CN114155676A - Logistics system damaged wood pallet detection alarm system and working method thereof - Google Patents
Logistics system damaged wood pallet detection alarm system and working method thereof Download PDFInfo
- Publication number
- CN114155676A CN114155676A CN202111430869.6A CN202111430869A CN114155676A CN 114155676 A CN114155676 A CN 114155676A CN 202111430869 A CN202111430869 A CN 202111430869A CN 114155676 A CN114155676 A CN 114155676A
- Authority
- CN
- China
- Prior art keywords
- tray
- wood
- detection
- layer
- personal computer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B5/00—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied
- G08B5/22—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied using electric transmission; using electromagnetic transmission
- G08B5/36—Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied using electric transmission; using electromagnetic transmission using visible light sources
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Electromagnetism (AREA)
- Pallets (AREA)
Abstract
The invention provides a logistics system damaged wooden tray detection alarm system and a working method thereof, belonging to the technical field of logistics tray detection, the system comprises a conveying mechanism, a detection mechanism and a main control mechanism, the conveying mechanism comprises a code divider, a transmission belt and a rejecting machine, the detection mechanism comprises a board upper side detection module, a board lower side detection module, a micro control module and an alarm module, the board upper side detection module comprises a position sensor, an industrial camera, an image preprocessing unit and a recognition unit, the position sensor is arranged on one side of the transmission belt, the industrial camera is arranged on a portal frame, the board lower side detection module comprises an infrared sensor, the main control mechanism comprises an industrial personal computer and a PLC (programmable logic controller), the system mainly detects and alarms the condition that the board on the upper side of the wooden tray is missing and the board on the lower side is not firm, the damaged wooden tray is prevented from entering a production process, and damage to equipment and products caused by the damaged wooden tray is reduced.
Description
Technical Field
The invention belongs to the technical field of logistics tray detection, and particularly relates to a logistics system damaged wood tray detection alarm system and a working method thereof.
Background
Wooden pallet can load more than 500kg in the pile up neatly of goods, transport and the storage process in a flexible way, has brought very big facility for the enterprise. However, due to the increase of the number of times of using the wooden pallet and the influence of the using environment, a certain number of damaged wooden pallets exist in the logistics system, and the damaged wooden pallets are difficult to distinguish by workers among a large number of pallets. Most enterprise's logistics system is automatic production line at present, and the tray of disappearance plank will lead to manipulator pile up neatly trouble of falling a pile in case the entering system, and the tray of crossbeam damage will lead to conveying fault and stacker to get and put goods trouble etc. to cause great equipment and product to damage.
Disclosure of Invention
The embodiment of the invention provides a logistics system damaged wood pallet detection alarm system and a working method thereof, which mainly detect and alarm the problem that a wood board on the upper side of a wooden pallet is missing and is not firmly fixed with a wood board on the lower side of the wooden pallet, avoid the damaged wood pallet from entering a production process, and reduce the damage of equipment and products caused by the damaged wood pallet.
In view of the above problems, the technical solution proposed by the present invention is:
a logistics system damaged wooden tray detection alarm system comprises a conveying mechanism, a detection mechanism and a main control mechanism, wherein the conveying mechanism comprises a code extension machine, a transmission belt and an eliminating machine, a jacking machine is arranged at the bottom of the inner side of the code extension machine, a portal frame is arranged at the top of the code extension machine, four groups of shifting forks are symmetrically arranged on the inner side of the code extension machine, the positions of the shifting forks correspond to fork holes of wooden trays, the transmission belt is arranged on one side of the code extension machine, the eliminating machine comprises an electric telescopic cylinder and an eliminating platform, the eliminating platform and the electric telescopic cylinder are respectively arranged on two sides of the transmission belt, the detection mechanism comprises a wooden upper side detection module, a wooden lower side detection module, a micro control module and an alarm module, the wooden upper side detection module comprises a position sensor, an industrial camera, an image preprocessing unit and an identification unit, the position sensor is arranged on one side of the transmission belt, the industrial camera set up in on the portal frame, plank downside detection module includes infrared sensor, infrared sensor is provided with two sets ofly, and respectively the symmetry set up in the inboard of sign indicating number extension, position sensor industrial camera with infrared sensor all with little control module electric connection, alarm module with little control module electric connection, main control mechanism includes industrial computer and PLC controller, the industrial computer with PLC controller electric connection, little control module with industrial computer electric connection, conveying mechanism with PLC controller electric connection.
As a preferable technical scheme of the invention, a rotating shaft is arranged at the center of the shifting fork, a servo motor is arranged at one end of the rotating shaft, and the output end of the servo motor is fixedly connected with the rotating shaft.
As a preferred technical scheme of the invention, two groups of electric telescopic cylinders are symmetrically arranged, one side of each electric telescopic cylinder is provided with a fixed seat, the output end of each electric telescopic cylinder penetrates through the fixed seat and is provided with a push plate, the overall dimension of each push plate is matched with the side dimension of a wood tray, the rejection table corresponds to the position of each push plate and is used for placing the damaged wood tray, one side of the rejection table is provided with a photoelectric sensor, and the photoelectric sensors are electrically connected with the alarm module.
As a preferred technical solution of the present invention, the identification unit uses a convolutional neural network, and includes an input layer, three convolutional layers, and a fully connected layer, the input layer inputs a single-channel image of 384 × 280 × 1 (height × width × number of color channels), the convolutional layer of the first layer uses 3 × 3 convolutional kernels of 8 channels 1, the convolution step is 1, the number of filling layers is 0, and the convolutional layer of the second layer uses 3 × 3 convolutional kernels of 16 channels 1, the convolution step is 1, the number of filling layers is 0, and the convolutional layer of the third layer uses 3 × 3 convolutional kernels of 16 channels 1, the convolution step is 1, the number of filling layers is 0, and the fully connected layer outputs the identification result to the micro control module.
As a preferred technical scheme of the invention, one side of the rejecting table is provided with an alarm lamp, and the alarm lamp is electrically connected with the alarm module.
As a preferable technical scheme of the invention, the industrial personal computer is provided with a network interface, a USB video interface, a driver and a serial communication interface, and the win32 recognition driver in the industrial personal computer is in real-time communication connection with the PLC through an open source program library Snap 7.
As a preferable technical scheme of the invention, the infrared sensor is obliquely arranged corresponding to the position of the cross beam at the bottom of the wooden pallet, and the infrared sensor adopts an infrared mirror reflection sensor.
As a preferred technical solution of the present invention, the image preprocessing unit is configured to intercept a specific area of an image to generate new image data, and perform graying processing.
On the other hand, the working method for detecting and alarming the damaged wooden pallet of the logistics system comprises the following steps:
s1, splitting the tray set, placing the stacked tray set in a code division machine, controlling four groups of shifting forks to be recovered by a servo motor, starting a jacking machine to lift the whole tray set, when the set height is reached, starting the servo motor to extend the shifting forks and clamp the shifting forks into fork holes of a second tray at the bottom layer, and continuously descending the jacking machine to a position which is level with a conveying belt to wait for conveying signals;
s2, detecting the lower side of the wood board, after the step S1, forming a gap between the second tray at the bottom layer and the tray at the bottom layer, wherein at the moment, two groups of infrared sensors send out detection signals, when the signals are shielded and cannot be reflected by a mirror surface, the situation that a cross beam at the lower side of the second tray at the bottom layer has a droop field is shown, the infrared sensors transmit the signals to an industrial personal computer through a micro control module, the industrial personal computer receives the signals and judges that the tray is a bad tray, and when the detection signals of the infrared sensors are not shielded, the signals are transmitted to the industrial personal computer to judge that the tray is good;
s3, detecting the upper side of the wood board, when the PLC outputs a wood tray conveying signal to the conveying belt, the conveying belt takes out the wood tray which is in place, when the position sensor detects a wood tray position signal on the conveying belt, the industrial personal computer controls the industrial camera to start to work, image information of the upper side of the wood tray at the current position is collected, then the image information is intercepted in size and subjected to gray processing by the image preprocessing unit and then is input to the identification unit, the size and the gray processing are compared with a tray image in the model base through the convolutional neural network for identification, and an identification result is transmitted to the industrial personal computer;
s4, alarming is rejected to the tray, and the industrial computer writes in the PLC controller with received good tray or bad tray signal through communication program, and the PLC controller starts according to bad tray signal control electronic telescoping cylinder, will damage the tray and release to rejecting the platform and keep in, controls the alarm lamp simultaneously and lights, and the suggestion staff in time removes and rejects the damaged wooden tray on the platform, and the good tray that detects out then relies on the transmission band to carry to appointed operation region.
Compared with the prior art, the invention has the beneficial effects that: whether the upper side and the lower side of the wooden tray are abnormal or not can be accurately judged, through recognition and alarming, personnel are informed to reject, the damaged tray can be effectively prevented from entering an actual production process, the equipment damage and the product damage caused by the tray are reduced, the service lives of equipment and spare parts are prolonged, and the product conveying consumption is reduced.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
FIG. 1 is a schematic structural diagram of a damaged wooden pallet detection alarm system of a logistics system disclosed by the invention;
FIG. 2 is an enlarged view at A in FIG. 1;
FIG. 3 is a schematic structural diagram of a damaged wooden pallet detection alarm system of a logistics system according to the present invention;
FIG. 4 is a communication connection block diagram of a logistics system damaged wooden pallet detection alarm system disclosed by the invention;
FIG. 5 is a model diagram of a recognition unit disclosed in the present invention;
FIG. 6 is a graph of a training loss function variation for the disclosed recognition unit;
FIG. 7 is a schematic flow chart of a working method of a damaged wooden pallet detection alarm of a logistics system disclosed by the invention;
description of reference numerals: 100-a conveying mechanism; 101-code extension; 1011-jack; 1012-a portal frame; 1013-a shifting fork; 1014-a rotating shaft; 1015-servo motor; 102-a conveyor belt; 103-a rejecting machine; 1031-an electric telescopic cylinder; 1032-a culling station; 1033-fixed seat; 1034-push plate; 1035-photosensor; 1036-warning light; 200-a detection mechanism; 201-detecting module on upper side of wood board; 2011-position sensor; 2012-industrial camera; 2013-an image preprocessing unit; 2014-an identification unit; 20141-input layer; 20142-convolutional layer; 20143-full link layer; 202-a wood board underside detection module; 2021-infrared sensor; 203-a micro control module; 204-an alarm module; 300-a master control mechanism; 301-industrial personal computer; 302-PLC controller.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the equipment or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Example one
Referring to the attached drawings 1-6, the invention provides a technical scheme: a logistics system damaged wooden tray detection alarm system comprises a conveying mechanism 100, a detection mechanism 200 and a main control mechanism 300.
Referring to fig. 1-4, a conveying mechanism 100 includes a stacking machine 101, a conveying belt 102 and a rejecting machine 103, the bottom of the inner side of the stacking machine 101 is provided with a lifting machine 1011, the top of the stacking machine 101 is provided with a portal frame 1012, the inner side of the stacking machine 101 is symmetrically provided with four groups of shifting forks 1013, the positions of the shifting forks 1013 correspond to fork holes of wood pallets, the stacking machine 101 is used for splitting the whole stack of wood pallets and belongs to a source in a logistics system, the wood pallets are separated individually according to work tasks, the logistics system is convenient for use in the flow operation, the conveying belt 102 is arranged at one side of the stacking machine 101, the conveying belt 102 is used for conveying the well-split wood pallets to a logistics operation area, the degree of automation is improved, the rejecting machine 103 includes an electric telescopic cylinder 1031 and a rejecting table 1032, the rejecting table 1032 and the electric telescopic cylinder 1031 are respectively arranged at two sides of the conveying belt 102, the rejecting machine 103 is used for rejecting damaged pallets in the stack of wood pallets out of the logistics system, the damaged tray is prevented from entering the operation production process.
Referring to fig. 1-6, the detecting mechanism 200 includes a board upper side detecting module 201, a board lower side detecting module 202, a micro-control module 203 and an alarm module 204, the board upper side detecting module 201 includes a position sensor 2011, an industrial camera 2012, an image preprocessing unit 2013 and an identification unit 2014, the position sensor 2011 is disposed on one side of the conveyor belt 102, the industrial camera 2012 is disposed on the gantry 1012, the board upper side detecting module 201 determines the absence of the surface of the board through collecting tray image information by CNN model identification, the board lower side detecting module 202 includes an infrared sensor 2021, the infrared sensors 2021 are disposed in two groups and are respectively and symmetrically disposed on the inner side of the code divider 101, the board lower side detecting module 202 logically determines the sagging of the beam on the lower side of the board tray through the signal of the infrared sensor 2021, and the position sensor 2011, the industrial camera 2012 and the infrared sensor 2021 are electrically connected to the micro-control module 203, the alarm module 204 is electrically connected with the micro control module 203, and the collected signals are transmitted to the micro control module 203 for collection and conversion, and are waited to be transmitted to the main control mechanism 300.
Referring to fig. 4, the master control mechanism 300 includes an industrial personal computer 301 and a PLC controller 302, the industrial personal computer 301 is electrically connected to the PLC controller 302, the micro control module 203 is electrically connected to the industrial personal computer 301, the conveying mechanism 100 is electrically connected to the PLC controller 302, the industrial personal computer 301 is configured with a network interface, a USB video interface, a driver and a serial communication interface, a win32 recognition driver in the industrial personal computer 301 is connected to the PLC controller 302 through an open source library Snap7 in a real-time communication manner, after a tray is recognized to be in place, the API control industrial camera 2012 is used for image acquisition, the recognition program preprocesses acquired images by calling OpenCV, inputs the processed images into a trained bad tray recognition model library for comparison, and finally writes the result into the PLC controller 302 of the electronic control device through the communication program.
The embodiment of the invention is also realized by the following technical scheme.
In the embodiment of the invention, a rotating shaft 1014 is arranged at the center of the shift fork 1013, a servo motor 1015 is arranged at one end of the rotating shaft 1014, the output end of the servo motor 1015 is fixedly connected with the rotating shaft 1014, and the servo motor 1015 controls the extension and retraction of the shift fork 1013 through a control signal of the PLC controller 302, so as to prevent the lifting jack 1011 from generating motion interference when lifting and detaching the tray group.
In the embodiment of the present invention, two sets of electric telescopic cylinders 1031 are symmetrically arranged, one side of each electric telescopic cylinder is provided with a fixed seat 1033, an output end of each electric telescopic cylinder 1031 penetrates through the fixed seat 1033 and is provided with a push plate 1034, the external dimension of each push plate 1034 is matched with the dimension of the side edge of a wood pallet, a rejection table 1032 corresponds to the position of the push plate 1034, the rejection table 1032 is used for placing a damaged wood pallet, one side of the rejection table 1032 is provided with a photoelectric sensor 1035, the photoelectric sensor 1035 is electrically connected with the alarm module 204, one side of the rejection table 1032 is provided with an alarm lamp 1036, the alarm lamp 1036 is electrically connected with the alarm module 204, when the detection mechanism 200 detects that the damaged wood pallet is, the PLC controller 302 controls the electric telescopic cylinders 1031 to work, push the detected pallet out of the conveying belt 102 and temporarily stores the detected pallet on the rejection table 1032, and when the photoelectric sensor 1035 detects the pallet, the alarm lamp 1036 is turned on by the alarm module 204, prompting staff to remove the damaged wood tray on the rejecting platform 1032 in time to prevent influencing subsequent detection processes.
Referring to fig. 5, in an embodiment of the present invention, the identification unit 2014 employs a convolutional neural network including one input layer 20141, three convolutional layers 20142, and one full-connected layer 20143, the input layer 20141 inputs a single-channel image of 384 × 280 × 1 (height × width × number of color channels), the first layer convolutional layer 20142 employs 3 × 3 convolution kernels of 8 channels of 1, the convolution step is 1, the number of filling layers is 0, the convolution is performed twice, the activation is performed by the ReLu function, and the down-sampling is performed by the maximum pooling, wherein the filter size of the pooling layer is 2 × 2, the step is 2, so that after the first layer convolutional layer 20142, the image size is halved, the output size is 192 × 140 8, the second layer convolutional layer 20142 employs 3 convolution kernels of 16 channels of 1, the step is 1, the number of filling layers is 0, the convolution is performed twice, the down-sampling is performed by the ReLu function, the filter size of the pooling layer is 2 x 2, the step size is 2, the image output size is 97 x 70 x 16, the third layer convolution layer 20142 uses a 3 x 3 convolution kernel with 16 channels being 1, the convolution step size is 1, the number of filling layers is 0, the convolution is performed once, the activation is performed by the ReLu function, the downsampling is performed by using the maximum pooling, the parameters of the pooling layer are the same twice, the image output size is 48 x 35 16, then the data is flattened into vectors 26880 by the Flatten () and finally the recognition result is output to the micro control module 203 through a 1 x 2 fully connected layer 20143.
After the model is constructed, a large number of pictures need to be trained to adjust parameters of a convolution kernel and a pooling filter, so that a loss function of the model can be taken to the lowest value in a back propagation mode, namely the model judgment accuracy is highest. In this embodiment, a total of 5090 pictures of 2524 good trays and 2566 bad trays are used to train the model, as shown in fig. 6, in the training process, the loss function is reduced in a gradient descending manner, after 4000 pictures are trained, the model has an overfitting phenomenon, the loss function rises to some extent, and then the model training is stopped immediately, at this time, the value of the loss function is the lowest, and is 0.01.
In the embodiment of the invention, the infrared sensor 2021 corresponds to the position of a cross beam at the bottom of the wood pallet and is obliquely arranged, the infrared sensor 2021 adopts an infrared mirror reflection sensor, the industrial personal computer 301 adopts an RS-232 standard to collect a signal of the infrared sensor 2021, the micro control module 203 under the Arduino platform is used for realizing data butt joint with the industrial personal computer 301, the communication with an upper computer is realized through serial communication of an MCU (microprogrammed control unit) in the micro control module 203, and the upper computer judges the state of the infrared sensor 2021 through a logic judgment program written by C + + and outputs a pallet quality judgment result to the field equipment PLC 302.
In an embodiment of the present invention, the image preprocessing unit 2013 is configured to intercept new image data from a specific area of an image, perform graying processing, and prevent the influence of different periods of time illumination and the color depth of the pallet wood on the accuracy of the identification unit.
Example two
Referring to fig. 6, another working method for detecting and alarming a damaged wooden pallet of a logistics system according to an embodiment of the present invention includes the following steps:
s1, splitting the tray set, placing the stacked tray set in the code division machine 101, controlling four groups of shifting forks 1013 to be recovered by a servo motor 1015, starting a jacking machine 1011 to lift the whole tray set, when the set height is reached, starting the servo motor 1015 to extend the shifting forks 1013 and clamp the shifting forks 1013 in fork holes of a second tray at the bottom layer, and continuously descending the jacking machine 1011 to a position flush with the conveying belt 102 to wait for conveying signals;
s2, detecting the lower side of the wood board, after the step S1, forming a gap between the second tray at the bottom layer and the tray at the bottom layer, wherein two groups of infrared sensors 2021 send out detection signals, when the signals are blocked and cannot be reflected by a mirror surface, the situation that a cross beam at the lower side of the second tray at the bottom layer has a droop field is shown, the infrared sensors 2021 transmit the signals to the industrial personal computer 301 through the micro control module 203, the industrial personal computer 301 receives the signals and judges that the tray is a bad tray, and when the detection signals of the infrared sensors 2021 are not blocked, the signals are transmitted to the industrial personal computer 301 and judged as a good tray;
s3, detecting the upper side of the wood board, when the PLC 302 outputs a wood tray conveying signal to the conveying belt 102, the conveying belt 102 takes out the wood tray which is in place, when the position sensor 2011 detects a wood tray position signal on the conveying belt 102, the industrial personal computer 301 controls the industrial camera 2012 to start to work, collects image information of the upper side of the wood tray at the current position, then intercepts the image information through the image preprocessing unit 2013, inputs the image information to the identification unit 2014 after the size and the graying processing are carried out, compares the image information with a tray image in the model base through a convolutional neural network for identification, and transmits an identification result to the industrial personal computer 301;
s4, a pallet rejecting alarm is carried out, an industrial personal computer 301 writes received good pallets or bad pallet signals into a PLC 302 through a communication program, the PLC 302 controls an electric telescopic cylinder 1031 to start according to the bad pallet signals, damaged pallets are pushed out to a rejecting platform 1032 to be temporarily stored, meanwhile, an alarm lamp 1036 is controlled to light up, a worker is prompted to timely remove the damaged wood pallets on the rejecting platform 1032, and the detected good pallets are conveyed to a designated operation area through a conveying belt 102.
According to the working method for detecting and alarming the damaged wooden tray of the logistics system, the damaged wooden tray is rejected to the outside of the working channel by detecting and alarming the missing of the front board of the single wooden tray and the drooping of the lower side beam after the tray group is split, and the sound-light alarm is utilized to prompt workers to remove the damaged wooden tray in time, so that the damaged wooden tray is prevented from entering the production process, and the damage to equipment and products caused by the damaged wooden tray is reduced.
It should be noted that the specific model specifications of the servo motor 1015, the electric telescopic cylinder 1031, the photoelectric sensor 1035, the alarm lamp 1036, the position sensor 2011, the industrial camera 2012, the infrared sensor 2021, the industrial personal computer 301 and the PLC controller 302 need to be determined by type selection according to the actual specification of the device, and the specific type selection calculation method adopts the prior art in the field, and therefore details are not described again.
It should be noted that the power supply and the principle of the servo motor 1015, the electric telescopic cylinder 1031, the photoelectric sensor 1035, the alarm lamp 1036, the position sensor 2011, the industrial camera 2012, the infrared sensor 2021, the industrial personal computer 301 and the PLC controller 302 are clear to those skilled in the art and will not be described in detail herein.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Of course, the processor and the storage medium may reside as discrete components in a user terminal.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in memory units and executed by processors. The memory unit may be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
Claims (9)
1. The utility model provides a damaged wooden tray of logistics system detects alarm system which characterized in that includes:
the conveying mechanism comprises a stacking machine, a conveying belt and an rejecting machine, wherein a jacking machine is arranged at the bottom of the inner side of the stacking machine, a portal frame is arranged at the top of the stacking machine, four groups of shifting forks are symmetrically arranged on the inner side of the stacking machine, the positions of the shifting forks correspond to fork holes of wood trays, the conveying belt is arranged on one side of the stacking machine, the rejecting machine comprises an electric telescopic cylinder and a rejecting table, and the rejecting table and the electric telescopic cylinder are respectively arranged on two sides of the conveying belt;
the detection mechanism comprises a board upper side detection module, a board lower side detection module, a micro control module and an alarm module, wherein the board upper side detection module comprises position sensors, industrial cameras, an image preprocessing unit and an identification unit, the position sensors are arranged on one side of the conveying belt, the industrial cameras are arranged on the portal frame, the board lower side detection module comprises infrared sensors, the infrared sensors are arranged in two groups and are symmetrically arranged on the inner sides of the code divider respectively, the position sensors, the industrial cameras and the infrared sensors are all electrically connected with the micro control module, and the alarm module is electrically connected with the micro control module;
the main control mechanism comprises an industrial personal computer and a PLC (programmable logic controller), the industrial personal computer is electrically connected with the PLC, the micro control module is electrically connected with the industrial personal computer, and the conveying mechanism is electrically connected with the PLC.
2. The wood pallet breakage detection and alarm system of claim 1, wherein a rotating shaft is arranged at the center of the shifting fork, a servo motor is arranged at one end of the rotating shaft, and the output end of the servo motor is fixedly connected with the rotating shaft.
3. The logistics system damaged wood tray detection and alarm system as claimed in claim 1, wherein the electric telescopic cylinder is symmetrically provided with two groups, a fixing seat is arranged on one side of the electric telescopic cylinder, a push plate is arranged after an output end of the electric telescopic cylinder penetrates through the fixing seat, the outer dimension of the push plate is matched with the side dimension of the wood tray, the removing table corresponds to the position of the push plate and is used for placing the damaged wood tray, a photoelectric sensor is arranged on one side of the removing table and is electrically connected with the alarm module.
4. The logistics system damaged wooden tray detection alarm system according to claim 1, wherein the identification unit adopts a convolutional neural network, and comprises an input layer, three convolutional layers and a fully connected layer, wherein the input layer inputs 384 x 280 x 1 (height x width x color channel number) single-channel images, the convolutional layer in the first layer adopts 3 x 3 convolutional kernels with 8 channels being 1, the convolutional step is 1, the number of filling layers is 0, the convolutional layer is twice, the convolutional layer in the second layer adopts 3 x 3 convolutional kernels with 16 channels being 1, the convolutional step is 1, the number of filling layers is 0, the convolutional layer in the third layer adopts 3 x 3 convolutional kernels with 16 channels being 1, the convolutional step is 1, the filling layer is 0, the convolutional layer is once, and the fully connected layer outputs the identification result to the micro control module.
5. The logistics system damaged wooden tray detection alarm system as claimed in claim 1, wherein an alarm lamp is arranged on one side of the rejection table, and the alarm lamp is electrically connected with the alarm module.
6. The system for detecting and alarming the damaged wooden pallet in the logistics system as claimed in claim 1, wherein the industrial personal computer is configured with a network interface, a USB video interface, a driver and a serial communication interface, and the win32 recognition driver in the industrial personal computer is in real-time communication connection with the PLC through a source-opening library Snap 7.
7. The wood pallet breakage detection and alarm system of claim 1, wherein the infrared sensor is obliquely arranged corresponding to the position of the cross beam at the bottom of the wood pallet, and the infrared sensor is an infrared mirror reflection sensor.
8. The system for detecting and alarming damaged wooden trays in logistics systems as claimed in claim 1, wherein the image preprocessing unit is configured to intercept specific areas of images to generate new image data and perform graying processing.
9. A working method for detecting and alarming a damaged wooden pallet of a logistics system is applied to the detection and alarming system for the damaged wooden pallet of the logistics system, which is characterized by comprising the following steps of:
s1, splitting the tray set, placing the stacked tray set in a code division machine, controlling four groups of shifting forks to be recovered by a servo motor, starting a jacking machine to lift the whole tray set, when the set height is reached, starting the servo motor to extend the shifting forks and clamp the shifting forks into fork holes of a second tray at the bottom layer, and continuously descending the jacking machine to a position which is level with a conveying belt to wait for conveying signals;
s2, detecting the lower side of the wood board, after the step S1, forming a gap between the second tray at the bottom layer and the tray at the bottom layer, wherein at the moment, two groups of infrared sensors send out detection signals, when the signals are shielded and cannot be reflected by a mirror surface, the situation that a cross beam at the lower side of the second tray at the bottom layer has a droop field is shown, the infrared sensors transmit the signals to an industrial personal computer through a micro control module, the industrial personal computer receives the signals and judges that the tray is a bad tray, and when the detection signals of the infrared sensors are not shielded, the signals are transmitted to the industrial personal computer to judge that the tray is good;
s3, detecting the upper side of the wood board, when the PLC outputs a wood tray conveying signal to the conveying belt, the conveying belt takes out the wood tray which is in place, when the position sensor detects a wood tray position signal on the conveying belt, the industrial personal computer controls the industrial camera to start to work, image information of the upper side of the wood tray at the current position is collected, then the image information is intercepted in size and subjected to gray processing by the image preprocessing unit and then is input to the identification unit, the size and the gray processing are compared with a tray image in the model base through the convolutional neural network for identification, and an identification result is transmitted to the industrial personal computer;
s4, alarming is rejected to the tray, and the industrial computer writes in the PLC controller with received good tray or bad tray signal through communication program, and the PLC controller starts according to bad tray signal control electronic telescoping cylinder, will damage the tray and release to rejecting the platform and keep in, controls the alarm lamp simultaneously and lights, and the suggestion staff in time removes and rejects the damaged wooden tray on the platform, and the good tray that detects out then relies on the transmission band to carry to appointed operation region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111430869.6A CN114155676A (en) | 2021-11-29 | 2021-11-29 | Logistics system damaged wood pallet detection alarm system and working method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111430869.6A CN114155676A (en) | 2021-11-29 | 2021-11-29 | Logistics system damaged wood pallet detection alarm system and working method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114155676A true CN114155676A (en) | 2022-03-08 |
Family
ID=80784119
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111430869.6A Pending CN114155676A (en) | 2021-11-29 | 2021-11-29 | Logistics system damaged wood pallet detection alarm system and working method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114155676A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114669489A (en) * | 2022-03-23 | 2022-06-28 | 烟台聚通智能设备有限公司 | Novel tray sorting and detecting mechanism |
| CN115507754A (en) * | 2022-10-14 | 2022-12-23 | 安徽黄山恒久链传动有限公司 | Dimension measuring program suitable for detecting multi-model chains |
| WO2024170530A1 (en) * | 2023-02-16 | 2024-08-22 | Haver & Boecker Ohg | Load carrier control apparatus, operating method and use |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107323767A (en) * | 2017-07-31 | 2017-11-07 | 深圳市欧视达自动化设备有限公司 | A kind of chewing gum packing detecting system and detection method |
| CN209231230U (en) * | 2018-12-12 | 2019-08-09 | 陕西中烟工业有限责任公司 | Tobacco factory's warehouse for finished product pallet based on computer vision technique detects warning device |
| CN209525280U (en) * | 2019-02-25 | 2019-10-22 | 芜湖天宇科技开发有限公司 | A kind of pallet damage monitoring system |
| WO2021000404A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Target detection method based on deep learning, and electronic apparatus |
| CN113333329A (en) * | 2021-08-04 | 2021-09-03 | 南京创智出彩科技有限公司 | Cigarette defect detection system based on deep learning |
-
2021
- 2021-11-29 CN CN202111430869.6A patent/CN114155676A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107323767A (en) * | 2017-07-31 | 2017-11-07 | 深圳市欧视达自动化设备有限公司 | A kind of chewing gum packing detecting system and detection method |
| CN209231230U (en) * | 2018-12-12 | 2019-08-09 | 陕西中烟工业有限责任公司 | Tobacco factory's warehouse for finished product pallet based on computer vision technique detects warning device |
| CN209525280U (en) * | 2019-02-25 | 2019-10-22 | 芜湖天宇科技开发有限公司 | A kind of pallet damage monitoring system |
| WO2021000404A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Target detection method based on deep learning, and electronic apparatus |
| CN113333329A (en) * | 2021-08-04 | 2021-09-03 | 南京创智出彩科技有限公司 | Cigarette defect detection system based on deep learning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114669489A (en) * | 2022-03-23 | 2022-06-28 | 烟台聚通智能设备有限公司 | Novel tray sorting and detecting mechanism |
| CN115507754A (en) * | 2022-10-14 | 2022-12-23 | 安徽黄山恒久链传动有限公司 | Dimension measuring program suitable for detecting multi-model chains |
| WO2024170530A1 (en) * | 2023-02-16 | 2024-08-22 | Haver & Boecker Ohg | Load carrier control apparatus, operating method and use |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114155676A (en) | Logistics system damaged wood pallet detection alarm system and working method thereof | |
| KR102461759B1 (en) | Intelligent Forklift and Container Position and Posture Deviation Detection Method | |
| CN103043359B (en) | Robot system, robot, and sorted article manufacturing method | |
| CN101710080B (en) | Stacking glass bottle detection method based on machine vision and transporter | |
| CN106066153A (en) | A kind of device detecting warehoused cargo size and weight | |
| CN216065399U (en) | Pressure riveting workstation with intelligent recognition function | |
| CA2725681A1 (en) | Sensor system for detecting the surface structures of several packaged articles | |
| CN111422630B (en) | Unstacking method of unstacking control device based on laser ranging guidance | |
| CN109465205B (en) | Dynamic sorting system and sorting method based on visual recognition technology | |
| EP3974124A1 (en) | Closed loop solution for loading/unloading cartons by truck unloader | |
| KR102473730B1 (en) | Courier sorting and conveying system | |
| CN111272766A (en) | Surface defect detection system based on vision technology and detection method thereof | |
| CN113428547A (en) | Goods-to-person holographic image sorting workstation and operation method | |
| CN112024462A (en) | Defective material removing equipment and control method and control device thereof | |
| CN211678817U (en) | Optical automatic product inspection machine | |
| CN116494227A (en) | Control system of polymorphic robot | |
| CN112793982B (en) | Stacker goods taking and placing system and application method thereof | |
| CN113703460B (en) | Method, device and system for identifying vacant position of navigation vehicle | |
| CN112551136B (en) | Portable timber selects separately pile up neatly system | |
| CN219383690U (en) | Goods placement system | |
| CN111620030B (en) | Automatic blanking method and system | |
| KR101834336B1 (en) | Material location recognition system using storage image monitoring and forklift truck | |
| CN215709064U (en) | Transfer device and warehousing system | |
| CN215157998U (en) | Feeding and discharging control system and detection assembly line | |
| CN114684522A (en) | Stacker and self-adaptive storage method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |