CN117592498A

CN117592498A - Vertical library inventory method based on RFID technology and deep learning vision technology

Info

Publication number: CN117592498A
Application number: CN202311615079.4A
Authority: CN
Inventors: 何春来; 孙嘉珺; 朴金生; 王卫军; 李子毅; 徐安宁; 惠泽
Original assignee: Potevio Logistics Technology Co ltd; China Electronics Technology Robot Co ltd
Current assignee: Potevio Logistics Technology Co ltd; China Electronics Technology Robot Co ltd
Priority date: 2023-11-29
Filing date: 2023-11-29
Publication date: 2024-02-23

Abstract

The invention provides a vertical library inventory method based on an RFID technology and a deep learning vision technology, which comprises the following steps: setting RFID labels for each cargo, and placing the cargoes with the RFID labels in a target warehouse; planning a moving route of the stacker, scanning RFID tags of all cargoes in a warehouse position when the stacker passes the warehouse position to be checked, and shooting characteristic surfaces of the cargoes; judging whether the goods are complete or not according to the shot characteristic surface information of the goods; combining the scanned RFID tag information of the goods with the shot characteristic surface information of the goods to judge the quantity of the goods; s6: the invention discloses a vertical warehouse inventory method based on an RFID technology and a deep learning vision technology, which is characterized in that the inventory method adopts a mode of combining the RFID technology and the vision technology, so that the defects of the inventory method are avoided, and the inventory efficiency is improved and the stability is higher.

Description

Vertical library inventory method based on RFID technology and deep learning vision technology

Technical Field

The invention relates to the technical field of warehouse systems, in particular to a vertical warehouse inventory method based on an RFID technology and a deep learning vision technology.

Background

The stereoscopic warehouse inventory technology is an important method in modern logistics warehouse management. The problems of low information degree, continuously increasing quantity of material types, rapidly increasing frequency of warehouse entering and exiting, large management loss, low warehouse operation efficiency caused by excessive manual operation, time and labor consumption of inventory operation and the like exist in the traditional warehouse management. Along with technological progress, RFID technology and vision technology are gradually applied to stereoscopic warehouse management scenes, so that the defects of traditional warehouse management are overcome, the operation cost of enterprises is reduced, and the economic benefit is improved. The conventional inventory method in the stereoscopic warehouse comprises an inventory method based on RFID technology and an inventory method based on vision technology.

The RFID-based inventory technology lacks timeliness, and inventory is only carried out on goods when the goods are delivered and put in storage, and the goods stacked in the vertical storage for a long time and a month can be lost and fall off due to various reasons; in order to completely shoot the characteristic information of the goods, the goods need to be taken out and checked and then put back into the warehouse based on the vision checking technology, which is not as efficient as RFID scanning labels.

Disclosure of Invention

The invention aims to provide a vertical library checking method based on an RFID technology and a deep learning vision technology, which improves checking efficiency.

In order to achieve the above object, the present invention provides the following technical solutions: a method for checking a vertical warehouse based on an RFID technology and a deep learning vision technology comprises the following steps: s1: setting RFID labels for each box of goods, putting the goods with the RFID labels into a target storage position, and recording the goods information in the target storage position; the step S1 includes: s11: placing the goods into a conveyor belt; s12: setting RFID labels for each cargo box through a marking machine; s13: stacking the goods in a stacking area to form a target stack shape and placing the goods on a tray; s14: conveying the trays to a target warehouse through a stacker; s15: recording cargo information stored in the target storage position; s2: planning a moving route of the stacker to enable the stacker to pass through all the warehouse positions to be checked; s3: when the stacker passes through the warehouse location which needs to be checked, scanning RFID labels of all cargoes in the warehouse location and shooting characteristic faces of the cargoes; s4: judging whether the goods are complete or not according to the shot characteristic surface information of the goods;

s5: combining the scanned RFID tag information of the goods with the shot characteristic surface information of the goods to judge the quantity of the goods; s6: comparing the quantity of the cargoes with the cargo information in the target library position recorded in the step S1; s7: removing the RFID tag on the goods and transporting the goods from which the RFID tag is removed to a sorting line, the step S7 including: s71: taking out the cargoes in the warehouse and conveying the cargoes to an unstacking area; s72: unpacking the goods in the unstacking area; s73: transporting the disassembled goods of the unstacking area to a conveyor belt; s74: removing RFID tags of the goods on the conveyor belt; s75: and recording cargo information on the conveyor belt and transporting the cargo on the conveyor belt to the sorting line.

Further, the device also comprises a wide-angle camera, and the characteristic surface of the goods is shot through the wide-angle camera.

Further, when the stacker moves along the moving route, the speed of the stacker does not exceed 160m/min.

Further, the system also comprises a marking machine, wherein the marking machine can set an RFID label for the goods.

Further, the warehouse management system is further included, and the warehouse management system can store the goods information in the target warehouse location and the goods information on the conveyor belt.

Further, the goods information comprises goods specifications of the goods and numbers of the goods.

Further, the automatic guide vehicle is further included, the trays are conveyed to the stacker through the automatic guide vehicle, and the trays are placed into a target warehouse through the stacker.

Analysis shows that the invention discloses a vertical warehouse inventory method based on an RFID technology and a deep learning vision technology, and the inventory method adopts a mode of combining the RFID technology and the vision technology, so that the defects of the RFID technology and the vision technology are avoided, the inventory efficiency is improved, and the stability is stronger.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. Wherein:

fig. 1 is a flow chart of a warehousing link according to an embodiment of the invention.

Fig. 2 is a flow chart of an inventory procedure according to an embodiment of the invention.

FIG. 3 is a flow chart of the outbound link according to an embodiment of the present invention.

Detailed Description

The invention will be described in detail below with reference to the drawings in connection with embodiments. The examples are provided by way of explanation of the invention and not limitation of the invention. Indeed, it will be apparent to those skilled in the art that modifications and variations can be made in the present invention without departing from the scope or spirit of the invention. For example, features illustrated or described as part of one embodiment can be used on another embodiment to yield still a further embodiment. Accordingly, it is intended that the present invention encompass such modifications and variations as fall within the scope of the appended claims and their equivalents.

In the description of the present invention, the terms "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", etc. refer to the orientation or positional relationship based on that shown in the drawings, merely for convenience of description of the present invention and do not require that the present invention must be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. The terms "coupled," "connected," and "configured" as used herein are to be construed broadly and may be, for example, fixedly connected or detachably connected; can be directly connected or indirectly connected through an intermediate component; either a wired electrical connection, a radio connection or a wireless communication signal connection, the specific meaning of which terms will be understood by those of ordinary skill in the art as the case may be.

One or more examples of the invention are illustrated in the accompanying drawings. The detailed description uses numerical and letter designations to refer to features in the drawings. Like or similar designations in the drawings and description have been used to refer to like or similar parts of the invention. As used herein, the terms "first," "second," "third," and "fourth," etc. are used interchangeably to distinguish one component from another and are not intended to represent the location or importance of the individual components.

As shown in fig. 1, according to an embodiment of the present invention, there is provided a method for inventory checking based on an RFID technology and a deep learning vision technology, comprising the steps of: s1: setting RFID labels for each cargo, placing the cargoes with the RFID labels in a target storage position, and recording cargo information in the target storage position; the step S1 comprises the following steps: s11: placing goods into the conveyor belt; s12: setting RFID labels for each cargo box through a marking machine; s13: stacking the goods into a target stack shape in a stacking area and placing the goods on a tray;

s14: conveying the trays to a target warehouse through a stacker; s15: recording the goods information stored in the target storage position, wherein the goods information in the storage position comprises the information of the tray and the goods information on the tray, and the step S1 is a storage process: after goods are unloaded from the trucks, the goods are transported to a stacking area through a conveying belt, a marking machine is arranged on site, an RFID label is attached to each box of goods, and the labels contain information such as goods gauge, number and the like. The RFID tag adopts a semi-active RFID, integrates the advantages of an active electronic tag and a passive electronic tag, does not work in a dormant state under most conditions, does not send RFID signals to the outside, and only when the RFID tag enters the activation signal range of the low-frequency activator, the RFID tag starts to work after being activated. After the labels are well attached, stacking is carried out, a high-sensitivity anti-interference passive RFID label is attached to a tray, and then goods warehouse entry is completed through the cooperation of an AGV (automatic guided vehicle) and a stacker. At the moment, scanned tray RFID information can be synchronously written into a warehouse management system WMS, so that the subsequent warehouse management needs are facilitated.

As shown in fig. 2, S2: planning a moving route of the stacker to enable the stacker to pass through all warehouse positions needing to be checked; s3: when the stacker passes through a warehouse site needing to be checked, RFID labels of all cargoes in the warehouse site are scanned, and characteristic surfaces of the cargoes are shot; s4: judging whether the goods are complete or not according to the shot characteristic surface information of the goods; s5: combining the scanned RFID tag information of the goods with the shot characteristic surface information of the goods to judge the quantity of the goods; s6: comparing the quantity of the cargoes with the information of the cargoes in the target library position recorded in the step S1; step S2-step S6 is the checking flow: in the warehouse, the goods in the warehouse are required to be checked periodically, after a warehouse management system WMS issues a checking instruction, a low-frequency code scanner installed on a stacker is started, the stacker passes through each warehouse position at a low speed, and meanwhile, the code scanner scans all RFID label information in the corresponding warehouse position, and a high-frame-rate wide-angle camera shoots the outer surface of a stack of goods. The RFID tag is scanned to determine that the goods in the box are not lost in the warehouse area, whether a stack of goods is completed or not is judged through a visual algorithm, if the stack of goods is completed, the fact that the goods on the tray are not abnormal in the arrangement mode is indicated, the quantity of the goods is consistent with the warehouse-in information, and therefore inventory of one warehouse position is achieved. The whole process can be completed in the low-speed operation of the stacker, and the efficiency is extremely high.

As shown in fig. 3, S7: removing the RFID tag on the goods and transporting the goods with the RFID tag removed to a sorting line, step S7 includes: s71: taking out the goods in the warehouse and conveying the goods to an unstacking area; s72: unpacking the goods in the unpacking area; s73: transporting the disassembled goods of the destacking area to a conveyor belt; s74: removing the RFID tag of the goods on the conveyor belt; s75: recording cargo information on the conveyor belt and transporting the cargo on the conveyor belt to a sorting line, wherein step S7 is a delivery process: when the goods are delivered, the scanner on the stacker scans the RFID tags on the tray and the goods, delivery data are updated, and after the goods are unstacked, the semi-active RFID electronic tags on the goods in each box are recovered through the RFID electronic tag recovery device before the goods enter the sorting line, so that recycling is realized.

Preferably, the device further comprises a wide-angle camera, the characteristic surface of the goods is shot through the wide-angle camera, and the wide-angle camera can completely shoot the outer surface of the goods.

Preferably, when the stacker moves along the moving route, the speed of the stacker does not exceed 160m/min, and the stacker keeps the moving speed, so that enough time for scanning the RFID tag and shooting the characteristic surface of the goods can be given without affecting the inventory efficiency.

Preferably, the system further comprises a marking machine, wherein the marking machine can set an RFID label for goods, and the marking machine can quickly set the RFID label on the goods.

Preferably, the warehouse management system is further included, and the warehouse management system can store the goods information in the target warehouse location and the goods information on the conveyor belt.

Preferably, the goods information includes a goods gauge of the goods and a number of the goods.

Preferably, the automatic guide vehicle is further included, the trays are conveyed to the stacker through the automatic guide vehicle, and the trays are placed in the target storage position through the stacker.

From the above description, it can be seen that the above embodiments of the present invention achieve the following technical effects: inventory checking comparison: and judging whether the goods are lost or not by utilizing an RFID technology, judging whether the goods are placed on the tray or not in compliance by utilizing a visual technology, wherein the information is combined to enable each box of goods to be in one-to-one correspondence with the tray and the library position, inventory data can be written into the inventory database in real time, and after the data of the whole library area are acquired, the inventory data are uniformly compared with WMS system data. If the goods are lost, specific information of the goods can be clearly lost. Loss condition analysis: through RFID record circulation information, a corresponding statistical report is generated, real-time recording and statistical analysis can be carried out on the loss condition, and basis is provided for service decision of a manager. And checking the warehouse with the highest loss rate of the goods, and checking the loss condition of the RFID goods. And counting the information of each corresponding node through a report, and checking the circulation condition, which warehouse, state and the like of circulation in the using process through the record of the RFID. Each flow link of warehouse management adopts an RFID technology to carry out intelligent management, firstly, each goods is attached with an RFID electronic tag, and each channel of the channel warehouse is provided with information of an RFID reader-writer identification tag to judge flows of goods warehouse entry, warehouse exit, allocation, warehouse shift, inventory checking and the like. The RFID technology performs automatic data acquisition, ensures the speed and accuracy of data input of each link of warehouse management, ensures that enterprises timely and accurately master real data of inventory, realizes efficient cargo searching and real-time inventory checking, and is beneficial to improving the work efficiency of warehouse management. The efficient warehouse management provides real-time data of all links of the enterprise business process for production managers, and solves the problems of insufficient monitoring capability of the warehouse site state, low site operation efficiency, data input lag and the like.

Compared with the prior art, the inventory method adopts a mode of combining the RFID technology and the visual technology, so that the respective defects of the inventory method are avoided, the inventory efficiency is improved, and the stability is enhanced. According to the invention, the semi-active RFID tag is attached to each box of goods, so that warehouse inventory management is accurate to each box of goods, and the warehouse entry and exit records and the circulation records of each box of goods can be searched. The semi-active RFID tag used in the invention supports recycling, has simple installation and recovery modes, realizes full-automatic installation and recovery, and saves cost. The camera used in the invention is a high-frame-rate wide-angle camera, and the information in the storage position is shot from the side when the stacker moves, so as to judge whether the goods are complete or not and whether the goods are placed on the tray according to the specification. And the scanners on the AGVs and the stacker can store data into a database in real time after scanning the information of the RFID electronic tags of the goods, and monitor the state and circulation condition of the goods in each box.

The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. The method for checking the vertical warehouse based on the RFID technology and the deep learning vision technology is characterized by comprising the following steps of:

s1: setting RFID labels for each box of goods, putting the goods with the RFID labels into a target storage position, and recording the goods information in the target storage position;

s2: planning a moving route of the stacker to enable the stacker to pass through all the warehouse positions to be checked;

s3: when the stacker passes through the warehouse location which needs to be checked, scanning RFID labels of all cargoes in the warehouse location and shooting characteristic faces of the cargoes;

s4: judging whether the goods are complete or not according to the shot characteristic surface information of the goods;

s5: combining the scanned RFID tag information of the goods with the shot characteristic surface information of the goods to judge the quantity of the goods;

s6: and comparing the quantity of the cargoes with the cargo information in the target library position recorded in the step S1.

2. The method for inventory checking based on RFID technology and deep learning vision technology according to claim 1, further comprising:

s7: and removing the RFID tag on the goods, and conveying the goods with the RFID tag removed to a sorting line.

3. The method for inventory in a standing warehouse based on the RFID technology and the deep learning vision technology according to claim 2, wherein the step S1 includes:

s11: placing the goods into a conveyor belt;

s12: setting RFID labels for each cargo box through a marking machine;

s13: stacking the goods in a stacking area to form a target stack shape and placing the goods on a tray;

s14: conveying the trays to a target warehouse through a stacker;

s15: and recording the goods information stored in the target storage position.

4. The method for inventory checking based on the RFID technology and the deep learning vision technology according to claim 1, further comprising a wide-angle camera through which the characteristic surface of the goods is photographed.

5. The method for inventory in a standing warehouse based on the RFID technology and the deep learning vision technology according to claim 1, wherein the speed of the stacker does not exceed 160m/min when the stacker moves along the moving route.

6. A method for inventory checking based on RFID technology and deep learning vision technology according to claim 3, wherein the step S7 includes:

s71: taking out the cargoes in the warehouse and conveying the cargoes to an unstacking area;

s72: unpacking the goods in the unstacking area;

s73: transporting the disassembled goods of the unstacking area to a conveyor belt;

s74: removing RFID tags of the goods on the conveyor belt;

s75: and recording cargo information on the conveyor belt and transporting the cargo on the conveyor belt to the sorting line.

7. The method of claim 1, further comprising a marking machine capable of providing the goods with an RFID tag.

8. The method of claim 6, further comprising a warehouse management system capable of storing cargo information in the target warehouse location and cargo information on the conveyor belt.

9. The method for inventory checking based on the RFID technology and the deep learning vision technology according to claim 6, wherein the goods information includes goods specifications and numbers of goods.

10. The method of claim 6, further comprising an automated guided vehicle by which the pallet is transported to the stacker, and by which the pallet is placed in a target stock location.