CN113836795B - Method and platform for constructing initial goods placement attitude model - Google Patents
Method and platform for constructing initial goods placement attitude model Download PDFInfo
- Publication number
- CN113836795B CN113836795B CN202111044006.5A CN202111044006A CN113836795B CN 113836795 B CN113836795 B CN 113836795B CN 202111044006 A CN202111044006 A CN 202111044006A CN 113836795 B CN113836795 B CN 113836795B
- Authority
- CN
- China
- Prior art keywords
- goods
- neural network
- initial
- initial placement
- cargo
- 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 44
- 230000001133 acceleration Effects 0.000 claims abstract description 84
- 238000003062 neural network model Methods 0.000 claims abstract description 39
- 230000009466 transformation Effects 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 238000005070 sampling Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 15
- 238000002372 labelling Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 3
- 230000036544 posture Effects 0.000 description 30
- 238000012360 testing method Methods 0.000 description 11
- 238000010801 machine learning Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 8
- 230000003139 buffering effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 239000000470 constituent Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000009863 impact test Methods 0.000 description 2
- 230000001976 improved effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002779 inactivation Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
A method for constructing an initial placement attitude model of goods comprises the following steps: comprising the following steps: acquiring triaxial acceleration data when goods are initially placed, and determining a section when the goods are placed stably according to the triaxial acceleration data; acquiring an average value of triaxial acceleration of goods placement in an interval section when the goods placement is stable, and carrying out nonlinear transformation on the average value; and comparing the average value of the triaxial acceleration with the initial placing gesture of the cargo, marking the cargo placing gesture according to a comparison result to obtain marking data, sending the average value of the triaxial acceleration after nonlinear transformation and the marking data into a neural network for training, and determining a cargo initial placing gesture neural network model according to a preset cargo initial placing gesture recognition accuracy requirement.
Description
Technical Field
The invention relates to the field of intelligent control, in particular to a method for constructing an initial goods placement posture model, a platform and a method for identifying initial goods placement postures.
Background
Goods can go through links such as storage, carrying and transportation from delivery to sellers, wherein can suffer from actions such as vibration, impact, drop and the like, even violent handling actions, wherein initial placing posture (face, edge and angle) of the goods is an important parameter for laboratory to set package transportation standards. The information is accurately detected and identified, so that the method and the structure of the package and the transportation test and the design of the package are improved in a targeted manner, the responsibility of goods loss is positioned, and the transportation loss is reduced.
The above information disclosed in the background section is only for a further understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention provides a cargo initial placement attitude model construction method, a cargo initial placement attitude recognition platform method and a cargo initial placement attitude recognition method.
The first aspect of the invention provides a method for constructing an initial placement attitude model of goods, which comprises the following steps: comprising the following steps: s1: acquiring triaxial acceleration data when goods are initially placed, and determining a section when the goods are placed stably according to the triaxial acceleration data; s2: acquiring an average value of triaxial acceleration of goods placement in an interval section when the goods placement is stable, and carrying out nonlinear transformation on the average value; s3: comparing the average value of the triaxial acceleration with the initial placing gesture of the goods, and marking the goods placing gesture according to the comparison result to obtain marking data, and S4: and sending the average value of the triaxial acceleration after nonlinear transformation and the labeling data into a neural network for training, and determining a cargo initial placement attitude neural network model according to a preset cargo initial placement attitude identification accuracy requirement.
According to one embodiment of the invention, wherein said S1 comprises: the initial placing posture of the goods is collected through the transportation environment detection device, wherein the transportation environment detection device comprises a triaxial acceleration sensor.
According to one embodiment of the present invention, in the step S1, the peak position of the waveform curve of the composite vector acceleration a of the triaxial acceleration of the initial placement posture of the cargo is determined, and the time coordinate of the peak is recorded as tmax, and the peak is traversed from the initial position t 0 of the a in the direction of the peak side by the step length N, and the average value of the vector acceleration a in the interval segment of the interval [0, N x N ] is calculated every time the traversingIf/>Determining the section as a candidate section, finishing the traversal when the traversal is finished to t max, and selecting the candidate section with the longest time length as the section when goods placement is stable, whereinA x、ax and a x are acceleration in X, Y and Z directions when the triaxial acceleration sensor detects initial placement of the cargo, n is the number of times of traversal, and b is a preset threshold.
According to one embodiment of the present invention, in the step S1, when the stable time zone for determining the placement of the cargo cannot be acquired at the end of the traversal, the time zone for stabilizing the placement of the cargo is set to a preset value, where the preset value relates to the triaxial acceleration data sampling rate, the sampling duration and the pre-trigger duration.
According to one embodiment of the present invention, in the S2, the average value of the triaxial acceleration isAnd/>The nonlinear transformation is/>And/>
According to one embodiment of the present invention, in S3, the initial placement posture of the cargo is a plane, a rib, and an angle, and the noted data is: the initial placement posture of the cargo is set to 0, the edges are set to 1, and the corners are set to 2.
According to an embodiment of the invention, the preset initial placement gesture recognition accuracy is to accurately recognize that the initial placement gesture of the goods is above 90%.
According to one embodiment of the present invention, the input of the neural network model during training is: the average value of the triaxial acceleration after nonlinear transformation and the labeling data; the output of the neural network model during training is as follows: the initial placement gesture after training is completed identifies a neural network model, wherein the neural network model at least comprises the network layer number of the neural network model, the node number of each layer and related parameters of the neural network; the neural network model is input in prediction as follows: the average value of triaxial acceleration after nonlinear transformation of the initial placing gesture of the goods in the interval section when the goods are placed stably; the output of the neural network model during prediction is as follows: initial placement attitude of the cargo.
A second aspect of the present invention provides a platform for identifying an initial placement attitude of a cargo, comprising: the system comprises an input device, a neural network model and an output device, wherein the input device is used for acquiring initial placement attitude data of goods; the neural network model calculates the collected initial placement attitude data of the goods; and the output device outputs a posture report of the initial placement of the goods according to the calculation result of the neural network model, wherein the neural network model is obtained according to the method.
According to one embodiment of the invention, the cargo initial placement attitude report includes a cargo initial placement attitude.
A third aspect of the present invention provides a method of identifying an initial placement attitude of a cargo, comprising: and sending data related to the goods eating placing gesture to the platform for identifying the initial placing gesture of the goods, and determining the initial placing gesture of the goods according to the report output by the platform.
According to the scheme of the invention, a machine learning algorithm is used for replacing a threshold segmentation method, so that the accuracy of the recognition of the placement gesture is effectively improved. The method and the device can accurately identify the goods placement state in the packaging and transporting process, and are favorable for making more reasonable packaging test standards and purposefully improving the product packaging design.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an exemplary method for constructing a model of the initial placement attitude of a good according to the present invention.
FIG. 2 is a flowchart of an implementation of the machine learning initial placement pose model construction of the present invention according to an exemplary embodiment of the present invention.
FIG. 3 is a schematic diagram of typical accelerations in the machine learning initial placement pose model of the present invention according to an exemplary embodiment of the present invention.
FIG. 4 is a flowchart of the machine learning initial placement pose model verification of the present invention according to an exemplary embodiment of the present invention.
FIG. 5 is a block diagram of an initial placement gesture-recognition platform of the present invention according to an exemplary embodiment of the present invention.
FIG. 6 is a flowchart of the initial placement gesture-recognition platform operation of the present invention in accordance with one exemplary embodiment of the present invention.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
As used herein, the terms "first," "second," and the like may be used to describe elements in exemplary embodiments of the present invention. These terms are only used to distinguish one element from another element, and the inherent feature or sequence of the corresponding element, etc. is not limited by the terms. Unless defined otherwise, all terms (including technical or scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Those skilled in the art will understand that the devices and methods of the present invention described herein and illustrated in the accompanying drawings are non-limiting exemplary embodiments and that the scope of the present invention is defined solely by the claims. The features illustrated or described in connection with one exemplary embodiment may be combined with the features of other embodiments. Such modifications and variations are intended to be included within the scope of the present invention.
Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the drawings, detailed descriptions of related known functions or configurations are omitted so as not to unnecessarily obscure the technical gist of the present invention. In addition, throughout the description, the same reference numerals denote the same circuits, modules or units, and repetitive descriptions of the same circuits, modules or units are omitted for brevity.
Furthermore, it should be understood that one or more of the following methods or aspects thereof may be performed by at least one control unit or controller. The terms "control unit," "controller," "control module," or "master control module" may refer to a hardware device that includes a memory and a processor. The memory or computer-readable storage medium is configured to store program instructions, and the processor is specifically configured to execute the program instructions to perform one or more processes that will be described further below. Moreover, it should be appreciated that the following methods may be performed by including a processor in combination with one or more other components, as will be appreciated by those of ordinary skill in the art.
In order to identify the initial placement posture, a transport environment analysis platform is embedded to identify and analyze the data collected by the acceleration sensor transported together with the goods, for example, the probability of the initial internal working posture of the goods in the actual transport process is analyzed, the method can be used for making laboratory package test standards, better examining the strength and package buffering performance of the product, and simultaneously optimizing and improving the structural strength of the product and the buffering package design, for example, the direction of the initial placement posture with high probability is protected in a key way.
The product package is generally hexahedron, and the initial placement gesture can be generally divided into three conditions of a face, a prismatic surface and an angular surface.
FIG. 1 is a flow chart of an exemplary method for constructing a model of the initial placement attitude of a good according to the present invention. As shown in figure 1 of the drawings,
At the step S1, three-axis acceleration data during initial placement of cargoes are collected, and a section during stable placement of cargoes is determined according to the three-axis acceleration data;
at the step S2, acquiring an average value of triaxial acceleration of goods placement in a section when the goods placement is stable, and carrying out nonlinear transformation on the average value;
at the step S3, comparing the average value of the triaxial acceleration with the initial placing posture of the cargo, marking the cargo placing posture according to the comparison result to obtain marked data,
And at the step S4, the average value of the triaxial acceleration after nonlinear transformation and the labeling data are sent into a neural network for training, and a cargo initial placement posture neural network model is determined according to a preset cargo initial placement posture identification accuracy requirement.
FIG. 2 is a flowchart of an implementation of the machine learning initial placement pose model construction of the present invention according to an exemplary embodiment of the present invention. As shown in the figure 2 of the drawings,
Firstly, acquiring a series of vibration or impact events with known placement postures through a triaxial acceleration sensor, and importing data of triaxial acceleration of the vibration or impact events into a platform; then, using the formulaVector synthesis is carried out on the triaxial acceleration data (wherein a refers to synthesized vector acceleration, a x、ax and a x refer to acceleration in the directions X, Y and Z acquired by an acceleration sensor respectively); and finally, putting the acceleration waveform synthesized by the vector into a Butterworth low-pass filter for filtering treatment to remove high-frequency noise.
Next, a process of finding a stable interval is performed, and fig. 3 is a schematic diagram of typical acceleration in the machine learning initial placement pose model according to the present invention according to an exemplary embodiment of the present invention.
As shown in fig. 3, first, a vector acceleration peak is found, and the time coordinate is recorded as t max; then, the acceleration start position t 0 (corresponding to the data point number of 0) is traversed to the right (the peak side) by a step length N, where N represents the number of sampling points, which can be selected according to the sampling frequency of the acceleration data, and the higher the sampling frequency is, the larger N can be obtained, for example, the N can be 2 when the sampling frequency is 800 Hz. Calculating average value of vector acceleration in interval [0, n ] interval by each traversalN is the nth traversal. Normally, when the goods are placed still, the acceleration sensor only receives the action of gravity, and the vector acceleration is close to the gravity acceleration of 1g. If it isB is a defined threshold value, and generally 0.1-0.2 g is taken, the interval is recorded as a candidate interval, otherwise, the interval is not recorded as a candidate area, the traversal is finished at a position of a vector acceleration peak t max, and t max is the peak moment; and finally, if the candidate interval exists, selecting the candidate interval with the longest time length as an initial placement stable interval, and if the candidate interval does not exist, selecting the fixed interval as the initial placement interval. The interval section fixed in the actual operation engineering can be selected [0,150]. Where 150 represents the data point, which is related to the data sampling rate and the impact pre-trigger time setting, where the impact pre-trigger time is the time period during which the data sampling should be recorded before the impact trigger of the set acceleration. The dimension of 150 sampling points is the number of sampling points, namely, the 150 th sampling point from the acceleration can select an experience value, and the experience value is related to the data sampling rate, the sampling duration and the pre-trigger duration; for example, when the sampling rate of the detection device is 800Hz, the total sampling point number of one piece of acceleration data is 2880, that is, the sampling time length is 3.6s, the impact pre-triggering time is set to be 1.6s, and considering that the falling weightlessness time cannot exceed 1s, the time length of a placement section in one piece of acceleration data may be 0.6s, corresponding to 480 points, and the upper limit of the fixed interval is more suitable to be 150 points before taking.
According to one or more embodiments of the present invention, after the initial placement stability interval is determined, a corresponding tri-axis acceleration waveform is intercepted according to the initial placement stability interval, and respective averages of tri-axis accelerations within the stability placement interval are calculated,And/>Then, for convenience of subsequent machine learning, nonlinear transformation is carried out on respective average values of the triaxial accelerations, and the transformed values are respectively/>And/>Forming neural network input vector/>Next, the triaxial average value/>And/>Performing comparative analysis on the initial placement posture of the vibration or impact test corresponding to the data, removing error data, wherein the process is called cleaning, marking according to the initial placement posture of the vibration or impact event corresponding to the data, setting the surface as 0, setting the edge as 1, setting the angle as 2, and calculating/>And storing the marked data in a database.
According to one or more embodiments of the invention, a series of nonlinear transformation values of the respective averages of triaxial accelerations for which initial placement poses are knownAnd sending the labeling data into the constructed DNN neural network, adjusting network parameters (such as the number of network layers, the number of nodes at each layer and the random inactivation probability and the like) according to the loss rate and the accuracy, judging whether the accuracy requirement of identification is met, if so, successfully constructing the model, outputting the model meeting the requirements of customers, and if not, adding a known initial placement gesture event and adjusting the network parameters to retrain the model until the requirements are met, and outputting the model meeting the requirements of customers.
According to one or more embodiments of the present invention, the preset initial placement posture recognition accuracy of the cargo is to accurately recognize that the initial placement posture of the cargo is more than 90 percent
According to one or more embodiments of the present invention, the database stores the original triaxial acceleration data and nonlinear transformation values of triaxial acceleration respective average values of stable intervalData such as labels.
According to one or more embodiments of the invention, cleaning and labeling are used for a model training phase, wherein cleaning: screening the data for training the model to exclude erroneous data: for example, the failure of the sensor to stick to the sensor results in errors in the recorded data. Wherein the label is as follows: the input data of the model is marked, namely, the initial placement gesture corresponding to the data is set to 0, 1 is set to the edge, and 2 is set to the angle.
According to one or more embodiments of the present invention, the neural network model inputs at the time of training are: the average value of the triaxial acceleration after nonlinear transformation and the labeling data; the output of the neural network model during training is as follows: the initial placement gesture after training is completed identifies a neural network model, wherein the neural network model at least comprises the network layer number of the neural network model, the node number of each layer and related parameters of the neural network; the neural network model is input in prediction as follows: the average value of triaxial acceleration after nonlinear transformation of the initial placing gesture of the goods in the interval section when the goods are placed stably; the output of the neural network model during prediction is as follows: initial placement attitude of the cargo. .
According to one or more embodiments of the present invention, a three-axis acceleration sensor is built in the transportation environment detection device, and the three-axis acceleration data refers to acceleration curves of X, Y, Z directions acquired by the three-axis acceleration sensor when an impact event occurs. Synthesis is performed using the formula: Where a refers to the resultant vector acceleration, and a x、ax and a x are the acceleration sensor X, Y and the acceleration in the Z direction, respectively.
FIG. 4 is a flowchart of the machine learning initial placement pose model verification of the present invention according to an exemplary embodiment of the present invention. As shown in fig. 4, data of the triaxial acceleration of the unknown placement posture event is imported into the platform, the average value of the triaxial acceleration in the stable initial placement posture interval and the calculation interval is identified by using the same method of the training model, corresponding nonlinear transformation is performed, the transformed data is sent into the trained initial placement posture identification model for identification and judgment, the placement posture is output after judgment, and the process is finished.
FIG. 5 is a block diagram of an initial placement gesture-recognition platform of the present invention according to an exemplary embodiment of the present invention.
As shown in fig. 6, the platform for identifying the initial placement posture of the goods, the input device, the neural network model and the output device, wherein the input device is used for acquiring initial placement data of the goods; the neural network model calculates the collected initial placement data of the goods; and the output device outputs a cargo initial placement attitude report according to the calculation result of the neural network model, wherein the neural network model is a neural network model trained according to the method of the figure 2.
FIG. 6 is a flowchart of the initial placement gesture-recognition platform operation of the present invention in accordance with one exemplary embodiment of the present invention.
As shown in fig. 6, a transportation environment detection device with a built-in three-axis acceleration sensor and data acquisition, storage, transmission and other components is placed in a product package (the transportation environment detection device can be a black box to the outside in general), and the transportation environment detection device is started; then, carrying out impact test (drop, throwing and the like) or actual transportation on the transportation environment detection device, obtaining initial placement attitude data, uploading the initial placement attitude data to an analysis platform through wireless remote or local connection, running an initial placement attitude analysis algorithm and a model by the platform, carrying out model training or initial placement attitude identification, then inducing corresponding information to generate an analysis report, and closing the transportation environment detection device after the test is completed or the transportation is completed.
The transportation environment detection device can be a black box to the outside, and is composed of a built-in triaxial acceleration sensor and components such as data acquisition, storage and transmission, a battery and the like. The transport environment detection device can perform initial placement posture testing, and mainly comprises initial placement tests (performed by using an impact table), drop tests (drop test machines), throwing (throwing machines or hand throwing). The data collected by the transportation environment detection device are triaxial acceleration curve data of an initial placement gesture event.
According to one or more embodiments of the invention, the analysis report is automatically generated by the platform, including the initial placement posture results of the cargo during the test or actual transportation. The cutoff conditions of the platform operation technology are as follows: after the test or the actual transportation is completed, the operation is stopped manually or automatically after the initial placement gesture of all cargoes are identified.
According to one or more embodiments of the invention, the platform for identifying the initial placement gesture of the goods is a logistics environment analysis platform, mainly comprises a server, a database, a client (a webpage end, a PC end and a mobile end) and the like, integrates an analysis algorithm and a machine learning model, and can realize functions of online detection, online storage, automatic identification, statistical analysis, information release, multi-user sharing and the like.
According to one or more embodiments of the present invention, aspects of the present invention seek initial placement stability intervals in a cargo vibration or shock acceleration signal through a threshold. In addition, the scheme of the invention calculates the nonlinear variation value of the triaxial average value in the initial placement stability interval, and sends the nonlinear variation value into the neural network for machine learning to produce an initial gesture recognition model. In addition, the scheme of the invention uses the initial attitude model to identify the object state when the goods are stably placed in the actual transportation process.
According to one or more embodiments of the invention, in order to identify the initial placement posture, the invention is embedded into a transport environment analysis platform to identify and analyze the data collected by the acceleration sensor transported with the goods, such as analyzing the probability of each initial placement posture of the goods in the actual transport process, and can be used for making laboratory package test standards, better examining the strength and package buffering performance of the product, and simultaneously, aiming at optimizing and improving the structural strength of the product and the buffering package design, such as the important protection of the initial placement posture direction with high probability.
According to one or more embodiments of the invention, processing logic in the methods of the invention may implement processes as the flows of the methods of the invention using encoded instructions (e.g., computer and/or machine readable instructions) stored on a non-transitory computer and/or machine readable medium (e.g., hard disk drive, flash memory, read-only memory, optical disk, digital versatile disk, cache, random access memory, and/or any other storage device or storage disk) in which information is stored for any period of time (e.g., for extended periods of time, permanent, transient instances, temporary caches, and/or information caches). As used herein, the term "non-transitory computer-readable medium" is expressly defined to include any type of computer-readable storage device and/or storage disk and to exclude propagating signals and to exclude transmission media.
According to one or more embodiments of the invention, the methods of the invention may be implemented using control circuitry, (control logic, a host system, or a control module), which may comprise one or more processors, or may comprise a non-transitory computer-readable medium therein. In particular, the master control system or control module may comprise a microcontroller MCU. The processors used to implement the processing of the method of the present invention may be, for example, but are not limited to, one or more single-core or multi-core processors. The processor(s) may include any combination of general-purpose processors and special-purpose processors (e.g., graphics processors, application processors, etc.). The processor may be coupled to and/or may include a memory/storage device and may be configured to execute instructions stored in the memory/storage device to implement various applications and/or operating systems running on the controller of the present invention.
The figures and detailed description of the invention referred to above as examples of the invention are intended to illustrate the invention, but not to limit the meaning or scope of the invention described in the claims. Accordingly, modifications may be readily made by one skilled in the art from the foregoing description. In addition, one skilled in the art may delete some of the constituent elements described herein without deteriorating the performance, or may add other constituent elements to improve the performance. Furthermore, one skilled in the art may vary the order of the steps of the methods described herein depending on the environment of the process or equipment. Thus, the scope of the invention should be determined not by the embodiments described above, but by the claims and their equivalents.
While the invention has been described in connection with what is presently considered to be practical, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (10)
1. A method for constructing an initial placement attitude model of goods comprises the following steps: comprising the following steps:
S1: acquiring triaxial acceleration data when goods are initially placed, and determining a section when the goods are placed stably according to the triaxial acceleration data;
S2: acquiring an average value of triaxial acceleration of the goods placement in the interval section when the goods placement is stable, and carrying out nonlinear transformation on the average value;
S3: comparing the average value of the triaxial acceleration with the initial placing gesture of the goods, marking the placing gesture of the goods according to the comparison result to obtain marking data,
S4: sending the average value of the triaxial acceleration after nonlinear transformation and the labeling data into a neural network for training, and determining a cargo initial placement attitude neural network model according to a preset cargo initial placement attitude identification accuracy requirement;
In the step S1, determining the peak position of the waveform curve of the composite vector acceleration a of the triaxial acceleration of the initial placement attitude of the cargo, recording the time coordinate of the peak as t max, traversing the initial position t 0 of the cargo from the step N to the peak side, and calculating the average value of the composite vector acceleration a in the interval of the interval [0, N x N ] each time If/>Determining the section as a candidate section, finishing the traversal when the traversal is finished to t max, and selecting the candidate section with the longest time length as the section when goods placement is stable, wherein/>A x、ay and a z are acceleration in X, Y and Z directions when the triaxial acceleration sensor detects initial placement of the cargo, n is the number of times of traversal, and b is a preset threshold.
2. The method of claim 1, wherein the S1 comprises:
The initial placing posture of the goods is collected through the transportation environment detection device, wherein the transportation environment detection device comprises a triaxial acceleration sensor.
3. The method according to claim 2, wherein in the S1, when the stable time zone for determining the placement of the cargo cannot be acquired at the end of the traversal, the time zone for the placement of the cargo is set to a preset value related to the triaxial acceleration data sampling rate, the sampling duration and the pre-trigger duration.
4. The method of claim 1, wherein in said S2, said triaxial acceleration has an average value ofAndThe nonlinear transformation is/> And/>
5. The method of claim 1, wherein in S3, the initial placement pose of the good is a face, a ridge, and an angle, and the labeling data is: the initial placement posture of the cargo is set to 0, the edges are set to 1, and the corners are set to 2.
6. The method of claim 1, wherein the preset initial placement gesture recognition accuracy is to accurately recognize that the initial placement gesture of the cargo is above 90%.
7. The method of claim 1, wherein,
The neural network model is input during training as follows: the average value of the triaxial acceleration after nonlinear transformation and the labeling data; the output of the neural network model during training is as follows: the initial placement gesture after training is completed identifies a neural network model, wherein the neural network model at least comprises the network layer number of the neural network model, the node number of each layer and related parameters of the neural network;
the neural network model is input in prediction as follows: the average value of triaxial acceleration after nonlinear transformation of the initial placing gesture of the goods in the interval section when the goods are placed stably; the output of the neural network model during prediction is as follows: initial placement attitude of the cargo.
8. A platform for identifying an initial placement pose of a good, comprising: input device, neural network model, output device, wherein,
The input device is used for acquiring initial placement attitude data of cargoes;
the neural network model calculates the collected initial placement attitude data of the goods;
The output device outputs a posture report of the initial placement of the goods according to the calculation result of the neural network model,
Wherein the neural network model is a neural network model according to any one of claims 1-7.
9. The platform of claim 8, wherein the cargo initial placement attitude report comprises a cargo initial placement attitude.
10. A method of identifying an initial placement pose of a good, comprising:
Feeding the data related to the initial placing attitude of the goods into the platform for identifying the initial placing attitude of the goods according to any one of claims 8 or 9, and determining the initial placing attitude of the goods according to the report output by the platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111044006.5A CN113836795B (en) | 2021-09-07 | 2021-09-07 | Method and platform for constructing initial goods placement attitude model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111044006.5A CN113836795B (en) | 2021-09-07 | 2021-09-07 | Method and platform for constructing initial goods placement attitude model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113836795A CN113836795A (en) | 2021-12-24 |
| CN113836795B true CN113836795B (en) | 2024-06-07 |
Family
ID=78958563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111044006.5A Active CN113836795B (en) | 2021-09-07 | 2021-09-07 | Method and platform for constructing initial goods placement attitude model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113836795B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664122A (en) * | 2018-04-04 | 2018-10-16 | 歌尔股份有限公司 | A kind of attitude prediction method and apparatus |
| CN112097374A (en) * | 2020-09-16 | 2020-12-18 | 珠海格力电器股份有限公司 | Device control method, device and computer readable medium |
| CN113256224A (en) * | 2021-06-22 | 2021-08-13 | 天津知途物联科技有限公司 | Impact inclination electronic tag for cargo transportation monitoring and monitoring method thereof |
-
2021
- 2021-09-07 CN CN202111044006.5A patent/CN113836795B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664122A (en) * | 2018-04-04 | 2018-10-16 | 歌尔股份有限公司 | A kind of attitude prediction method and apparatus |
| CN112097374A (en) * | 2020-09-16 | 2020-12-18 | 珠海格力电器股份有限公司 | Device control method, device and computer readable medium |
| CN113256224A (en) * | 2021-06-22 | 2021-08-13 | 天津知途物联科技有限公司 | Impact inclination electronic tag for cargo transportation monitoring and monitoring method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 车用汽油机瞬态空燃比的混沌时序非线性组合辨识模型;李岳林等;中国公路学报;20150415;第28卷(第4期);第109-115页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113836795A (en) | 2021-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110991311B (en) | Target detection method based on dense connection deep network | |
| CN108632097B (en) | Abnormal behavior object identification method, terminal device and medium | |
| US20150104106A1 (en) | Method, system and apparatus for determining a contour segment for an object in an image captured by a camera | |
| CN107808122A (en) | Method for tracking target and device | |
| Li | Two-view motion segmentation from linear programming relaxation | |
| CN107430693A (en) | For vehicle classification and the equipment and system of checking | |
| CN109902619B (en) | Image closed loop detection method and system | |
| CN113112526A (en) | Target tracking method, device, equipment and medium | |
| Hendrawan et al. | Improvement object detection algorithm based on YoloV5 with BottleneckCSP | |
| KR20200010971A (en) | Apparatus and method for detecting moving object using optical flow prediction | |
| Viraktamath et al. | Comparison of YOLOv3 and SSD algorithms | |
| CN110443119B (en) | Method and device for identifying state of goods in carriage | |
| CN113836795B (en) | Method and platform for constructing initial goods placement attitude model | |
| Feng et al. | A novel approach for trajectory feature representation and anomalous trajectory detection | |
| CN111968103B (en) | Steel coil interval detection method, system, medium and electronic terminal | |
| CN116946610B (en) | Method and device for picking up goods in intelligent warehousing system | |
| CN111814653B (en) | Method, device, equipment and storage medium for detecting abnormal behavior in video | |
| CN114255435A (en) | Method and device for detecting abnormality of transport device, electronic apparatus, and storage medium | |
| CN113792484B (en) | Cargo impact attitude model construction method and platform | |
| WO2021138893A1 (en) | Vehicle license plate recognition method and apparatus, electronic device, and storage medium | |
| US20230342951A1 (en) | Object tracking apparatus, object tracking method, and program | |
| Li et al. | Computer vision based conveyor belt congestion recognition in logistics industrial parks | |
| US10839258B2 (en) | Computer-readable recording medium, detection method, and detection device | |
| WO2018161305A1 (en) | Grasp quality detection method, and method and system employing same | |
| CN114648554A (en) | Method, device and equipment for acquiring machine position guarantee data and storage medium |
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 |