CN115482416A - Method, device and equipment for alarming out-of-order wire of packing wire and storage medium - Google Patents

Abstract

The invention provides a method, a device, equipment and a storage medium for alarming when a wrapping wire is disordered, wherein the method comprises the steps of obtaining a target environment image of a target wrapping station; inputting the target environment image into a packing characteristic labeling model to obtain a packing line identifier and a packing station mark bit identifier, and training the packing characteristic labeling model to obtain a target packing station initial environment image; converting color channels of the initial environment image into each other to generate a converted environment image; determining the initial environment image and the conversion environment image as sample images, labeling the sample images, and generating a sample data set; determining the trained model as a packing characteristic labeling model; determining the packing wire state of a target packing station and sending alarm information based on the number of the packing wire marks and the number of the packing station mark marks; the image acquisition and the image processing related to the invention are completed by the mechanical equipment, so that the judgment accuracy is improved, and the labor cost is effectively reduced.

Description

Method, device and equipment for alarming out-of-order wire of wrapping wire and storage medium

Technical Field

The invention relates to the technical field of target detection, in particular to a method, a device, equipment and a storage medium for alarming out of order of a wrapping wire.

Background

In the production process of steel products, the packing process is an important step of wire and bar production, a plurality of packing machines are shared in a packing station, and each packing machine needs a corresponding wire to pack. In the process of wire feeding, the wires are wound with a certain probability, and once the wires are wound, the feeding is blocked, so that the wires are broken, and therefore, in the actual production, the winding condition of the wires is found in time and is processed, which is particularly important. The disordered wire identification of the packing wire generally applicable in the current market mainly depends on experienced workers to carry out manual identification, but because a plurality of production lines need to run for a long time, a large amount of manpower needs to be invested to complete disordered wire state identification of the packing wire, the manual identification is limited by subjective consciousness and production experience of people, uncertainty exists in judgment conclusion, and the accuracy cannot be estimated.

Therefore, whether the packaging wire is wound or not needs to be detected in real time by adopting an intelligent monitoring means in the whole packaging process, and alarm information is sent out in time when the winding of the wire is detected, so that more labor cost is saved, and the accuracy of a judgment conclusion is improved.

Disclosure of Invention

In view of the disadvantages of the prior art, the present invention provides a method, an apparatus, a device and a storage medium for alarming when a wire is broken, so as to solve the above technical problems.

The invention provides a method for alarming the disorder of a packing wire, which comprises the following steps: acquiring a target environment image of a target packing station; inputting the target environment image into a packing characteristic labeling model to obtain a packing line identifier and a packing station marker identifier, wherein the training mode of the packing characteristic labeling model comprises the steps of obtaining an initial environment image of the target packing station, and the initial environment image comprises a red, green and blue three-primary-color channel; converting the red, green and blue three-primary color channels with each other, including interchanging the brightness value of the red color channel with the brightness value of the blue color channel to generate a conversion environment image; determining the initial environment image and the conversion environment image as sample images, and marking the characteristic of a packing line and the characteristic of a packing station mark bit in the sample images to generate a sample data set; training an initial labeling model based on the sample data set, and determining the trained initial labeling model as a packing characteristic labeling model; determining the packing wire state of the target packing station based on the number of the packing wire identifications and the number of the packing station mark identifications; and when the packing wire state of the target packing station is a wire disordering state, sending alarm information.

In one embodiment of the invention, obtaining the initial environment image of the target packing station further comprises: determining a region of interest of an initial environment image based on the initial environment image of the target packing station; determining a region outside the region of interest in the initial environment image as a region of non-interest, and filtering the region of non-interest.

In an embodiment of the present invention, labeling the characteristic of the packing line and the characteristic of the packing station flag in the sample image includes: carrying out rotary labeling on the characteristic of the packing line and the characteristic of the marker bit of the packing station in the sample image through a rectangular frame, wherein the rectangular frame comprises a non-standard rectangular frame; correcting the non-standard rectangular frame into a standard rectangular frame through a minimum circumscribed rectangle; eliminating abnormal angle loss values at the boundary based on an annular smooth label method to obtain an angle prediction result of the packing feature labeling model; and detecting the packing line and the packing station zone bit with rotation attributes in a preset angle range based on the angle prediction result to obtain a packing line characteristic marking frame and a packing station zone bit characteristic marking frame.

In an embodiment of the present invention, after determining the state of the bundling line of the target bundling station based on the number of the bundling line identifiers and the number of the bundling station flag identifiers, the method further includes: if the packing wire state of the target packing station is a disordered wire state, judging that the feeding state of the packing machine is abnormal, wherein the abnormal feeding state of the feeding machine comprises a packing wire missing state and a packing wire winding state; the packaging machine is arranged at the target packaging station and used for packaging products by using a packaging line, and the packaging station mark bit is arranged on the packaging machine or the target packaging station.

In one embodiment of the invention, the judging that the feeding state of the packaging machine is abnormal comprises the following steps: determining the position of each packing wire based on the packing wire identification, and if the positions of at least two packing wires are crossed, judging that the feeding abnormal state is a packing wire winding state; and if the positions of any packing lines are not crossed, judging that the feeding abnormal state is a packing line missing state.

In an embodiment of the present invention, inputting the target environment image into the packing feature labeling model to obtain a packing station identifier and a packing station flag identifier includes: inputting the target environment image into the packing characteristic marking model, and identifying the characteristic of the marking bit of the packing station and the characteristic of the packing line in the target environment image to obtain a marking frame of the packing line and a marking frame of the marking bit of the packing station; and determining the packing wire marking frame as a packing wire identifier, and determining the packing station mark bit marking frame as a packing station mark bit identifier.

In an embodiment of the present invention, determining the packing line state of the target packing station based on the number of the packing line identifiers and the number of the packing station flag identifiers includes: determining the number of the packing line identifications and the number of the packing station mark identifications based on the packing line identifications and the packing station mark identifications; if the number of the wrapping line identifiers is equal to the number of the identifier numbers of the wrapping stations, judging that the state of the wrapping line of the target wrapping station is a normal state; and if the number of the packing line identifications is less than the number of the packing station mark bit identifications, judging that the packing line state of the target packing station is a disordered line state.

In one embodiment of the present invention, sending alarm information based on the wire disorder state includes: acquiring an environment image of a plurality of frames of the target station, and detecting the wrapping line state of the plurality of frames of the target station; when the wrapping state of the multiple frames of the target stations is detected to be a messy state, determining the messy frame number of the multiple frames of the target stations, wherein the wrapping state of the multiple frames of the target stations is the messy state; and if the number of the random line frames is greater than or equal to the preset safety frame number threshold value, sending alarm information.

The invention provides a device for alarming the disorder of a packing wire, which comprises: the image acquisition module is used for acquiring a target environment image of a target packaging station; the identification determining module is used for inputting the target environment image into the packing characteristic labeling model to obtain a packing line identification and a packing station mark bit identification; the state determining module is used for determining the packing line state of the target packing station based on the number of the packing line identifications and the number of the packing station mark identifications; and the alarm module is used for sending alarm information when the packing wire state of the target packing station is a wire disordering state.

The present invention provides an electronic device, including: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic equipment is enabled to realize the method for alarming out of the wire of the bundling as described above.

The present invention provides a computer-readable storage medium, characterized in that a computer program is stored thereon, which, when executed by a processor of a computer, causes the computer to execute the wrapping-wire miswire alarm method as described above.

Has the beneficial effects that: according to the method, the device, the equipment and the storage medium for alarming the disordered wire of the packing wire, provided by the invention, the target environment image of a target packing station is obtained, a packing characteristic labeling model is obtained based on the target environment image training, the target environment image is subjected to mask processing in the model training process so as to improve the reasoning speed of the model, the obtained environment image is subjected to color channel change processing to obtain a new environment image, the environment image obtained by color channel conversion and the environment image obtained by initial acquisition are used as sample data so as to improve the generalization capability of the model, the packing wire identification and the packing station mark bit identification in the target environment image are identified through the packing characteristic model, the state of the packing wire is judged by comparing the number of the packing wire identification and the number of the packing station mark bit identification, and the alarm is given according to the disordered wire state of the packing wire; the image acquisition, the image processing and the final conclusion drawing are completed by the mechanical equipment, so that the accuracy of judgment is greatly improved, and the labor cost is effectively reduced.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

fig. 1 is a schematic diagram of a system architecture for performing a wire field packaging and wire disorder alarm according to an exemplary embodiment of the present application;

FIG. 2 is a flow chart illustrating the steps of packed mess line alert identification according to an exemplary embodiment of the present application;

FIG. 3 is a schematic diagram of a baling station shown in an exemplary embodiment of the present application;

FIG. 4 is a block diagram of a packaged miswire alarm device shown in an exemplary embodiment of the present application;

FIG. 5 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Other advantages and effects of the present invention will become apparent to those skilled in the art from the disclosure herein, wherein the embodiments of the present invention are described in detail with reference to the accompanying drawings and preferred embodiments. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, and are not intended to limit the scope of the present invention.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present invention, however, it will be apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details, and in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring embodiments of the present invention.

Fig. 1 is a schematic diagram of a system architecture for performing a package wire disorder alarm in a wire field according to an exemplary embodiment of the present application.

Referring to fig. 1, the system architecture may include an image acquisition apparatus 101 and a computer device 102. The computer device 102 may be at least one of a desktop Graphics Processing Unit (GPU) computer, a GPU computing cluster, a neural network computer, and the like. The environment image of the packing station is acquired through the image acquisition device, and then related technicians can use the computer equipment 102 to process the environment image, so that the conclusion whether the packing line of the packing station has disorder lines or not and whether an alarm is needed or not is obtained.

Illustratively, the image acquisition device 101 firstly acquires an environment image of a target packing station, and transmits the environment image to the computer device 102, after the computer device 102 receives the environment image of the target packing station, a packing characteristic labeling model is obtained based on environment image training, then the target environment image is input to the packing characteristic labeling model to obtain a packing line identifier and a packing station mark identifier, then the disorder condition of the packing line of the target packing station is judged by comparing the number of the packing line identifiers with the number of the packing station mark identifiers, and alarm information is sent based on the disorder condition.

Fig. 2 is a flowchart illustrating a procedure of alarming for a wire-wrapping disorder according to an exemplary embodiment of the present application.

As shown in fig. 2, in an exemplary embodiment, the method for alarming for the disordered wire of the covered wire at least includes steps S210 to S240, which are described in detail as follows:

and step S210, acquiring a target environment image of a target packaging station.

It should be understood that a fixed camera is provided at each packing station to acquire the operating state of each packing station. The environment image of the target packing station is collected through the fixed camera arranged on the packing station, one or more cameras are arranged on the periphery of the target station, the collected environment image can be adjusted through adjusting the angle of the cameras, so that multiple environment images comprising target packing station information are obtained, and the multiple images capable of comprising 360 degrees of the target packing station are optimal.

In one embodiment of the invention, a plurality of 2073600 high-definition camera devices for shooting are arranged at different angles of a target packing station, and the camera devices are matched with a work station, so that the relevant camera devices can acquire working condition pictures of each station in a scene. And based on the camera equipment arranged at the packing station, 1920x1080 high-resolution environment images are acquired so as to ensure that the identification labeling model can extract accurate image information for training, and the accuracy of the identification labeling model is improved.

Step S220, inputting the target environment image into a packing characteristic labeling model to obtain a packing line identifier and a packing station mark bit identifier. The training mode of the packing characteristic labeling model comprises the steps of obtaining an initial environment image of a target packing station, wherein the initial environment image comprises a red, green and blue three-primary color channel; converting the three primary colors of red, green and blue color channels with each other, including interchanging the brightness value of the red color channel with the brightness value of the blue color channel, to generate a conversion environment image; determining the initial environment image and the conversion environment image as sample images, and marking the characteristic of a packing line and the characteristic of a packing station mark bit in the sample images to generate a sample data set; and training the initial labeling model based on the sample data set, and determining the trained initial labeling model as a packing characteristic labeling model.

It should be understood that, in the present invention, a packing feature labeling model is first obtained by training according to the environment image of the target packing workstation, and the model training steps are as follows: acquiring an initial environment image of a target packaging station, wherein the initial environment image comprises three primary colors of red, green and blue; converting the three primary color channels of red, green and blue into each other, wherein the conversion comprises interchanging the brightness value of the red color channel with the brightness value of the blue color channel to generate a conversion environment image; determining the initial environment image and the conversion environment image as sample images, and marking the characteristic of a packing line and the characteristic of a packing station mark bit in the sample images to generate a sample data set; and training the initial labeling model based on the sample data set, and determining the trained initial labeling model as a packing characteristic labeling model.

In the training process of the feature labeling model, the obtaining of the initial environment image of the target packing station further comprises: determining an interested area of the initial environment image based on the initial environment image of the target packing station; and determining a region outside the region of interest in the initial environment image as a region of non-interest, and filtering the region of non-interest.

The environment image not only comprises the packing station mark position and the packing line, but also comprises complex illumination conditions and figure images, but the mark position of the packing station is a triangular structure with bright characteristics existing on a packing machine, and the packing line is a strip-shaped line segment which is very convenient to identify and classify, so that the region where the packing line and the packing station mark position are located can be manually specified as an interested region in the environment image, the rest part of the region is a non-interested region, and the non-interested region is filtered, thereby avoiding the false detection condition and improving the model reasoning speed.

In an embodiment of the invention, a target environment image S is obtained, the image is divided into two parts, i.e., S1 and S2, wherein the S1 area is a target area including a packing line and a packing station flag bit, and the S2 area includes other image information such as image information of an operator, and the image S1 part is defined as an interested area, and the image S2 part is defined as a non-interested area, and the image S2 area is filtered.

The method comprises the steps of training a packed feature labeling model, firstly, obtaining an environment image as a sample data set. Because the acquired original environment image is limited, a new environment image can be obtained by performing channel change or rotation processing on the acquired original environment image, and the obtained new environment image and the acquired original environment image are jointly used as a sample image for model training to increase a sample data set for model training, thereby improving the generalization capability of the model.

In an embodiment of the present invention, a plurality of environment images of a target workstation are acquired by a camera device fixed in a working environment of a packing workstation, the acquired environment image information is used as a first image data set, channel change is performed on the acquired environment images, that is, brightness values of three primary color channels of an original environment image are extracted to obtain a new environment image with a red color channel brightness value of X, a green color channel brightness value of Y, and a blue color channel brightness value of Z, the red color channel brightness value is converted with the blue color channel brightness value to obtain a red color channel brightness value of Z, a green color channel brightness value of Y, and a blue color channel brightness value of X, the new environment image is used as a second image data set, and the first image data set and the second image data set are merged to be used as sample data sets required by model training.

In an embodiment of the present invention, the obtained environment images may also be subjected to rotation processing, that is, each environment image includes a packing line image and a packing station flag image, and any environment image M is subjected to matting to obtain a corresponding packing line image and a corresponding packing station flag image N, N in the image M is rotated by an angle R in a clockwise direction to obtain a new environment image M1, all M1 are combined together to serve as a third image data set, and the third image data set serves as a part of the sample image data set.

And after sample data of model training is obtained, labeling the sample image.

Marking the characteristic of the packing line and the characteristic of the marker bit of the packing station in the sample image comprises the following steps: carrying out rotary labeling on the characteristic of a packing line and the characteristic of a packing station mark bit in a sample image through a rectangular frame, wherein the rectangular frame comprises a non-standard rectangular frame; correcting the non-standard rectangular frame into a standard rectangular frame through the minimum circumscribed rectangle, and eliminating abnormal angle loss values at the boundary based on an annular smooth label method to obtain an angle prediction result of the packing feature labeling model; and detecting the packing line and the packing station zone bit with the rotation attribute in a preset angle range based on the angle prediction result to obtain a packing line characteristic marking frame and a packing station zone bit characteristic marking frame.

It should be understood that due to the visual effect and the rotation property of each wrapping line, a plurality of wrapping lines in the camera field of view may be overlapped greatly, and a traditional non-rotation detection algorithm may have a large amount of missing detection. In order to avoid the condition of missing detection, an angle prediction result is added at the output end of the model, and a high-precision rotating target detection model is innovatively developed.

In one embodiment of the present invention, the problem of angular periodicity is solved by using a Circular Smooth Label (CSL) to increase the tolerance of error between adjacent angles, and the formula of the circular smooth label method is as follows:

where g (x) is the window function, r is the radius of the window function, and θ is the angle of the current bounding box.

It should be understood that the acquired initial environment image has diverse environment information including complex illumination conditions and character information, so that a data set with training significance fully based on the rotation labeling needs to be made for deep learning model training to obtain the envelope marking information and the envelope marking position marking information of the target packing station. The standard rectangular frame is a parallelogram with one corner being a right angle, and the non-standard rectangle is other quadrangles with non-rectangle.

In one embodiment of the invention, a wrapping station image obtained by shooting in a specific industrial scene is subjected to labeling, learning, detecting and obtaining target frames of a wrapping line and a marker target (namely a wrapping line labeling frame and a wrapping station marker labeling frame), the position information of the wrapping line and the wrapping station marker in the image is detected through the target frames, the information is recorded at the same time, a wrapping station rotating data set is manufactured, and the wrapping station rotating data set is divided into three parts: training a training set, a testing set and a verifying set, and training a packing line and a packing station mark bit target detection model (namely a packing characteristic labeling model) by using data of the training set. When the detection model is trained, effective information which can be used for training of the training set after the image is labeled comprises image basic attributes and labeled information. The image base attributes are: filename-filename, width-width, height-height, depth-image depth. The labeling information includes: xmin, ymin, xmax and Ymax respectively represent the horizontal coordinate of the upper left corner, the vertical coordinate of the upper left corner, the horizontal coordinate of the lower right corner and the vertical coordinate of the lower right corner of each target frame in the image; class, i.e. the class of the target object. And extracting the wrapping line identifier and the wrapping station mark bit identifier in the range of the target frame in the training set image of each wrapping station target environment image through a deep learning network, and finally obtaining a rotation detection model (namely a wrapping feature labeling model) of the wrapping line and the mark bit target. In this embodiment, a Yolov5 neural network is selected, and other models, such as a transform, e.g., RNN (LSTM), fast-RCNN, R3det, etc., may be selected. During the training of the classification model, effective information which can be used for training of the training set after the image labeling comprises image basic attributes and labeling information. The image base attributes are: filename-filename, width-width, height-height, depth-image depth. The labeling information includes: xmin, ymin, xmax and Ymax respectively represent the horizontal coordinate of the upper left corner, the vertical coordinate of the upper left corner, the horizontal coordinate of the lower right corner and the vertical coordinate of the lower right corner of each target frame in the image; class, i.e. the class of the target object, where the target is either a wrapping line or a flag bit, both of which have a rotation property. And finally obtaining a packing station target classification model by learning the target characteristics and the categories of the target characteristics in the range of the target frame in each packing station training set image.

It should be understood that, the packing line identifiers and the packing station identifier identifiers are respectively labeled on the packing lines and the packing station identifiers in the target environment image through the packing characteristic labeling model, the number of the packing line identifiers is the number of the packing lines, the number of the packing station identifier identifiers is the number of the packing station identifiers in the same way, so that the number of the packing line identifiers and the number of the packing station identifier identifiers are obtained, namely the number of the packing lines and the number of the packing station identifiers, and the packing line disorder state of the packing station can be judged by comparing the number of the packing line identifiers and the number of the packing station identifier identifiers, so that alarm can be implemented according to the packing line disorder state.

And step S230, determining the packing wire state of the target packing station based on the number of the packing wire identifications and the number of the packing station mark identifications.

Inputting the target environment image into a packing characteristic labeling model, and obtaining a packing station identifier and a packing station mark identifier comprises the following steps: inputting the target environment image into a packing characteristic labeling model, and identifying the characteristic of a packing station mark bit and the characteristic of a packing line in the target environment image to obtain a packing line labeling frame and a packing station mark bit labeling frame; and determining the marking frame of the packing wire as the identification of the packing wire, and determining the marking frame of the marker bit of the packing station as the identification of the marker bit of the packing station.

Determining the packing line state of the target packing station based on the packing line identification number of the packing line identification and the packing station mark bit identification number of the packing station mark bit identification comprises the following steps: determining the number of the packing line identifications and the number of the packing station mark identifications on the basis of the packing line identifications and the packing station mark identifications; if the number of the packing wire identifications is equal to the number of the packing station mark bit identifications, judging that the packing wire state of the target packing station is a normal state; and if the number of the packing wire identifications is less than the number of the packing station mark bit identifications, judging that the packing wire state of the target packing station is a disordered wire state.

FIG. 3 is a schematic diagram of a baling station shown in an exemplary embodiment of the present application.

As shown in fig. 3, the whole image is a part of the target baling station, and a baling station flag, a baling line and a baling machine are included between the target baling station and the target baling station. The triangular A, B and C are the flag bits of the baling station, the linear a, B and C are the baling lines, and the area connecting the baling station and the baling lines is part of the baling machine. In the packing station as shown in the figure, a plurality of packing station mark positions and a plurality of packing wires are included, each packing station mark position corresponds to one packing wire, wherein the positions shown by A, B and C are the packing station mark positions, the positions shown by a, B and C are the packing wires, the packing wires a and B are not broken, and the packing wire C is broken. In the process of image recognition and marking, a and b are normally recognized and marked, and c cannot be successfully marked, so that in the target environment image, when the packing station packing line state is a normal state, the number of the packing station mark bit identifiers is equal to the number of the packing line identifiers; when the packing state of the packing station is a disordered state, the number of the mark bits of the packing station is greater than that of the packing line marks. The wrapping wire is broken due to the winding of the wrapping wire, so that the wrapping wire is in a disordered state when the wrapping wire is broken.

In an embodiment of the invention, the obtained target environment image is input into the packing feature labeling model, so that the number of the packing line feature identifications in the target environment image is K1, and the number of the packing station mark bit feature identifications in the target environment image is K2, and if K1 is less than K2 through comparison, the target packing station is judged to be in a disorder state.

In another embodiment of the invention, the obtained target environment image is input into the packing feature labeling model, so that the number of the packing line feature identifiers in the target environment image is K3, and the number of the packing station mark bit feature identifiers in the target environment image is K4, and if K3= K4 is obtained through comparison, the target packing station is determined to be in a normal state.

And S240, sending alarm information when the packing wire state of the target packing station is a wire disordering state.

Sending alarm information based on the disorder line state includes: acquiring an environment image of a plurality of frames of target stations, and detecting the wrapping line state of the plurality of frames of target stations; when the wrapping state of the multi-frame target station is detected to be a disordered state, determining the disordered frame number of the multi-frame target station, wherein the wrapping state of the multi-frame target station is the disordered state; and if the number of the disordered line frames is greater than or equal to the preset safety frame number threshold value, sending alarm information.

In an embodiment of the present invention, when a packing line of a certain packing station is in a disorder state, a threshold of a safe frame number for sending an alarm is preset to be N1. And determining that the packing wire state of the target packing station is a wire disorder state, acquiring N frames of images backwards based on the moment, marking the N frames of images, confirming that the packing station environment information in the N frames of images all indicate that the packing wire disorder state of the packing station is the wire disorder state, and controlling a controller of the packing station to send alarm information if N is greater than N1.

Still include after the packing line state of the target packing station is confirmed to packing line sign quantity based on packing line sign quantity of packing line sign and packing station sign quantity of packing station sign: if the packing wire state of the target packing station is a disordered wire state, judging that the feeding state of the packing machine is abnormal, wherein the abnormal feeding state of the feeding machine comprises a missing packing wire state and a winding packing wire state; the baling press sets up in target packing station to utilize the line packing product of making a bag, the station bit of making a bag sets up in baling press or target packing station.

Judge that baling press material loading state includes for the material loading is unusual: determining the position of each packing wire based on the packing wire identification, and if the positions of at least two packing wires are crossed, judging that the feeding abnormal state is a packing wire winding state; and if the positions of any packing lines are not crossed, judging that the feeding abnormal state is a packing line missing state.

It should be understood that the target baling station is a spatial area that includes the baler, the baling line, and the baling station flag. The packing station flag bit can be set on the packer or the packing station, and is not limited herein.

In an embodiment of the present invention, the number of the identifiers of the packing stations and the number of the identifiers of the packing lines of the target environment image are obtained based on the packing characteristic labeling model, so as to determine that the state of the packing lines of the target packing station is a disordered line state, and determine that the feeding state of the packing machine of the packing station is a feeding abnormal state based on the disordered line state of the packing lines. And determining the position information of each packing wire based on the packing wire identification, analyzing the position information of the plurality of packing wires to obtain the intersection of the packing wires, and judging that the packing wires at the packing station are wound, namely the abnormal loading state of the packing machine is the winding state of the packing wires.

In an embodiment of the present invention, the number of the identifiers of the packing stations and the number of the identifiers of the packing lines of the target environment image are obtained based on the packing characteristic labeling model, so as to determine that the state of the packing lines of the target packing station is a disordered state, and determine that the feeding state of the packing machine of the packing station is a feeding abnormal state based on the disordered state of the packing lines. And determining the position information of each baling line based on the baling line identification, analyzing the position information of the plurality of baling lines to obtain that the baling lines are independent and have no cross, and judging that the baling lines at the baling station are not wound, namely the abnormal feeding state of the baling machine is the missing state of the baling lines.

Fig. 4 is a block diagram of a wrapping wire mess alarm device according to an exemplary embodiment of the present application. The device can be applied to the implementation environment shown in fig. 1 and is specifically configured in the intelligent terminal 102. The apparatus may also be applied to other exemplary implementation environments and be specifically configured in other devices, and this embodiment does not limit the implementation environment to which the apparatus is applied.

As shown in fig. 4, the exemplary apparatus for alarming for wire jumbling of a covered wire includes: an image acquisition module 410, an identification determination module 420, a status determination module 430, and an alarm module 440.

The image acquisition module 410 is used for acquiring a target environment image of a target packaging station; the identification determining module 420 is configured to input the target environment image to the packing feature labeling model to obtain a packing line identification and a packing station flag bit identification; the state determining module 430 is configured to determine a packing line state of the target packing station based on the number of the packing line identifiers and the number of the packing station identifier; and the alarm module 440 is used for sending alarm information when the packing wire state of the target packing station is a disordered wire state.

It should be noted that the wrapping wire disorder alarm device provided in the foregoing embodiment and the wrapping wire disorder alarm method provided in the foregoing embodiment belong to the same concept, and specific manners of operations executed by each module and unit have been described in detail in the method embodiment, and are not described herein again. In practical applications, the packet wire disorder alarm device provided in the above embodiment may distribute the above functions through different function modules as required, that is, divide the internal structure of the device into different function modules to complete all or part of the above described functions, which is not limited herein.

An embodiment of the present application further provides an electronic device, including: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by one or more processors, the electronic equipment is enabled to realize the method for alarming out of the wire by the bundling wire provided by the above embodiments.

FIG. 5 illustrates a schematic structural diagram of a computer system suitable for use to implement the electronic device of the embodiments of the subject application. It should be noted that the computer system 500 of the electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and applicable scope of the embodiments of the present application.

As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes, such as executing the methods in the above-described embodiments, according to a program stored in a Read-Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for system operation are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An Input/Output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output section 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.

In particular, according to embodiments of the present application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. When the computer program is executed by the Central Processing Unit (CPU) 801, various functions defined in the system of the present application are executed.

It should be noted that the computer readable media shown in the embodiments of the present application may be computer readable signal media or computer readable storage media or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may comprise a propagated data signal with a computer-readable computer program embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

Another aspect of the present application also provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor of a computer, causes the computer to execute the foregoing method for alarming out-of-order wire for a covered wire. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist alone without being assembled into the electronic device.

Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for alarming out of the wire-wrapping disorder provided in the above embodiments.

The foregoing embodiments are merely illustrative of the principles of the present invention and its efficacy, and are not to be construed as limiting the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims (11)

1. A method for alarming the disorder of a packing wire is characterized by comprising the following steps:

acquiring a target environment image of a target packing station;

inputting the target environment image into a packing characteristic labeling model to obtain a packing line identifier and a packing station marker identifier, wherein the training mode of the packing characteristic labeling model comprises the steps of obtaining an initial environment image of the target packing station, and the initial environment image comprises a red, green and blue three-primary-color channel; converting the three primary color channels of red, green and blue into each other, wherein the conversion comprises interchanging the brightness value of the red color channel with the brightness value of the blue color channel to generate a conversion environment image; determining the initial environment image and the conversion environment image as sample images, and labeling the characteristic of a packing line and the characteristic of a packing station marker bit in the sample images to generate a sample data set; training an initial labeling model based on the sample data set, and determining the trained initial labeling model as a packing characteristic labeling model;

determining the packing wire state of the target packing station based on the number of the packing wire identifications and the number of the packing station mark identifications;

and when the packing wire state of the target packing station is a wire disordering state, sending alarm information.

2. The method for alarming when the wire is jumbled by the packing wire according to claim 1, wherein in the training process of the feature labeling model, the obtaining of the initial environment image of the target packing station further comprises:

determining a region of interest of an initial environment image based on the initial environment image of the target packing station;

and determining a region outside the region of interest in the initial environment image as a region of non-interest, and filtering the region of non-interest.

3. The method for alarming of the disordered wire of the packing wire according to the claim 1, wherein the step of labeling the packing wire characteristic and the packing station flag bit characteristic in the sample image comprises the following steps:

carrying out rotary labeling on the characteristic of a packing line and the characteristic of a packing station mark bit in the sample image through a rectangular frame, wherein the rectangular frame comprises a non-standard rectangular frame;

correcting the non-standard rectangular frame into a standard rectangular frame through a minimum circumscribed rectangle;

eliminating abnormal angle loss values at the boundary based on an annular smooth label method to obtain an angle prediction result of the packing feature labeling model;

and detecting the packing line and the packing station zone bit with rotation attributes in a preset angle range based on the angle prediction result to obtain a packing line characteristic marking frame and a packing station zone bit characteristic marking frame.

4. The method for alarming when the wire is disordered according to any one of claims 1 to 3, wherein after determining the state of the wrapping wire of the target wrapping station based on the number of the wrapping wire identifiers and the number of the wrapping station identifiers, the method further comprises:

if the packing wire state of the target packing station is a disordered wire state, judging that the feeding state of the packing machine is abnormal, wherein the abnormal feeding state of the feeding machine comprises a missing packing wire state and a winding packing wire state;

the baling press set up in target packing station to utilize the baling line packing product, the packing station marker bit set up in the baling press or target packing station.

5. The baling line messy line alarm method according to claim 4, wherein determining that the feeding state of the baling machine is abnormal comprises:

determining the position of each wrapping wire based on the wrapping wire identification, and if the positions of at least two wrapping wires are crossed, judging that the abnormal feeding state is the wrapping wire winding state;

and if the positions of any packing lines are not crossed, judging that the feeding abnormal state is a packing line missing state.

6. The method for alarming the disordered wire of the packing line according to any one of claims 1 to 3, wherein the step of inputting the target environment image into the packing feature labeling model to obtain a packing station identifier and a packing station flag identifier comprises the steps of:

inputting the target environment image into the packing characteristic marking model, and identifying the characteristic of the marking bit of the packing station and the characteristic of the packing line in the target environment image to obtain a marking frame of the packing line and a marking frame of the marking bit of the packing station;

and determining the packing wire marking frame as a packing wire identifier, and determining the packing station mark bit marking frame as a packing station mark bit identifier.

7. The method for alarming when the wire is disordered according to any one of claims 1 to 3, wherein the step of determining the state of the wire to be wrapped of the target wrapping station based on the number of the wire to be wrapped of the wrapping wire identifier and the number of the station to be wrapped of the wrapping station identifier comprises the steps of:

determining the number of the packing line identifications and the number of the packing station mark identifications on the basis of the packing line identifications and the packing station mark identifications;

if the number of the packing line identifications is equal to the number of the packing station mark bit identifications, judging that the packing line state of the target packing station is a normal state;

and if the number of the wrapping line identifications is smaller than that of the wrapping station mark position identifications, judging that the wrapping line state of the target wrapping station is a disordered line state.

8. The method for alarming when the wire is tangled according to any one of claims 1 to 3, wherein sending alarm information based on the tangle state comprises:

acquiring an environment image of a plurality of frames of the target station, and detecting the wrapping line state of the plurality of frames of the target station;

when the wrapping state of the multiple frames of the target stations is detected to be a messy state, determining the messy frame number of the multiple frames of the target stations, wherein the wrapping state of the multiple frames of the target stations is the messy state;

and if the random line frame number is greater than or equal to a preset safety frame number threshold, sending alarm information.

9. The utility model provides a baling line mess line alarm device which characterized in that includes:

the image acquisition module is used for acquiring a target environment image of a target packing station;

the identification determining module is used for inputting the target environment image into the packing characteristic labeling model to obtain a packing line identification and a packing station mark bit identification;

the state determining module is used for determining the packing line state of the target packing station based on the number of the packing line identifications and the number of the packing station mark identifications;

and the alarm module is used for sending alarm information when the packing wire state of the target packing station is a wire disordering state.

10. An electronic device, characterized in that the electronic device comprises:

one or more processors;

storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the method of any of claims 1-8.

11. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to execute the method for making a covered wire miswire alarm according to any one of claims 1 to 8.

Images