing step S605, determine whether the total pixel area is greater than R1 and smaller than R2. If so, it means that the total pixel area of ​​the color image is greater than R1 and smaller than R2, and execute step S606. If not, it means that the total pixel area of ​​the color image is greater than R2, and execute step S607.

[0150] Step S606: Determine that the operating condition model corresponding to the operating condition of the video signal to be analyzed is a continuously changing operating condition model.

[0151] In the specific implementation of step S606, the calculated total pixel area of ​​the color image is compared with R1 and R2 to determine that the total pixel area of ​​the color image is greater than R1 and smaller than R2. From the above visual model, it can be seen that the total pixel area of ​​the color image is at (R1, R2). It can be determined that the working condition corresponding to the video signal to be analyzed is a continuously changing working condition, and it can be further determined that the working condition model of the working condition corresponding to the video signal to be analyzed is a continuously changing working condition model.

[0152] Step S607: Determine whether the total pixel area is greater than R2. If so, execute step S608; if not, execute step S603.

[0153] In the specific implementation of step S607, determine whether the total pixel area is greater than R2. If so, it means that the total pixel area of ​​the color image is greater than R2, and execute step S608. If not, it means that the total pixel area of ​​the color image is less than R2, and execute step S603.

[0154] Step S608: Determine that the operating condition model corresponding to the operating condition of the video signal to be analyzed is a full-load operating condition model.

[0155] In the specific implementation of step S608, the calculated total pixel area of ​​the color image is compared with R1 and R2 to determine that the total pixel area of ​​the color image is greater than R2. From the above visual model, it can be seen that the total pixel area of ​​the color image is at (R2, ∞), and it can be determined that the working condition corresponding to the video signal to be analyzed is the full-load working condition. It can be further determined that the working condition model of the working condition corresponding to the video signal to be analyzed is the full-load working condition model.

[0156] An automatic selection method for multiple working condition models based on video signals is provided based on an embodiment of the present invention. By using a visual model to analyze the video signal to be analyzed, it is determined which working condition the video signal to be analyzed is in, and then the working condition model of the working condition corresponding to the video signal to be analyzed is determined, thereby improving the scalability and reliability of each working condition model.

[0157] Based on the above-mentioned embodiment of the present invention provides a method for automatically selecting multiple working condition models based on video signals, if the currently executed business including multiple working conditions is a rubber discharge quantity monitoring business, and the working conditions include no-load working conditions, continuously changing working conditions and fully loaded working conditions, step S103 is executed to call the working condition model for prediction, and the process of obtaining the predicted working condition parameters is as follows: Figure 7 FIG. 1 is a flow chart of calling a working condition model for prediction in a rubber feed rate monitoring service according to an embodiment of the present invention, which mainly includes the following steps:

[0158] Step S701: Determine the working condition model of the working condition corresponding to the video signal to be analyzed. If it is a no-load working condition model, execute step S702; if it is a continuously changing working condition model, execute step S703; if it is a fully loaded working condition model, execute step S704.

[0159] Step S702: calling the scheduling logic corresponding to the no-load working condition model, and using the total pixel area corresponding to the no-load working condition to predict the unloading amount of the rubber unloading conveyor belt, to obtain the predicted unloading amount A.

[0160] In step S702, A is a positive integer.

[0161] In the embodiment of the present invention, A is 0 kg / h.

[0162] It should be noted that under no-load conditions, there is no raw material on the conveyor belt, and the material discharge rate is close to 0kg / h. At this time, only the black surface of the conveyor belt can be seen in the video signal, and almost no rubber raw material can be monitored.

[0163] In the process of specifically implementing step S702, it can be seen from the fact that the working condition model corresponding to the working condition of the video signal to be analyzed is the no-load working condition model that the working condition corresponding to the video signal to be analyzed is the no-load working condition. After obtaining the total pixel point area corresponding to the no-load working condition, the no-load working condition model is called, and the total pixel point area corresponding to the no-load working condition is used to predict the unloading amount of the rubber unloading conveyor belt, and the predicted unloading amount is 0kg / h.

[0164] Step S703: calling the scheduling logic corresponding to the continuously changing working condition model, and using the total pixel area corresponding to the continuously changing working condition to predict the discharge amount of the rubber discharge conveyor belt, to obtain the predicted discharge amount B.

[0165] In step S703, B is a positive integer.

[0166] In the embodiment of the present invention, B is 0 to 6000 kg / h.

[0167] It should be noted that in the continuous production of rubber under continuously changing working conditions, the unstable upstream production causes the unloading amount on the conveyor belt to fluctuate continuously, sometimes increasing and sometimes decreasing. At this time, the unloading rate ranges from 0 to 6000 kg / h. Since the conveyor belt has a vibration function, the raw materials are evenly spread on the conveyor belt, but the surface of the conveyor belt is not completely covered, resulting in a sharp contrast between the exposed conveyor belt surface and the white rubber raw material.

[0168] In the process of specifically implementing step S703, it can be seen from the fact that the working condition model of the working condition corresponding to the video signal to be analyzed is a continuously changing working condition model that the working condition corresponding to the video signal to be analyzed is a continuously changing working condition. After obtaining the total pixel point area corresponding to the continuously changing working condition, the continuously changing working condition model is called, and the total pixel point area corresponding to the continuously changing working condition is used to predict the unloading amount of the rubber unloading conveyor belt, and the predicted unloading amount is 0 to 6000 kg / h.

[0169] Optionally, the total pixel area corresponding to the continuously changing working condition is used, and according to a pre-established linear model, the unloading amount of the rubber unloading conveyor belt is predicted, and the predicted unloading amount is 0 to 6000 kg / h.

[0170] The formula for the linear model is as follows:

[0171] f(x i )=ωx i +b, (5),

[0172] Among them, x i is the calculated pixel area; f(x i ) is the preset feeding amount.

[0173] Step S704: calling the scheduling logic corresponding to the full-load working condition model, and using the total pixel area corresponding to the full-load working condition and the downstream press working state parameters to predict the discharge amount of the rubber discharge conveyor belt, to obtain the predicted discharge amount C.

[0174] In step S704, C is a positive integer.

[0175] In the embodiment of the present invention, C is 6000-8000 kg / h.

[0176] It should be noted that during continuous rubber production, fully loaded conditions occur. Once upstream production reaches a stable state, the conveyor belt unloads material at full capacity and stabilizes. At this point, the unloading rate ranges from 6,000 to 8,000 kg / h. The material completely covers the conveyor belt surface, leaving virtually no exposed surface. The material accumulates continuously, stopping at a certain level.

[0177] When unloading on the conveyor belt, the unloading rate is 0-7t / h. When it exceeds about 5.5t / h, it begins to accumulate, and 7t / h reaches the maximum accumulation level.

[0178] In the process of specifically implementing step S704, it can be seen from the fact that the working condition model of the working condition corresponding to the video signal to be analyzed is the full-load working condition model that the working condition corresponding to the video signal to be analyzed is the full-load working condition. After obtaining the total pixel area corresponding to the full-load working condition, the full-load working condition model is called, and the total pixel area corresponding to the full-load working condition and the working state parameters of the downstream extruder are used to predict the feeding amount of the rubber feeding conveyor belt, and the predicted feeding amount is 0 to 6000 kg / h.

[0179] It should be noted that the working state parameters of the extruder include but are not limited to the extruder current, grinding head pressure, and inner wall temperature.

[0180] Through the neural network training model, the mapping relationship between the working state parameters of the extruder and the discharge amount on the conveyor belt is established.

[0181] It should be noted that in order to better understand the above description, the rubber process flow is explained below.

[0182] Figure 8 A schematic diagram of a rubber process flow provided by an embodiment of the present invention.

[0183] exist Figure 8 In the rubber process, the main process includes the discharge port, vibrating screen and extruder. The raw materials are discharged at the discharge port and enter the vibrating screen. Then the raw materials on the vibrating screen directly enter the extruder for compression and water filtration.

[0184] Figure 9 A characteristic schematic diagram of neural network modeling under full load conditions provided by an embodiment of the present invention.

[0185] exist Figure 9 In the process, after feature extraction of process mechanism and equipment operation analysis, the extruder current, grinding head pressure, inner wall temperature, etc. are used as key parameters. Through the neural network algorithm, the real-time feeding amount is fitted and predicted, and the corresponding model is established to realize online monitoring under full load conditions.

[0186] Figures 10(a) and 10(b) are comparison diagrams of a rubber unloading conveyor belt provided by an embodiment of the present invention in an empty working condition and a fully loaded working condition, and Figures 11(a) and 11(b) are schematic diagrams of the effects before and after machine vision processing of a rubber unloading conveyor belt provided by an embodiment of the present invention in an empty working condition and a fully loaded working condition.

[0187] Figure 10(a) shows the state of the rubber unloading conveyor belt under no-load conditions. Under no-load conditions, there is no raw material on the conveyor belt. At this time, the unloading rate is close to 0 kg / h. At this time, only the black surface of the conveyor belt can be seen in the video signal, and almost no rubber raw material can be detected. The effect is shown in Figure 11(a).

[0188] Figure 10(b) shows the state of the rubber unloading conveyor belt under full load. Under full load, after upstream production reaches a stable state, the unloading rate on the conveyor belt also reaches full load and stabilizes. At this time, the unloading rate ranges from 6000 to 8000 kg / h. The raw material completely covers the conveyor belt surface, with almost no exposed surface visible, and the thickness continues to accumulate, as shown in Figure 11(b).

[0189] An automatic selection method for multiple working condition models based on video signals provided in an embodiment of the present invention processes the video signals to be analyzed in a rubber discharge quantity monitoring service under no-load conditions, continuously changing conditions, or full-load conditions, and calls the working condition model corresponding to the working condition determined by the video signal to be analyzed to predict the working condition parameters, thereby improving the scalability and reliability of each working condition model.

[0190] The above-mentioned embodiment of the present invention Figure 1 Corresponding to the method for automatically selecting multiple working condition models based on video signals shown in FIG, an embodiment of the present invention further provides an automatic device for selecting multiple working condition models based on video signals, such as Figure 12 As shown, the device for automatically selecting multiple working condition models based on video signals includes: an acquisition module 1201 , an analysis module 1202 and a prediction module 1203 .

[0191] The acquisition module 1201 is used to acquire the captured video signal to be analyzed in real time during the execution of a business process involving multiple working conditions.

[0192] The analysis module 1202 is configured to analyze the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed.

[0193] The prediction module 1203 is used to call the operating condition model to perform prediction and obtain predicted operating condition parameters.

[0194] Optional, based on the above Figure 12 The analysis module 1202 shown is specifically configured to:

[0195] The video signal to be analyzed is processed based on a pre-established visual model to obtain a color image; the total pixel area of ​​the color image is calculated; the working condition model of the working condition corresponding to the video signal to be analyzed is determined using the total pixel area; there is a preset corresponding relationship between the total pixel area and the working condition model.

[0196] Optional, based on the above Figure 12 The prediction module 1203 shown is specifically configured to:

[0197] The working condition model is called and the total pixel area is used for prediction to obtain the predicted working condition parameters.

[0198] It should be noted that the specific principles and execution processes of each module or unit in the automatic selection device for multi-working condition models based on video signals disclosed in the above-mentioned embodiment of the present invention are the same as those of the automatic selection method for multi-working condition models based on video signals implemented in the above-mentioned embodiment of the present invention. Please refer to the corresponding parts of the automatic selection method for multi-working condition models based on video signals disclosed in the above-mentioned embodiment of the present invention, and they will not be repeated here.

[0199] An embodiment of the present invention provides a device for automatically selecting multiple operating condition models based on video signals. While executing a business process involving multiple operating conditions, the device acquires a captured video signal to be analyzed in real time. The device analyzes the video signal to be analyzed based on a pre-established visual model to obtain an operating condition model corresponding to the operating condition of the video signal to be analyzed. The operating condition model is then used to perform predictions to obtain predicted operating condition parameters. In this solution, after pre-establishing a visual model, the visual model is used to analyze the video signal to be analyzed. After determining the operating condition model corresponding to the operating condition of the video signal to be analyzed, the determined operating condition model is used to predict operating condition parameters, thereby improving the generalizability and reliability of each operating condition model.

[0200] Optional, based on the above Figure 12 The multi-condition model automatic selection device based on video signals is shown, combined with Figure 12 ,like Figure 13 As shown, the apparatus for automatically selecting multiple working condition models based on video signals further includes a construction module 1304 .

[0201] The construction module 1304 includes: an acquisition unit, a grayscale unit, a mean filtering unit, an image binarization processing unit, a division unit, a determination unit and a creation unit.

[0202] The acquisition unit is used to add marks to the monitoring areas in the video signals of different working conditions and acquire color images in the monitoring areas.

[0203] The grayscale unit is used to calculate the three-component brightness in the color image, take the maximum value of the three-component brightness as the grayscale value of the grayscale image, and obtain a grayscale image represented by pixels.

[0204] The mean filtering unit is used to perform mean filtering on the grayscale image using the kernel data to obtain a filtered grayscale image.

[0205] The image binarization processing unit is used to perform image binarization processing on the filtered grayscale image based on a preset threshold value to obtain the grayscale values ​​of the pixels of the filtered grayscale image.

[0206] The division unit is used to calculate the total pixel area of ​​all grayscale values ​​and divide the total pixel area to obtain the pixel area range corresponding to different types of working conditions.

[0207] The determination unit is used to determine the working condition models corresponding to different types of working conditions based on the pixel area ranges corresponding to the different types of working conditions.

[0208] The establishment unit is used to establish a visual model based on the scheduling logic between the working condition models.

[0209] An automatic selection device for multiple working condition models based on video signals is provided based on an embodiment of the present invention. A visual model is obtained by performing visual model training on video signals of different working conditions. The visual model is then used to analyze the video signal to be analyzed, thereby improving the scalability and reliability of each working condition model.

[0210] Optional, based on the above Figure 12 The analysis module 1202 shown is specifically configured to:

[0211] The video signal to be analyzed is processed based on a pre-established visual model to obtain a color image; the total pixel area of ​​the color image is calculated; if the total pixel area is less than R1, the working condition model of the working condition corresponding to the video signal to be analyzed is determined to be a no-load working condition model; if the total pixel area is greater than R1 and less than R2, the working condition model of the working condition corresponding to the video signal to be analyzed is determined to be a continuously changing working condition model; if the total pixel area is greater than R2, the working condition model of the working condition corresponding to the video signal to be analyzed is determined to be a fully loaded working condition model; R1 and R2 are positive integers, and R1 is less than R2.

[0212] An automatic selection device for multiple working condition models based on video signals provided in an embodiment of the present invention analyzes the video signal to be analyzed by using a visual model to determine the working condition of the video signal to be analyzed, and then determines the working condition model of the working condition corresponding to the video signal to be analyzed, thereby improving the scalability and reliability of each working condition model.

[0213] Optional, based on the above Figure 12 The prediction module 1203 shown is specifically configured to:

[0214] If the working condition model of the working condition corresponding to the video signal to be analyzed is the no-load working condition model, the scheduling logic corresponding to the no-load working condition model is called, and the unloading amount of the rubber unloading conveyor belt is predicted using the total pixel area corresponding to the no-load working condition to obtain the predicted unloading amount A; if the working condition model of the working condition corresponding to the video signal to be analyzed is the continuously changing working condition model, the scheduling logic corresponding to the continuously changing working condition model is called, and the unloading amount of the rubber unloading conveyor belt is predicted using the total pixel area corresponding to the continuously changing working condition to obtain the predicted unloading amount B; if the working condition model of the working condition corresponding to the video signal to be analyzed is the fully loaded working condition model, the scheduling logic corresponding to the fully loaded working condition model is called, and the unloading amount of the rubber unloading conveyor belt is predicted using the total pixel area corresponding to the fully loaded working condition and the working state parameters of the downstream extruder to obtain the predicted unloading amount C; A, B and C are positive integers.

[0215] An automatic selection device for multiple working condition models based on video signals provided in an embodiment of the present invention processes the video signals to be analyzed in the rubber discharge quantity monitoring business under no-load conditions, continuously changing conditions, or full-load conditions, and calls the working condition model corresponding to the working condition determined by the video signal to be analyzed to predict the working condition parameters, thereby improving the scalability and reliability of each working condition model.

[0216] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0217] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0218] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for automatically selecting multi-condition models based on video signals, characterized in that: The method comprises: Acquire the captured video signals to be analyzed in real time during the execution of business operations involving various working conditions; The video signal to be analyzed is analyzed based on a pre-established visual model to obtain a working condition model of the working condition corresponding to the video signal to be analyzed, which includes: performing image processing on the video signal to be analyzed based on the pre-established visual model to obtain a color image; calculating the total pixel area of ​​the color image; and determining the working condition model of the working condition corresponding to the video signal to be analyzed using the total pixel area; wherein a preset corresponding relationship exists between the total pixel area and the working condition model; The operating condition model is called to perform prediction to obtain predicted operating condition parameters.

2. The method according to claim 1, characterized in that The calling of the operating condition model to perform prediction and obtain the predicted operating condition parameters includes: The operating condition model is called, and prediction is performed using the total pixel area to obtain predicted operating condition parameters.

3. The method according to claim 1, characterized in that The process of pre-establishing a visual model includes: Marking monitoring areas in video signals of different working conditions and acquiring color images of the monitoring areas; Calculating the brightness of the three components in the color image, taking the maximum value of the brightness of the three components as the grayscale value of the grayscale image, and obtaining a grayscale image represented by pixels; Performing mean filtering on the grayscale image using Kernel data to obtain a filtered grayscale image; Based on a preset threshold, performing image binarization processing on the filtered grayscale image to obtain grayscale values ​​of pixels in the filtered grayscale image; Calculating the total pixel area of ​​all the grayscale values, and dividing the total pixel area to obtain pixel area ranges corresponding to different types of working conditions; Determining the operating condition models corresponding to the different types of operating conditions based on the pixel area ranges corresponding to the different types of operating conditions; A visual model is established based on the scheduling logic between the working condition models.

4. The method according to claim 1, wherein If the working condition includes a no-load working condition, a continuously changing working condition, and a full-load working condition, the video signal to be analyzed is analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed, including: Performing image processing on the video signal to be analyzed based on a pre-established visual model to obtain a color image; Calculating the total pixel area of ​​the color image; If the total pixel area is smaller than R1, determining that the working condition model corresponding to the working condition of the video signal to be analyzed is the no-load working condition model; If the total pixel area is greater than R1 and less than R2, determining that the working condition model corresponding to the working condition of the video signal to be analyzed is the continuously changing working condition model; If the total pixel area is greater than R2, it is determined that the working condition model corresponding to the working condition of the video signal to be analyzed is the full-load working condition model; R1 and R2 are positive integers, and R1 is less than R2.

5. The method according to claim 2 or 4, characterized in that If the currently executed business involving multiple working conditions is a rubber unloading amount monitoring business, the working conditions include no-load working conditions, continuously changing working conditions, and fully loaded working conditions, the working condition model is called for prediction to obtain predicted working condition parameters, including: If the working condition model corresponding to the working condition of the video signal to be analyzed is the no-load working condition model, calling the scheduling logic corresponding to the no-load working condition model, and using the total pixel area corresponding to the no-load working condition to predict the feeding amount of the rubber feeding conveyor belt, to obtain the predicted feeding amount A; If the working condition model corresponding to the working condition of the video signal to be analyzed is the continuously changing working condition model, calling the scheduling logic corresponding to the continuously changing working condition model, and using the total pixel area corresponding to the continuously changing working condition to predict the feeding amount of the rubber feeding conveyor belt, to obtain the predicted feeding amount B; If the working condition model corresponding to the working condition of the video signal to be analyzed is the full-load working condition model, the scheduling logic corresponding to the full-load working condition model is called, and the feeding amount of the rubber feeding conveyor belt is predicted using the total pixel area corresponding to the full-load working condition and the working state parameters of the downstream extruder to obtain the predicted feeding amount C; A, B and C are positive integers.

6. A device for automatically selecting multiple working condition models based on video signals, characterized in that: The device comprises: An acquisition module is used to acquire the captured video signals to be analyzed in real time during the execution of a business process involving multiple working conditions; An analysis module, configured to analyze the video signal to be analyzed based on a pre-established visual model to obtain a working condition model corresponding to the working condition of the video signal to be analyzed; A prediction module, used to call the operating condition model to perform prediction and obtain predicted operating condition parameters; The analysis module is specifically used for: The video signal to be analyzed is subjected to image processing based on a pre-established visual model to obtain a color image; the total pixel area of ​​the color image is calculated; the working condition model of the working condition corresponding to the video signal to be analyzed is determined using the total pixel area; and a preset corresponding relationship exists between the total pixel area and the working condition model.

7. The device according to claim 6, characterized in that The prediction module is specifically used for: The operating condition model is called, and prediction is performed using the total pixel area to obtain predicted operating condition parameters.

8. The device according to claim 6, characterized in that Also includes: Building blocks; The building module includes: an acquisition unit, a grayscale unit, a mean filtering unit, an image binarization processing unit, a division unit, a determination unit and a creation unit; The acquisition unit is used to add marks to the monitoring areas in the video signals of different working conditions and acquire color images in the monitoring areas; The grayscale unit is used to calculate the brightness of the three components in the color image, and use the maximum value of the brightness of the three components as the grayscale value of the grayscale image to obtain a grayscale image represented by pixels; The mean filtering unit is used to perform mean filtering on the grayscale image using Kernel data to obtain a filtered grayscale image; The image binarization processing unit is used to perform image binarization processing on the filtered grayscale image based on a preset threshold value to obtain the grayscale values ​​of the pixels of the filtered grayscale image; The division unit is used to calculate the total pixel area of ​​all the grayscale values ​​and divide the total pixel area to obtain pixel area ranges corresponding to different types of working conditions; The determining unit is configured to determine the operating condition models corresponding to the different types of operating conditions based on the pixel area ranges corresponding to the different types of operating conditions; The establishing unit is used to establish a visual model based on the scheduling logic between the working condition models.

Images