CN111929636B - Intelligent identification and marking positioning method for metal container - Google Patents
Intelligent identification and marking positioning method for metal container Download PDFInfo
- Publication number
- CN111929636B CN111929636B CN202010547426.4A CN202010547426A CN111929636B CN 111929636 B CN111929636 B CN 111929636B CN 202010547426 A CN202010547426 A CN 202010547426A CN 111929636 B CN111929636 B CN 111929636B
- Authority
- CN
- China
- Prior art keywords
- container
- transmitting power
- self
- adaptive
- identification
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000002184 metal Substances 0.000 title claims abstract description 25
- 230000035945 sensitivity Effects 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 28
- 238000012360 testing method Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 description 13
- 238000004519 manufacturing process Methods 0.000 description 11
- 238000013178 mathematical model Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 239000003550 marker Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000008713 feedback mechanism Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S1/00—Beacons or beacon systems transmitting signals having a characteristic or characteristics capable of being detected by non-directional receivers and defining directions, positions, or position lines fixed relatively to the beacon transmitters; Receivers co-operating therewith
- G01S1/02—Beacons or beacon systems transmitting signals having a characteristic or characteristics capable of being detected by non-directional receivers and defining directions, positions, or position lines fixed relatively to the beacon transmitters; Receivers co-operating therewith using radio waves
- G01S1/08—Systems for determining direction or position line
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Entrepreneurship & Innovation (AREA)
- Radar, Positioning & Navigation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses an intelligent identification and marking positioning method for a metal container, which comprises the following steps: s1, adjusting input transmitting power: the transmitting power is adaptively adjusted by the antenna connected with the reader-writer, so that the adjusted transmitting power P ts The current antenna is only covered with a single bin, so that the intelligent recognition function of the first metal container is realized; s2, carrying out positive bias marking and positioning of the metal container; s3, the input transmitting power is adjusted in a secondary self-adaptive mode. The method adopts twice self-adaptive adjustment of the transmitting power, and improves the self-adaptability and the internal robustness of the RFID system for the intelligent container identification and marking positioning method. The first self-adaptive transmitting power can be used as the working power of a reader-writer for intelligently identifying single library bits of the container, and the antenna number corresponding to the library bits is utilized to realize the automatic and reliable identification of the container; the second self-adaptive transmitting power can be used as the working power of a reader-writer for positioning the secondary mark of the container in a given positioning area range, and the accurate positioning of the container forward-offset position can be realized.
Description
Technical Field
The invention belongs to the field of wireless identification and container positioning, and particularly relates to an intelligent identification and marking positioning method for a metal container.
Background
At present, a great deal of manual operation conditions still exist in the production, manufacturing and storage management links of most small and medium enterprises, particularly, various raw materials, parts and waste materials are stored in manual libraries of industrial manufacturing enterprises, and the phenomena of low working efficiency, low income and high cost can be brought by a great deal of dependence on manual warehouse-in and stacking storage operations by using a trolley or a stacker. Meanwhile, most manual warehouses lack of efficient bar code recognition technology to ensure the correspondence of goods space, containers and materials, warehouse information is required to be manually input into enterprise business systems such as MES, ERP and the like, and the accuracy of material inventory cannot be comprehensively ensured, so that a reliable and convenient automatic acquisition technology is required to be introduced to assist in optimizing and managing links such as production, manufacturing, warehouse logistics and the like.
The passive ultrahigh frequency radio frequency automatic identification (UHF RFID) is a technology for realizing wireless communication and data interaction between a tag and a reader-writer based on the principle of electromagnetic coupling backscattering, mainly comprises the reader-writer, the tag and a background information system, has the advantages of long and controllable identification distance, high identification speed, strong multi-target identification capability, long data storage time, safe and reliable information, no need of battery power supply, low comprehensive cost and the like, can be used for realizing intelligent management systems such as large-capacity article storage logistics, full life cycle management of a supply chain and the like, and is a universal interconnection technology for realizing the integration of the supply chain, online and offline new retail, smart logistics, smart industry and smart city cores in the future.
For a production and manufacturing workshop for storing UHF-based RFID metal containers, the tags are generally attached to the bottom of the metal containers, the antenna is buried at the bottom of the ground, and if the positions of the containers in small areas cannot be well adjusted by a conventional ranging type or network connectivity type non-ranging RFID wireless positioning mode.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides an intelligent metal container identification and marking positioning method which adopts the idea of adaptively adjusting the transmitting power twice, adds a feedback mechanism and further improves the self-adaptability and the internal robustness of the RFID system for the intelligent container identification and marking positioning method.
The aim of the invention is realized by the following technical scheme: a metal container intelligent identification and mark positioning method comprises the following steps:
s1, adjusting input transmitting power: the transmitting power is adaptively adjusted by the antenna connected with the reader-writer, so that the adjusted transmitting power P ts The current antenna is only covered with a single bin, so that the intelligent recognition function of the first metal container is realized;
s2, carrying out positive bias marking and positioning of the metal container: based on the transmission power P ts Determining a threshold value of the distance from the center of the library position, and performing offline training by using the identification times of the corresponding distance within a certain time period of N seconds and the positive mark state ID of the container position to obtain an intelligent mark classification forward bias positioning model and obtain a forward bias state judgment result of container position placement;
s3, the transmission power of the input is adjusted in a secondary self-adaptive mode: when the distance of the normal position area is given, if the characteristic sensitivity of the data at the current transmitting power is smaller than the characteristic sensitivity value at other transmitting powers, the input transmitting power is adjusted in a secondary self-adaptive mode based on the characteristic sensitivity database.
Further, the step S1 includes the following substeps:
s11, the reader antenna sequentially sets the basic transmitting power as P t0 And P t1 Wherein P is t0 For critical transmit power, P t1 The maximum transmitting power of the reader-writer is set;
s12, judging whether the identification range of the current reader antenna covers a single bin or not for each basic transmitting power and finishing the execution of the two cases;
s13, if the identification range covers a plurality of library bits, namely a plurality of containers are identified, adaptively reducing P t1 The method comprises the steps of carrying out a first treatment on the surface of the If the identification range does not identify the bin container, adaptively scaling up P t0 The steps of the self-adaptive adjustment are t dB units, t is selected according to the actual application scene, and t=1 is generally taken;
s14, when P t0 And P t1 And when the identification range of the reader-writer antenna after the self-adaptation adjustment covers a single library bit under both conditions and the execution of the two conditions is finished, calculating to obtain the self-adaptation transmitting power: p (P) ts ＝(P t0 +P t1 )/2。
Further, the step S2 includes the following sub-steps:
s21, acquiring sample data and fitting the sample data, and dividing the sample data into a positive sample and a negative sample, wherein the positive sample refers to the situation that a container deviates within a specified distance in a single bin (namely, a small-area container is placed positive), and the negative sample refers to the situation that the container exceeds the deviation distance in the single bin (namely, the small-area container is placed biased); dividing positive and negative samples into a training set and a testing set respectively, acquiring an intelligent identification marking function through learning the training set, verifying through the testing set, and determining the dividing ratio of the training set and the testing set according to the actual condition of the number of samples;
s22, model training, wherein the first self-adaptive transmitting power P is acquired based on S1 ts Setting a test distance threshold value of unit change from the center of the library position;
inputting a recognition frequency reference vector of a fixed time period N seconds in a training set and a forward bias mark state ID of a container label position as sample training data; processing the data to obtain a recommended normal region range under the current self-adaptive transmitting power;
then, training an intelligent mark classification model to obtain an intelligent mark classification forward bias positioning model;
s23, identification is carried out, an identification frequency reference vector of a fixed time period N seconds in a test set and a forward bias mark state ID of a container label position are input as test data, and a forward bias state judgment result of container position placement is obtained through the intelligent mark classification forward bias positioning model trained in S22.
Further, the step S3 includes the following substeps:
s31, constructing a characteristic sensitivity database aiming at different self-adaptive transmitting powers and corresponding data characteristics thereof in the S2;
s32, recording the distance corresponding to the place where the recognition times in N seconds reach the preset threshold value as the recommended normal mark area distance, and when the normal mark area distance is fixed, referring to the transmitting power corresponding to the maximum sensitivity point in the characteristic sensitivity database to perform primary feedback on the transmitting power, namely, performing secondary self-adaptive transmitting power adjustment;
s33, circularly executing the step S2 to obtain the optimal self-adaptive working power for positioning the container position forward bias marks.
Further, in the step S33, the secondary adaptive transmit power adjustment method is as follows: and realizing self-adaptive adjustment according to self-adaptive adjustment steps towards the direction of the maximum sensitivity point on the basis of the current transmitting power, or directly adjusting the transmitting power corresponding to the maximum sensitivity point.
The beneficial effects of the invention are as follows:
1. the invention adopts the idea of adaptively adjusting the transmitting power twice, and adds a feedback mechanism, thereby further improving the self-adaptability and the internal robustness of the RFID system for the intelligent container identification and marking positioning method. The first self-adaptive transmitting power in the method can be used as the working power of a reader-writer for intelligently identifying single library bits of the container, and the antenna number corresponding to the library bits is utilized to realize the automatic and reliable identification of the container; the second self-adaptive transmitting power can be used as the working power of a reader-writer for secondary marking and positioning of the container under the given positioning area range, and the accurate positioning of the forward-biased position of the container is further realized under the condition that the storage position of the positioning area is placed by the divided position by extracting the characteristic of the input parameter to feed back the input transmitting power.
2. The method introduces the machine learning idea of intelligent marker classification, adds the reference for feedback and secondary self-adaption by feature extraction, gives a design thought to the marker positioning method of the container position forward bias in a small area range limited as a single bin position, and realizes dynamic marker positioning of the position forward bias state by different self-adaption transmitting powers and recognition times in a certain time period through a trained intelligent marker classification model.
3. Aiming at the problems of inconsistent information of containers and warehouse positions, large manual recording errors, incorrect position placement and the like in application scenes such as logistics warehouse and production workshops, the method provided by the invention provides an intelligent application solution from a brand-new view point of intelligent container identification and mark positioning, assists in automatic intelligent container management and accurate mark positioning of small-area forward bias positions, has higher flexibility, reliability and self-adaption, can be effectively applied to intelligent identification and position forward bias mark positioning of different containers, can reduce various risks of production and warehouse management cost improvement caused by manual placement errors or deviation from a warehouse position center area, and provides a feasible and reliable solution idea for application and implementation of RFID technology in container identification and forward bias positioning management, so that intelligent identification of objects such as containers and realization of position forward bias mark positioning are more scientific, reasonable and intelligent.
4. In the implementation process of the invention, the RFID system formed by the components such as the tag, the reader-writer, the antenna, the computer and the like does not increase extra hardware resources, the implementation cost and the hardware power consumption are relatively low, and the invention has better practicability and flexibility.
Drawings
FIG. 1 is a flow chart of the intelligent identification and marking and positioning method of the metal container of the present invention;
FIG. 2 is a graph of raw data of the number of identifications versus distance for 5 seconds at different transmit powers in accordance with an embodiment of the present invention;
FIG. 3 is a graph of an embodiment of the invention based on FIG. 2 obtained by Fourier fitting;
FIG. 4 is a graph of slope versus distance of a curve derived based on FIG. 3 using Gaussian fitting in accordance with an embodiment of the present invention;
fig. 5 is a fourier fit of the transmit power versus distance curve for the highest sensitivity of fig. 4 for an embodiment of the present invention.
Detailed Description
In order to solve the problems of low working efficiency of container management, manual placement of containers such as misalignment and the like in the management process of logistics storage and the like, realize one-to-one binding of containers and bin antennas and accurate marking and positioning of forward-biased positions of small-area containers, and furthest reduce production and management risks caused by unreliability of article management supply chains, the invention designs and constructs an intelligent reliable container identification and marking and positioning method, introduces an antenna number positioning and intelligent marking and classifying algorithm idea of self-adaptive RFID (radio frequency identification) transmitting power, namely, firstly, self-adaptively adjusts the antenna transmitting power to meet the identification range to exactly cover a single bin, and realizes reliable identification of the bin to which the container belongs by using an antenna number; secondly, realizing dynamic marking and positioning of the forward bias state of the position by classifying different self-adaptive transmitting powers and the recognition times in a certain time period through intelligent marking, and assisting in automatic management of the container; if the normal position area is given, the transmitting power can be fed back and adjusted, and the secondary self-adaptive mark positioning function is realized. The automatic identification of the warehouse location container and the marking and positioning function of whether the container is placed in a deviation normal area can be realized, the method has necessity and urgency for improving the control of the production process flow and the warehouse management level of enterprises, and is also greatly helpful for improving the intelligent and informationized development of the workshop management system of small and medium enterprises.
The technical scheme of the invention is further described below with reference to the accompanying drawings.
The invention aims to provide a practical and intelligent metal container identification and mark positioning method. Unlike the RFID indoor positioning algorithm which generally adopts fixed time, time difference, angle, phase, received signal strength value (RSSI) and other actual ranging parameters and network opposite non-ranging parameters, the invention realizes the intelligent identification of the container and the mark positioning function of whether the position of the container is forward biased based on the RFID background, and is characterized in that the invention introduces the ideas of intelligent algorithms such as antenna number container identification theory, intelligent mark classification machine learning, secondary self-adaptive feedback and the like based on self-adaptive transmitting power.
Because of the interference of unknown laws such as multipath effect, noise, reflection phenomenon and the like in the actual environment, the influence of the interference is difficult to eliminate externally, and therefore, the optimal transmitting power of the reader-writer for container identification is unpredictable in advance each time, so that the method has higher practical application value and universality.
The principle schematic diagram of the intelligent identification and marking positioning method of the metal container is shown in fig. 1, and the specific implementation example process is as follows:
(1) Firstly, a theoretical mathematical model of the self-adaptive transmitting power container identification of the antenna number positioning module based on UHF RFID self-adaptive transmitting power is given, and the deduction process of the embodiment is as follows:
when the reader antenna can read tag information with different distances, the following formula needs to be satisfied:
wherein P is t Representing the transmitting power of the reader antenna, P loss Representing total power loss based on free space propagation and tag backscatter, G t Indicating the gain of the transmitting antenna, G r The unit of the antenna gain is dBm, and the following description is omitted. In addition, lambda is the emission wavelength (m) of electromagnetic wave, d is the distance (m) between the tag and the antenna, L is the system loss factor independent of propagation, A is the effective area (m 2 )。
In combination with the actual application scenario, G is known r ＝G t =2dbm, x= -74dBm, let l=1, derived:
let f=915 mhz, a r ＝3×4＝1.2×10 -3 m 2 ，A t ＝2.5×2.5＝6.25×10 -4 m 2 There are two cases:
let d=0.3m for the case of covering a single bin, calculated as: p (P) t More than or equal to 13.54dBm, the rounding is as follows:
P t ≥14dBm
let d=0.6m for the case where multiple bin labels are read, there are calculated: p (P) t More than or equal to 25.58dBm, and rounding to obtain:
P t ≥26dBm
the above formula derives that, in this embodiment, the spatial mapping relationship between the coverage status and the transmit power is:
the theoretical mathematical model for intelligent identification of the container with the adaptive transmitting power is as follows:
wherein s is the actual state returned under the appointed input transmitting power, 0 indicates that the antenna number is not recognized, 1 indicates that the single bin is just covered, 2 indicates that a plurality of tags are recognized, y indicates the optimal transmitting power after self-adaption adjustment, and P t For the transmit power parameter, here t=1 is taken.
(2) Secondly, providing an actual measurement experience mathematical model of the self-adaptive transmitting power container identification of the antenna number positioning module based on UHF RFID self-adaptive transmitting power, basically matching with the theoretical mathematical model, and the embodiment is described as follows:
based on the actually measured data and in combination with the actual application scene, the corresponding transmitting power in the range of the identification distance less than 0.36m is assumed to be 0-13dBm, and the single bin bit cannot be identified, and the transmitting power P is sequentially increased t The method comprises the steps of carrying out a first treatment on the surface of the The corresponding transmitting power of 14-25dBm in the range of 0.36m-1.055m can identify and cover single bin, and P is maintained t The position calibration judgment of the subsequent intelligent mark classification model is carried out unchanged; the corresponding transmitting power within the range of the identification distance exceeding 1.055m is 26-30dBm, a plurality of library position labels can be identified, and P is gradually decreased t Thereby determining an RFID antenna number positioning mathematical model of the adaptive transmission power.
Based on the mathematical model obtained in the two steps, the intelligent identification and marking positioning method for the metal container provided by the invention comprises the following steps:
s1, adjusting input transmitting power: based on self-adaptive RFID thought, the antenna connected with the reader-writer is self-adaptively adjusted to transmit power, so that the adjusted transmit power P ts The current antenna is only covered with a single bin, so that the intelligent recognition function of the first metal container is realized;
comprises the following substeps:
s11, the reader antenna sequentially sets the basic transmitting power as P t0 And P t1 Wherein P is t0 For critical transmit power, P t1 The maximum transmitting power of the reader-writer is set; the basic transmitting power of the antenna of the reader-writer of this embodiment is set as follows: p (P) t0 ＝14dBm，P t1 ＝30dBm；
S12, after the tag returns data, judging whether the identification range of the current reader antenna covers a single library bit or not according to the identification condition of the reader for the antenna number corresponding to the current tag of each basic transmitting power and finishing the execution of the two conditions;
s13, if the identification range corresponding to the transmission power of 30dBm covers a plurality of bin positions, namely a single bin position antenna can identify a plurality of containers, enabling P to be the same as the identification range t1 ＝P t1 -1; if the identification range corresponding to the transmission power of 14dBm does not identify the bin container, let P t0 ＝P t0 +1；
S14, when P t0 And P t1 And when the identification range of the reader-writer antenna after the self-adaptation adjustment covers a single library bit under both conditions and the execution of the two conditions is finished, calculating to obtain the self-adaptation transmitting power: p (P) ts ＝(P t0 +P t1 ) 2, here according to the embodiment models in (1) and (2), the present embodiment takes: p (P) t0 ＝14dBm，P t1 =25 dBm, giving P ts ＝20dBm。
S2, performing positive bias marking and fixing of the metal containerBits: based on intelligent mark classification concept and based on transmitting power P ts Determining a threshold value of the distance from the center of a library position, performing offline training by using the identification times of the corresponding distance within a certain time period N seconds and the positive mark state ID of the container position to obtain an intelligent mark classification forward bias positioning model, obtaining the recommended forward bias area distance under different self-adaptive transmitting power, performing online identification on actually input data, obtaining a forward bias state judgment result of container position placement, and realizing the function of first container forward bias mark positioning judgment;
comprises the following substeps:
s21, acquiring sample data and fitting, wherein the sample data comprises a reference vector (P ts +test threshold+number of times of identification in N seconds of antenna) and the forward bias flag state ID of the container tag position;
dividing sample data into positive samples and negative samples, wherein the positive samples refer to the situation that a container is offset within a specified distance in a single bin (namely, a small area container is placed positive), and the negative samples refer to the situation that the container exceeds the offset distance in the single bin (namely, the small area container is placed biased); dividing positive and negative samples into a training set and a testing set respectively, acquiring an intelligent identification marking function through learning the training set, verifying through the testing set, and determining the dividing ratio of the training set and the testing set according to the actual condition of the number of samples, wherein the selecting ratio is 7:3;
s22, model training, wherein the first self-adaptive transmitting power P is acquired based on S1 ts Setting a test distance threshold value of unit change from the center of the library position;
inputting a recognition frequency reference vector of a fixed time period N seconds in a training set and a forward bias mark state ID of a container label position as sample training data; the data is processed, sensitivity characteristics such as curve slope and the like can be further extracted, and a recommended normal region range under the current self-adaptive transmitting power is obtained;
then, training an intelligent mark classification model (data used for model training is derived from test data, and a model can be trained by adopting an SVM) to obtain an intelligent mark classification forward bias positioning model;
s23, identification is carried out, an identification frequency reference vector of a fixed time period N seconds in a test set and a forward bias mark state ID of a container label position are input as test data, a trained intelligent mark classification forward bias positioning model is used for obtaining a forward bias state judgment result of container position placement, and identification judgment accuracy is calculated.
An RFID test experiment system platform is built, and a metal container, a 32-channel UHF RFID reader-writer, an anti-metal tag and a 3×3×0.6cm are selected in the embodiment 3 Is a 2dBic ceramic antenna. The embodiment sets the unit working time of the antenna of the reader/writer to be 100ms, and the distance from the base position (80 multiplied by 80 cm) 2 ) The test distance threshold k=10 cm for center unit change, the corresponding recognition times in 15 seconds from the center point 0cm, 10cm, 20cm, 30cm, 40cm, 50cm, 60cm, 70cm and 80cm under the transmission power of 14 dBm-30 dBm (taking the step t=4 dB), after experimental test data are processed, the average number of 3 times of the recognition times in 5 seconds is obtained as a sample data source, and the sensitivity curve of the recognition times and the distance in 5 seconds under different powers can be obtained based on the experimental data, wherein the sensitivity curve is shown in fig. 2. To compensate for the imperfections in the experimental data, a fourier curve fit is performed to obtain fig. 3, from which it is known that as the transmit power increases gradually, the sensitivity curve changes significantly, and the recognition distance increases. When the identification distance is fixed, the larger the absolute value of the slope in a certain distance range of the curve represents the larger variation of the identification times, namely the more sensitive, and the finding of the transmitting power with the maximum sensitivity in the positive judgment distance value is of great significance. Therefore, after deriving the curve, a gaussian curve fitting simulation is performed to obtain fig. 4, and at this time, the transmitting power corresponding to the maximum sensitivity when the distance is known can be observed. In order to more intuitively reflect the relationship between the transmission power and the distance at the highest sensitivity, the experimental data were subjected to fourier curve fitting simulation, see fig. 5. Then, the sample is divided into positive samples (the number of recognition times in 1 second)>=10, 1 indicates that the container mark position is correct) and a negative sample (number of identifications in 1 second<10, -1 indicates the container label position deviation), and positive and negative samples are respectively divided, wherein one part is used as a training set, and the other part is used as a test set.
In this embodiment, n=5 is taken, the adaptive transmitting power and the identification frequency reference vector corresponding to the fixed 5 seconds in the training set and the forward bias mark state ID of the container label position are taken as sample training data, the data are processed, sensitivity characteristics such as curve slope and the like can be further extracted, the recommended forward bias region range under the current adaptive transmitting power can be obtained, then the intelligent label classification model training is performed, the trained intelligent label classification forward bias mark positioning model is obtained, whether the label of the container position in the forward bias position is taken as the identification result, 1 represents the mark positioning and forward bias, and 1 represents the mark positioning and bias. It should be specifically noted that, in fig. 1, the feature extraction of different forms of S2 is mainly used to meet different application requirements, in this embodiment, the number of recognition times within 5 seconds is selected as the feature basis for distinguishing the positive bias, and the slope of the distance curve from the center point of the bin is used as the feature reference of the subsequent second adaptive transmit power.
And inputting the identification frequency reference vector and the forward bias mark state ID of the container label position, which are fixed for 5 seconds, in the test set into the intelligent label classification identification model trained in the previous step, obtaining the forward bias state judgment result of container position placement, and further calculating to obtain the identification judgment accuracy.
S3, the transmission power of the input is adjusted in a secondary self-adaptive mode: based on the feedback idea, when the distance of the normal position area is given, if the characteristic sensitivity of the data under the current transmitting power is smaller than the characteristic sensitivity value under other transmitting powers, the input transmitting power is adjusted in a secondary self-adaptive mode based on the characteristic sensitivity database.
Comprises the following substeps:
s31, constructing a characteristic sensitivity database aiming at different self-adaptive transmitting powers and corresponding data characteristics thereof in the S2;
s32, recording the distance corresponding to the place where the recognition times in N seconds reach the preset threshold value as the recommended normal mark area distance, and when the normal mark area distance is fixed, referring to the transmitting power corresponding to the maximum sensitivity point in the characteristic sensitivity database to perform primary feedback on the transmitting power, namely, performing secondary self-adaptive transmitting power adjustment;
s33, circularly executing the step S2 to obtain the optimal self-adaptive working power for positioning the container position forward bias marks.
In the step S33, the secondary adaptive transmit power adjustment method includes: and realizing self-adaptive adjustment according to self-adaptive adjustment steps towards the direction of the maximum sensitivity point on the basis of the current transmitting power, or directly adjusting the transmitting power corresponding to the maximum sensitivity point.
In this embodiment, the absolute value of the slope of the curve identifying the average number of times and the distance within 1 second is selected as the sensitivity characteristic. And constructing a characteristic sensitivity database by utilizing the absolute value of the slope of the curve of the average frequency and the distance which are recognized within 1 second under different self-adaptive transmitting powers, and carrying out primary feedback, namely secondary self-adaptive transmitting power adjustment by referring to the maximum sensitivity point. The transmitting power input into the S2 is fed back and adjusted once, the self-adaptive adjustment can be realized according to a certain step towards the direction of the maximum sensitivity point on the basis of the current transmitting power, the self-adaptive adjustment can also be directly carried out to the transmitting power corresponding to the maximum sensitivity point, the self-adaptive adjustment is carried out on the basis, and finally the judging result of the forward bias state of the container is optimized.
In this embodiment, the reader may be a desktop reader with a radio frequency identification reader-writer function, or may be a semi-mobile handset with a socket, or other intelligent mobile terminals, and the communication mode may be serial ports, internet ports or other same local area networks.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (3)
1. The intelligent metal container identifying and marking positioning method is characterized by comprising the following steps:
s1, adjustingTransmit power of the node input: the transmitting power is adaptively adjusted by the antenna connected with the reader-writer, so that the adjusted transmitting power P ts The current antenna is only covered with a single bin, so that the intelligent recognition function of the first metal container is realized; comprises the following substeps:
s11, the reader antenna sequentially sets the basic transmitting power as P t0 And P t1 Wherein P is t0 For critical transmit power, P t1 The maximum transmitting power of the reader-writer is set;
s12, judging whether the identification range of the current reader antenna covers a single bin or not for each basic transmitting power and finishing the execution of the two cases;
s13, if the identification range covers a plurality of library bits, namely a plurality of containers are identified, adaptively reducing P t1 The method comprises the steps of carrying out a first treatment on the surface of the If the identification range does not identify the bin container, adaptively scaling up P t0 The steps of the self-adaptive adjustment are t dB units;
s14, when P t0 And P t1 And when the identification range of the reader-writer antenna after the self-adaptation adjustment covers a single library bit under both conditions and the execution of the two conditions is finished, calculating to obtain the self-adaptation transmitting power: p (P) ts ＝(P t0 +P t1 )/2；
S2, carrying out positive bias marking and positioning of the metal container: based on the transmission power P ts Determining a threshold value of the distance from the center of the library position, and performing offline training by using the identification times of the corresponding distance within a certain time period of N seconds and the positive mark state ID of the container position to obtain an intelligent mark classification forward bias positioning model and obtain a forward bias state judgment result of container position placement;
s3, the transmission power of the input is adjusted in a secondary self-adaptive mode: when the distance of the righting region is given, if the characteristic sensitivity of the data under the current transmitting power is smaller than the characteristic sensitivity value under other transmitting powers, the input transmitting power is adjusted in a secondary self-adaptive mode based on the characteristic sensitivity database; comprises the following substeps:
s31, constructing a characteristic sensitivity database aiming at different self-adaptive transmitting powers and corresponding data characteristics thereof in the S2;
s32, recording the distance corresponding to the place where the recognition times in N seconds reach the preset threshold value as the recommended normal mark area distance, and when the normal mark area distance is fixed, referring to the transmitting power corresponding to the maximum sensitivity point in the characteristic sensitivity database to perform primary feedback on the transmitting power, namely, performing secondary self-adaptive transmitting power adjustment;
s33, executing the step S2 in a circulating way, and stopping the circulation when the container offset distance is smaller than the container offset distance under the last self-adaptive working power, namely, the offset detection of the small container area is further close to the single-base-position center distance, so as to obtain the optimal self-adaptive working power for positioning the container position forward-offset mark.
2. The method for intelligently identifying and positioning a metal container according to claim 1, wherein the step S2 comprises the following substeps:
s21, acquiring sample data and fitting the sample data, and dividing the sample data into a positive sample and a negative sample, wherein the positive sample refers to the situation that a container deviates within a specified distance in a single bin, and the negative sample refers to the situation that the container exceeds the deviation distance in the single bin; dividing positive and negative samples into a training set and a testing set, acquiring an intelligent identification marking function through learning of the training set, and verifying through the testing set;
s22, model training, wherein the first self-adaptive transmitting power P is acquired based on S1 ts Setting a test distance threshold value of unit change from the center of the library position;
inputting a recognition frequency reference vector of a fixed time period N seconds in a training set and a forward bias mark state ID of a container label position as sample training data; processing the data to obtain a recommended normal region range under the current self-adaptive transmitting power;
then, training an intelligent mark classification model to obtain an intelligent mark classification forward bias positioning model;
s23, identification is carried out, an identification frequency reference vector of a fixed time period N seconds in a test set and a forward bias mark state ID of a container label position are input as test data, and a forward bias state judgment result of container position placement is obtained through the intelligent mark classification forward bias positioning model trained in S22.
3. The method for intelligently identifying and positioning a metal container according to claim 1, wherein in step S33, the secondary adaptive transmit power adjustment method is as follows: and realizing self-adaptive adjustment according to self-adaptive adjustment steps towards the direction of the maximum sensitivity point on the basis of the current transmitting power, or directly adjusting the transmitting power corresponding to the maximum sensitivity point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010547426.4A CN111929636B (en) | 2020-06-16 | 2020-06-16 | Intelligent identification and marking positioning method for metal container |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010547426.4A CN111929636B (en) | 2020-06-16 | 2020-06-16 | Intelligent identification and marking positioning method for metal container |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111929636A CN111929636A (en) | 2020-11-13 |
| CN111929636B true CN111929636B (en) | 2024-03-26 |
Family
ID=73317585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010547426.4A Active CN111929636B (en) | 2020-06-16 | 2020-06-16 | Intelligent identification and marking positioning method for metal container |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111929636B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116749658B (en) * | 2023-08-21 | 2023-11-14 | 武汉精臣智慧标识科技有限公司 | RFID label printer and read-write method thereof |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1636223A (en) * | 2002-02-21 | 2005-07-06 | 普罗梅格公司 | RF point of sale and delivery method and system using communication with remote computer and having features to read a large number of RF tags |
| CN102103680A (en) * | 2010-08-17 | 2011-06-22 | 中兴通讯股份有限公司 | Method for positioning and identifying electronic tag, reader and positioning system |
| CN102183760A (en) * | 2010-09-19 | 2011-09-14 | 西南交通大学 | Location method based on power scanning of radio frequency identification (RFID) reader-writer antenna |
| JP2012073245A (en) * | 2010-09-29 | 2012-04-12 | Fujitsu Ltd | Measuring method and device for radio frequency identifying tag positions |
| CN102890765A (en) * | 2011-07-20 | 2013-01-23 | 富士通株式会社 | Method and device for locating radio frequency identification tags |
| CN103069647A (en) * | 2010-04-26 | 2013-04-24 | 剑桥企业有限公司 | RFID tag interrogation systems |
| CN103177276A (en) * | 2013-04-07 | 2013-06-26 | 南京大学 | Cargo positioning method and system based on adaptive adjustment antenna power |
| CN103413110A (en) * | 2013-08-29 | 2013-11-27 | 戴生伟 | Object positioning searching device, assembly and method |
| CN107851241A (en) * | 2015-06-04 | 2018-03-27 | 泰科消防及安全有限公司 | System and method for the positioning object in facility |
| CN107886022A (en) * | 2017-11-01 | 2018-04-06 | 阳光凯讯(北京)科技有限公司 | Intelligent repository goods and materials orientation management system based on ultra wide band and radio frequency identification |
| CN108491908A (en) * | 2018-04-08 | 2018-09-04 | 国网江苏省电力有限公司宿迁供电分公司 | A kind of visual intelligent warehousing system and method based on radio frequency identification |
| CN110399756A (en) * | 2019-07-23 | 2019-11-01 | 深圳市琥玟科技有限公司 | A kind of method and system using article in RFID identification adjacent container |
| CN110691981A (en) * | 2017-03-28 | 2020-01-14 | 自动化公司 | Method and apparatus for locating RFID tags |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3029319B1 (en) * | 2014-12-02 | 2018-01-19 | Nexess | INVENTORY SYSTEM OF OBJECTS CONTAINED IN LIMITED SPACE BY AN ENCLOSURE AND AN INVENTORY PROCESS IMPLEMENTED BY SUCH A INVENTORY SYSTEM |
-
2020
- 2020-06-16 CN CN202010547426.4A patent/CN111929636B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1636223A (en) * | 2002-02-21 | 2005-07-06 | 普罗梅格公司 | RF point of sale and delivery method and system using communication with remote computer and having features to read a large number of RF tags |
| CN103069647A (en) * | 2010-04-26 | 2013-04-24 | 剑桥企业有限公司 | RFID tag interrogation systems |
| CN102103680A (en) * | 2010-08-17 | 2011-06-22 | 中兴通讯股份有限公司 | Method for positioning and identifying electronic tag, reader and positioning system |
| CN102183760A (en) * | 2010-09-19 | 2011-09-14 | 西南交通大学 | Location method based on power scanning of radio frequency identification (RFID) reader-writer antenna |
| JP2012073245A (en) * | 2010-09-29 | 2012-04-12 | Fujitsu Ltd | Measuring method and device for radio frequency identifying tag positions |
| CN102890765A (en) * | 2011-07-20 | 2013-01-23 | 富士通株式会社 | Method and device for locating radio frequency identification tags |
| CN103177276A (en) * | 2013-04-07 | 2013-06-26 | 南京大学 | Cargo positioning method and system based on adaptive adjustment antenna power |
| CN103413110A (en) * | 2013-08-29 | 2013-11-27 | 戴生伟 | Object positioning searching device, assembly and method |
| CN107851241A (en) * | 2015-06-04 | 2018-03-27 | 泰科消防及安全有限公司 | System and method for the positioning object in facility |
| CN110691981A (en) * | 2017-03-28 | 2020-01-14 | 自动化公司 | Method and apparatus for locating RFID tags |
| CN107886022A (en) * | 2017-11-01 | 2018-04-06 | 阳光凯讯(北京)科技有限公司 | Intelligent repository goods and materials orientation management system based on ultra wide band and radio frequency identification |
| CN108491908A (en) * | 2018-04-08 | 2018-09-04 | 国网江苏省电力有限公司宿迁供电分公司 | A kind of visual intelligent warehousing system and method based on radio frequency identification |
| CN110399756A (en) * | 2019-07-23 | 2019-11-01 | 深圳市琥玟科技有限公司 | A kind of method and system using article in RFID identification adjacent container |
Non-Patent Citations (1)
| Title |
|---|
| RFID读写器功率的自适应调节策略;姜涛 等;计算机工程;20101031;第36卷(第20期);第291-293页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111929636A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101597199B1 (en) | Rfid portal system with rfid tags having various read ranges | |
| CN110334788B (en) | Distributed multi-antenna reader positioning system and method based on deep learning | |
| CN104199023A (en) | RFID indoor positioning system based on depth perception and operating method thereof | |
| CN102338866A (en) | Radio frequency indoor positioning method based on virtual tag algorithm | |
| CN107145811B (en) | RFID boundary determining method and system based on reference label | |
| CN104091184B (en) | Electronic label detecting method and system | |
| CN108491908B (en) | Visual intelligent warehousing system and method based on radio frequency identification | |
| CN111929636B (en) | Intelligent identification and marking positioning method for metal container | |
| CN104200351A (en) | Logistics management system and positioning method based on RFID rapid positioning | |
| CN105844439A (en) | Warehouse management scheme based on ISO 14443B standard | |
| CN111753937B (en) | RFID (radio frequency identification) label rapid detection method and system based on multi-label | |
| CN109726956A (en) | A kind of UAV Intelligent hangar inventory and optimization method based on RFID | |
| CN104850874A (en) | Method and system for accurately positioning single vector reader-writer | |
| US20080191843A1 (en) | Scanning Settings Inferred From Prior Scan Data | |
| CN104765016A (en) | Radio frequency identification and location method based on intelligent control over power | |
| Ren et al. | Building materials management system based on RFID technology | |
| CN102194138A (en) | Interrogator | |
| CN111526520A (en) | RFID and WSN integrated network multi-target planning method | |
| CN104076323A (en) | RFID positioning method based on simulation tag | |
| CN107944317B (en) | Ultrahigh frequency RFID (radio frequency identification) reading system and misreading removal method thereof | |
| CN103218588A (en) | Radio frequency identification device (RFID) of transport vehicle | |
| US20110006883A1 (en) | Method and system for managing virtual space | |
| CN101685492A (en) | RFID communication model air interface parameter testing method | |
| Irfan et al. | Genetic-based approach for efficient RFID ReaderAntenna positioning | |
| CN109447558B (en) | Method for selecting efficient read-write interval based on RFID (radio frequency identification) equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |