CN113554247A

CN113554247A - Method, device and system for evaluating running condition of automatic guided vehicle

Info

Publication number: CN113554247A
Application number: CN202010327022.4A
Authority: CN
Inventors: 池志攀
Original assignee: Beijing Jingdong Qianshi Technology Co Ltd
Current assignee: Beijing Jingdong Qianshi Technology Co Ltd
Priority date: 2020-04-23
Filing date: 2020-04-23
Publication date: 2021-10-26

Abstract

The invention discloses a method, a device and a system for evaluating the running condition of an automatic guided vehicle, and relates to the technical field of computers. One embodiment of the method comprises: acquiring current operation data of the automatic guided vehicle; training a data model by using current operation data to obtain a use model; the current operating conditions of the automated guided vehicle are evaluated using the usage model and a stored baseline model, wherein the baseline model is derived from a historical operating data training data model. The automatic guide transport vehicle can find that the automatic guide transport vehicle possibly has operation problems in time.

Description

Method, device and system for evaluating running condition of automatic guided vehicle

Technical Field

The invention relates to the technical field of computers, in particular to a method, a device and a system for evaluating the running condition of an automatic guided vehicle.

Background

With the development of automation technology, automated guided vehicles have been used in industries such as logistics and warehousing. Due to wear of various components of the automated guided vehicle, regular service and maintenance of these devices is often required.

At present, equipment is overhauled and maintained mainly by manually evaluating the running condition of an automatic guided transport vehicle and according to the manually evaluated running condition.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:

the existing artificial evaluation method cannot find the running problems of the automatic guided transport vehicle in time.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method, an apparatus, and a system for evaluating an operation status of an automated guided vehicle, which can find that there may be an operation problem in the automated guided vehicle in time.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided an automated guided vehicle operation condition evaluation method including:

acquiring current operation data of the automatic guided vehicle;

training a data model by using the current operation data to obtain a use model;

evaluating the current operating conditions of the automated guided vehicle using the usage model and a stored baseline model, wherein the baseline model is derived from historical operating data training the data model.

Preferably, the method for evaluating the operation condition of the automated guided vehicle further includes:

acquiring historical operation data of a plurality of automatic guided vehicles;

dividing the historical operating data into at least one data phase;

performing, for the historical operating data of each of the data phases: extracting a plurality of first feature sets from the historical operating data, wherein each first feature set corresponds to a time domain feature or a frequency domain feature;

performing, for each of the first feature sets: training the data model by using the data in the first feature set to obtain a corresponding baseline model;

storing a plurality of the baseline models.

Preferably, the first and second electrodes are formed of a metal,

after the acquiring the current operation data of the automated guided vehicle, further comprising:

dividing the current operating data into at least one data phase;

executing, for the current running data of each of the data phases: extracting a plurality of second feature sets from the current data, wherein feature categories corresponding to the second feature sets correspond to feature categories corresponding to the first feature sets in a one-to-one correspondence manner;

the step of training a data model using the current operating data comprises:

performing, for each of the second feature sets: and training a data model by using the data in the second feature set.

Preferably, the step of dividing into at least one data phase comprises:

determining a motion state indicated by each data point in the historical operating data and/or the current operating data, wherein the motion state comprises any one of a deceleration state, a uniform speed state and an acceleration state;

and dividing at least one data phase for the historical operating data and/or the current operating data according to the motion state indicated by each data point, wherein the data included in each data phase indicates the same motion state.

Preferably, the step of extracting a plurality of first feature sets and/or a plurality of second feature sets, which is performed for each of the data phases, includes:

for each of the data phases, performing:

extracting a plurality of time domain features and a plurality of frequency domain features by using the data in the data stage;

selecting a plurality of target features from the plurality of time domain features and the plurality of frequency domain features;

and forming a corresponding feature set by using the data corresponding to each target feature, wherein the feature set is the first feature set when the data in the data phase is the historical operating data, and the feature set is the second feature set when the data in the data phase is the current operating data.

Preferably, the step of evaluating the current operating condition of the automated guided vehicle comprises:

calculating a health assessment value of the automated guided vehicle using the usage model and a stored baseline model;

and when the health assessment value does not meet the preset health condition, determining that the current operation of the automatic guided vehicle has a problem.

Preferably, the first and second electrodes are formed of a metal,

the number of the usage models is multiple;

the number of the baseline models is multiple;

wherein the feature classes of the plurality of feature usage models correspond to the feature classes of the plurality of baseline models one to one;

the calculating of the health assessment value of the automated guided vehicle step includes:

for each of the usage models, performing:

matching a corresponding target baseline model for the use model according to the feature class corresponding to the use model;

calculating a feature health assessment value by using the use model and the target baseline model;

and calculating a health evaluation value by using a plurality of the characteristic health evaluation values.

generating warning information when the current operating condition indicates that there is a problem in the operation of the automated guided vehicle;

providing the warning information to maintenance personnel to maintain the automated guided vehicle and/or replace the automated guided vehicle.

In a second aspect, an embodiment of the present invention provides an automatic guided vehicle operation condition evaluation apparatus, including: an acquisition unit, a training unit and an evaluation unit, wherein,

the acquisition unit is used for acquiring the current operation data of the automatic guided vehicle;

the training unit is used for training a data model by using the current operation data acquired by the acquisition unit to obtain a use model;

and the evaluation unit is used for evaluating the current operating condition of the automatic guided vehicle by utilizing the use model obtained by the training unit and a stored baseline model, wherein the baseline model is obtained by training the data model by historical operating data.

Preferably, the automated guided vehicle operation condition evaluation device further includes: a memory cell, wherein,

the training unit is further used for acquiring historical operation data of the automatic guided vehicles; dividing the historical operating data into at least one data phase, and executing the following steps aiming at the historical operating data of each data phase: extracting a plurality of first feature sets from the historical operating data, wherein each first feature set corresponds to a time domain feature or a frequency domain feature; performing, for each of the first feature sets: training the data model by using the data in the first feature set to obtain a corresponding baseline model;

the storage unit is used for storing the plurality of baseline models obtained by the training unit.

In a third aspect, an embodiment of the present invention provides an automated guided vehicle operation condition evaluation system, including: an automated guided vehicle and an apparatus for evaluating the operation condition of the automated guided vehicle,

the automatic guided vehicle is used for acquiring current operation data of the automatic guided vehicle in real time and providing the current operation data to the automatic guided vehicle operation condition evaluation device.

One embodiment of the above invention has the following advantages or benefits: the operation data use model generated in the normal operation process by adopting the automatic guided transport vehicle and the operation data use model generated in the abnormal operation process by adopting the automatic guided transport vehicle have obvious difference, so that the current operation condition of the automatic guided transport vehicle can be evaluated by utilizing the current operation data training data model, the use model and the baseline model obtained by the historical operation data training data model, and the possible operation problem of the automatic guided transport vehicle can be found in time.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

fig. 1 is a schematic view of a main flow of an automated guided vehicle operation condition evaluation method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a main process flow for training out a baseline model according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a main flow of training a data model with current operating data according to an embodiment of the invention;

FIG. 4 is a schematic diagram of a main flow of a pre-treatment step according to an embodiment of the invention;

FIG. 5 is a schematic diagram of a main flow of determining an operational status of a data point according to an embodiment of the present invention;

FIG. 6 is a schematic illustration of a main flow of determining an operational status of a data point according to another embodiment of the present invention;

FIG. 7 is a schematic illustration of different data phases demarcated from run data over time, in accordance with an embodiment of the present invention;

FIG. 8 is a schematic diagram of a main flow of extracting a plurality of feature sets according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of a main flow of calculating a health assessment value for an automated guided vehicle according to an embodiment of the present invention;

FIG. 10 is a schematic diagram of a feature baseline model and an example of a feature baseline model according to an embodiment of the invention;

fig. 11 is a schematic diagram of the main units of the automated guided vehicle operation condition evaluation apparatus according to the embodiment of the present invention;

FIG. 12 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

fig. 13 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

An automated guided vehicle generally refers to a device that can travel along a predetermined route to transport items from one location to another.

For example, in automated warehouses, Automated Guided Vehicles (AGVs) have been widely used in cargo handling scenarios. The equipment has complex structure, expensive manufacturing cost and high maintenance cost. Generally, the machine needs to be stopped during maintenance or overhaul, equipment is removed from a working site, and the operation on the site is greatly influenced. If the health state of the equipment can be evaluated, the decline or fault symptom of the equipment can be found in advance, the equipment with poor state can be maintained and maintained in advance, the influence on field operation can be effectively reduced, and the service life of the equipment can be obviously prolonged.

The difference exists between the operation data generated by the automatic guided vehicle in the normal operation process and the operation data generated by the automatic guided vehicle in the abnormal operation process, however, because the operation data has too many dimensions, and the rule of the difference between the operation data is difficult to find or capture, the purpose of standardizing the data with multiple dimensions of the operation data can be achieved through the data model, and therefore, the result can be more definite through the data model.

Based on this, in the following embodiments of the present invention, the current operating condition of the automated guided vehicle is evaluated using the obtained current operating data usage model of the automated guided vehicle and the baseline model trained from the historical operating data.

Fig. 1 is a method for evaluating an operation status of an automated guided vehicle according to an embodiment of the present invention, and as shown in fig. 1, the method for evaluating an operation status of an automated guided vehicle may include the following steps:

s101: acquiring current operation data of the automatic guided vehicle;

s102: training a data model by using current operation data to obtain a use model;

s103: the current operating conditions of the automated guided vehicle are evaluated using the usage model and a stored baseline model, wherein the baseline model is derived from a historical operating data training data model.

The current operation data may be operation data operating within a set time period.

The historical operating data corresponding to the baseline model may be operating data generated by normal operation or abnormal operation of the automated guided vehicle.

The data model can be selected from existing models which can be trained, such as a Gaussian mixture model.

In the embodiment shown in fig. 1, there is a significant difference between the operation data usage model generated by the automated guided vehicle in the normal operation process and the operation data usage model generated by the automated guided vehicle in the abnormal operation process, so that the current operation condition of the automated guided vehicle can be evaluated by using the current operation data to train the data model to obtain the usage model and the baseline model obtained from the historical operation data to train the data model, so that the possible operation problem of the automated guided vehicle can be found in time.

Generally, vibration of the automated guided vehicle during operation is one of important contents for performing an evaluation of an operation condition (e.g., the normal or healthy state of the automated guided vehicle, or an abnormal state of the automated guided vehicle), wherein both the displacement and the speed of the vibration reflect the operation state of the automated guided vehicle. The acquisition of the operating data of the automated guided vehicle can be carried out by means of the prior art. For example, an automated guided vehicle is generally equipped with an Inertial Measurement Unit (IMU), which is a device capable of measuring three-axis attitude angles (or angular velocities) and accelerations of a device (the automated guided vehicle) on which the IMU is located, and can be used for a navigation control algorithm of the automated guided vehicle, and the like. Then, the vibration data of the equipment, such as the acceleration, the angular acceleration and the like of the automated guided vehicle can be obtained by collecting the data of the IMU, and the vibration data of the equipment can be used as the operation data of the automated guided vehicle. The frequency of acquisition of the operating data of the automated guided vehicle is high, typically 100 times/second.

Therefore, the specific implementation manner of S101 may be to establish communication with the automated guided vehicle or the IMU, and directly receive real-time operation data sent by the IMU in the automated guided vehicle or collect operation data for a certain period of time (e.g., 30min, 60min, etc.); the method can also be implemented by collecting operation data of a period of time detected by an IMU in the automated guided vehicle and then sending the collected operation data to a device or equipment implementing the method for evaluating the operation condition of the automated guided vehicle through the terminal.

For example, for an AGV, the current operational data or historical operational data may include: the method comprises the steps of collecting data time (accurate to millisecond), AGV running time length, actual speeds of a left wheel and a right wheel, AGV position and head direction, acceleration of a gyroscope XYZ and angular acceleration of three axes. In particular, the historical data may include operational data for a plurality of AGVs that perform better, as well as operational data for AGVs that perform less well or are used for a longer period of time. The historical operating data provided by the AGVs can be the operating data corresponding to the normal operating state or the operating data corresponding to the abnormal operating state, regardless of the AGVs with better performance or the AGVs with worse performance or long service life.

In addition, it should be noted that the automated guided vehicle may go through a straight-ahead stage, a turning stage, and the like during the operation, and the current operation data or the historical operation data used in the embodiments of the present invention are the operation data of the automated guided vehicle in the straight-ahead stage. Because the interference factors received by the automatic guided vehicle in the straight-going stage are the least, the accuracy of evaluation can be effectively improved by selecting the operation data in the straight-going stage.

For S103 described above, the current operating conditions of the automated guided vehicle may be evaluated by comparing the difference between the usage model and the stored baseline model. When the historical operation data is derived from operation data corresponding to abnormal operation states of a plurality of automatic guided vehicles, the smaller the difference between the used model and the stored baseline model is, the higher the possibility that the current operation condition of the automatic guided vehicle is abnormal is the evaluation result; when the historical operation data is derived from operation data corresponding to normal operation states of a plurality of automated guided vehicles, the smaller the difference between the usage model and the stored baseline model, the greater the likelihood that the evaluation result is that the current operation condition of the automated guided vehicle is normal.

The accuracy of the evaluation result can be directly or indirectly influenced by the current operation data processing, the historical operation data processing, the process of obtaining the baseline model by adopting the historical operation data training data model and the process of obtaining the use model by adopting the current operation data training data model. Specific embodiments given in various embodiments of the present invention are discussed in detail below to effectively improve the accuracy of the evaluation result.

In an embodiment of the present invention, as shown in fig. 2, the method for evaluating the operation condition of the automated guided vehicle may further include the steps of:

s201: acquiring historical operation data of a plurality of automatic guided vehicles;

s202: dividing historical operating data into at least one data phase;

s203: performing for the historical operating data of each data phase: extracting a plurality of first feature sets from historical operating data, wherein each first feature set corresponds to a time domain feature or a frequency domain feature;

s204: performing, for each first feature set: training the data model by using data in the first characteristic set to obtain a corresponding baseline model;

s205: a plurality of baseline models are stored.

It should be noted that the steps shown in fig. 2 may be performed before the step of obtaining the current operation data of the automated guided vehicle, and the stored baseline models may be directly called in the subsequent evaluation process; in addition, the steps given in fig. 2 may be executed before step S103, or may be executed in synchronization with step S101 or step S102.

The specific implementation of step 201 may be to directly receive the operation data sent by the multiple automated guided vehicles as historical operation data; historical operating data of a plurality of automated guided vehicles transmitted by the receiving terminal may also be used.

In addition, the above embodiment may further include screening out erroneous operation data (the erroneous data refers to data that is significantly different from other operation data), and may also include further dividing the historical operation data to ensure the accuracy of the baseline model. In addition, because the relevance between different features (any one of time domain features or frequency domain features) is difficult to determine, and the accuracy of a reference model trained by historical operating data including a plurality of time domain features or frequency domain features is low, and the real condition is difficult to accurately reflect.

At least one data phase divided in step S202 may be divided according to the operation states (deceleration state, uniform speed state, acceleration state) corresponding to the historical operation data, and the at least one data phase may include: any one or more of a data stage corresponding to a deceleration state, a data stage corresponding to a uniform speed state and a data stage corresponding to an acceleration state.

The time domain feature is any one or more of a mean value obtained by using operation data (historical operation data or current operation data), a mean value after an absolute value is taken, a peak-to-peak value, a standard deviation, a root mean square value, a peak value, a waveform index, a peak index, a pulse index, a margin index, a skewness index and a kurtosis index.

The frequency domain features refer to the features determined by calculating the amplitude values after fourier transform at each data stage and determining the amplitude values, and may include any one or more features of mean, standard deviation, variance, skewness and margin.

Corresponding to the training of a plurality of baseline models (each corresponding to a feature), as shown in fig. 3, the following steps may be performed on the current operation data obtained in step S101:

s301: dividing current operation data into at least one data phase;

s302: executing, for the current running data of each data phase: extracting a plurality of second feature sets from the current data, wherein feature categories corresponding to the second feature sets correspond to feature categories corresponding to the first feature sets in a one-to-one manner;

s303: performing, for each second feature set: the data model is trained using the data in the second feature set.

The feature category refers to a feature category corresponding to each feature included in the time domain features and a feature category corresponding to each feature included in the frequency domain features, for example, the feature category corresponding to the mean feature in the frequency domain features may be a frequency domain mean category, and the feature category corresponding to the mean feature in the time domain features may be a time domain mean category.

It should be noted that what is obtained by training in step S303 is the usage model corresponding to each second feature set, and since the second feature set corresponds to one feature class, the features or feature classes correspond to the usage models one to one. For example, the mean feature or the frequency domain mean category in the frequency domain features corresponds to one usage model, and the mean feature or the time domain mean category in the time domain features corresponds to another usage model.

The steps given in fig. 3 are used to divide the current operating data into a second feature set (where the first feature set is a feature data set including historical operating data, and the second feature set is a feature data set including current operating data), and train a data model for each time domain feature or frequency domain feature to obtain a usage model. The baseline model corresponding to each time domain feature or frequency domain feature is conveniently compared, and therefore the accuracy of evaluation is further guaranteed.

In an embodiment of the present invention, as shown in fig. 4, the step of dividing into at least one data phase in step S202 and/or step S302 may include the following steps:

s401: determining a motion state indicated by each data point in the historical operation data and/or the current operation data, wherein the motion state comprises any one of a deceleration state, a uniform speed state and an acceleration state;

s402: and dividing at least one data phase for the historical operating data and/or the current operating data according to the motion state indicated by each data point, wherein the data included in each data phase indicates the same motion state.

There are two specific embodiments of the step S401.

The first embodiment: as shown in FIG. 5, determining the operating state of each data point based on the speed at which each data point includes may include the steps of:

steps S501 to S503 are performed for each data point in the historical operating data and/or the current operating data, and after the operating status of each data point in all the historical operating data and/or the current operating data is determined over a period of time, step S504 is performed to determine the operating status of each data point.

S501: calculating the uniform speed of the data points, and selecting a preset first number of data points before and after the data points according to the time sequence of the acquisition of the data points;

for example, a certain data point d in the collected historical operation data or current operation data of the AGV_iSelecting n data points before and after the data point and marking as w_b，w_a(wherein, w_bBy being located at a data pointd_iThe previous n data points; w is a_aBy being located at the data point d_iThe next n data points); i.e. w_b，w_aEach of the n data points includes n data points strictly ordered according to the time of acquisition, and the data points may include only the speed data, and may also include other data, and only the speed data of the data points is considered in the embodiment of the present invention. Because the collected historical operating data and/or the current operating data have two speeds v of the left wheel and the right wheel_l，v_rThe unified velocity v of each data point can be calculated by the calculation formula (1):

calculating formula (1):

wherein v represents the uniform velocity of a data point; v. of_lCharacterizing a left wheel speed for a data point; v. of_rThe right wheel speed of one data point is characterized.

The preset first number of users can be flexibly set according to own requirements.

S502: respectively calculating the maximum value and the minimum value of the data points of the preset first number before and after;

for example, calculate w_bRespectively is w_bmax，w_bmin；w_aRespectively is w_amax，w_amin。

S503: comparing the maximum value and the minimum value in the preset first number of data points before and after, and preliminarily determining the initial operation state of the data points according to the comparison result;

for example, if w_bmax≤w_aminAnd w_bmin≠w_amaxThen the data point d is considered_iIn an acceleration phase; if w_bmin≥w_amaxAnd w_bmax≠w_aminThen the data point d is considered_iIn a deceleration phase; if w_bmin＝w_amax＝w_bmax＝w_aminThen the data point d is considered_iAt a constant speed stage.

S504: the final operating state of the data points is adjusted using a mode of the initial operating state of a preset second number of data points after the data points.

This step is to smooth each data point. For example, for data point d_iUsing m data points [ d ] after the data point_i+1....d_i+m]As the mode of the initial state identification of data point d_iThe final motion state.

The second embodiment: as shown in fig. 6, the step of determining the operation state of each data point based on the acceleration (acceleration of XYZ three axes) included in each data point may include:

s601: according to the time sequence of the collection of the data points, a third number of data points are selected from the front and the back of the data points;

for example, for a certain data point dj in the collected historical operating data or current operating data of the AGV, N data points before and after the data point are selected and respectively marked as W_b，W_a(wherein, W_bBy being located at the data point d_jThe previous N data points; w_aBy being located at the data point d_jThe next N data points); i.e. W_b，W_aEach of the N data points includes N data points strictly ordered according to the time of acquisition, and the data points may include only velocity data, and may also include other data, and only acceleration data of XYZ three axes of the data points is considered in the embodiment of the present invention.

And the preset third number of users can be flexibly set according to own requirements.

S602: preliminarily determining the initial running state of the data point according to the acceleration of the data point;

for example, if a_x< 0 and a_y< 0 and a_zIf < 0, the data point d is considered_jIn a deceleration phase; if a_x> 0 and a_y> 0 and a_zIf > 0, the data point d is considered_jIn an acceleration phase; if a_x0 and a_y0 and a_zIf 0, the data point d is considered_jAt a constant speed stage. If a_x、a_yAnd a_zOne or two of the acceleration data are less than 0, and the other acceleration data are greater than or equal to 0, then the true acceleration value corresponding to the acceleration with larger absolute value is selected, and the data point d is determined_jIn the phase (c). For example, if the true acceleration value corresponding to the acceleration with a larger absolute value is smaller than 0, the data point d is_jIn a deceleration phase; for example, if the true acceleration value corresponding to the acceleration with a larger absolute value is greater than 0, the data point d is_jIn the acceleration phase. Wherein, a_xRepresenting the acceleration corresponding to the X axis; a is_yRepresenting acceleration corresponding to the Y axis; a is_zAnd characterizing the acceleration corresponding to the Z axis.

S603: the final operating state of the data points is adjusted using a mode of the initial operating state of a preset fourth number of data points after the data points.

This step is to smooth each data point. For example, for data point d_jUsing M data points [ d ] after this data point_j+1....d_j+m]As the mode of the initial state identification of data point d_jThe final motion state.

Based on the technical scheme given by the above-mentioned fig. 5 or fig. 6, the final motion state of each data point is obtained. Based on the motion state, a straight-going operation can be divided into different data stages (a deceleration stage, an acceleration stage and a constant speed stage, wherein the operation state of each data point in the deceleration stage is a deceleration state, the operation state of each data point in the acceleration stage is an acceleration state, and the operation state of each data point in the constant speed stage is a constant speed state).

After the operation data of a period of time is processed by the embodiment shown in fig. 5, the obtained result can be shown in a graph, for example, the result of dividing the operation data of a period of time into different data phases shown in fig. 7. Wherein fig. 7-1 is an acceleration stage, fig. 7-2 is a uniform speed stage, fig. 7-3 is a deceleration stage, and fig. 7-4 is an acceleration of the acceleration stage corresponding to fig. 7-1; 7-5 are accelerations corresponding to the acceleration phase of FIG. 7-2; fig. 7-6 illustrate acceleration during the acceleration phase corresponding to fig. 7-3.

Because the data training data models in different stages (deceleration, uniform speed and acceleration) have certain differences, the historical operating data and/or the current operating data are divided into different stages, generally, the more concentrated the data are, the more consistent the data characteristics are, and the higher the accuracy of the obtained use model is, therefore, in the embodiment of the invention, the data models are trained according to the stages and the various characteristics included in the frequency domain characteristics and/or the time domain characteristics, and the accuracy of the baseline model obtained based on the historical operating data and the accuracy of the use model obtained based on the current operating data can be further ensured.

In an embodiment of the present invention, as shown in fig. 8, the above steps (step S203 extracting a plurality of first feature sets from historical operating data, step S302 extracting a plurality of second feature sets from current operating data) related to extracting a plurality of feature sets may include the following steps:

for each data phase, performing:

s801: extracting a plurality of time domain characteristics and a plurality of frequency domain characteristics by using data in the data stage;

for historical operating data, the data in the data stage refers to the historical operating data belonging to the data stage (acceleration stage, constant speed stage, deceleration stage); for the current operation data, the data in the data phase refers to the current operation data belonging to the data phase (acceleration phase, uniform velocity phase, deceleration phase).

Respectively extracting time domain characteristics and frequency domain characteristics from the actual speeds of a left wheel and a right wheel, the accelerations of three axes of gyroscope XYZ and the angular accelerations of the three axes which are included by data points in a data stage, wherein the total of the actual speeds, the accelerations of the three axes of gyroscope XYZ and the angular accelerations of the three axes are 8 dimensions:

the time domain features may include: mean, mean after absolute value, peak, standard deviation, root mean square value, peak, waveform index, peak index, pulse index, margin index, skewness index, kurtosis index, and the like. For example, the mean value of the z-axis acceleration after taking the absolute value, the time domain mean value of the y-axis acceleration, the mean value of the x-axis acceleration after taking the absolute value, the mean value of the x-axis acceleration, the mean value of the y-axis acceleration after taking the absolute value, and the like.

The frequency domain features refer to amplitude values of data in a data phase after Fourier transformation, and features obtained through the amplitude values. The frequency domain features may include: mean, standard deviation, variance, skewness, margin, and the like. For example, the y-axis angular acceleration spectrum mean, the x-axis acceleration root mean square value, the y-axis acceleration root mean square, the z-axis angular acceleration spectrum mean, the z-axis angular acceleration deflection, the x-axis angular acceleration variance, the x-axis angular acceleration spectrum mean, and the like.

The time domain features and the frequency domain features can be obtained by calculation in the existing calculation mode.

S802: selecting a plurality of target features from a plurality of time domain features and a plurality of frequency domain features;

the plurality of target features generally needs to include both time domain features and frequency domain features.

The step can be realized by sorting a plurality of time domain characteristics and a plurality of frequency domain characteristics according to the importance degree of the characteristics through XGboost. XGboost is one of the most common methods currently used to assess feature importance. In the step, according to a plurality of time domain features and a plurality of frequency domain features which are arranged from top to bottom in importance degree, the feature which is ranked at the top 20% is selected as the target feature.

The plurality of target features selected in this step include: the method comprises the following steps of obtaining a Z-axis acceleration mean value, a Z-axis angular acceleration frequency spectrum mean value, a mean value after the Z-axis acceleration takes an absolute value, a Y-axis acceleration time domain mean value, a mean value after the X-axis acceleration takes an absolute value, an x-axis acceleration mean value, a y-axis acceleration mean value, a mean value after the Y-axis acceleration takes an absolute value, a speed peak value, a Y-axis angular acceleration frequency spectrum mean value, an X-axis acceleration root mean square value, a Y-axis acceleration maximum value minus minimum value, a Y-axis angular acceleration peak value, a Z-axis angular acceleration frequency spectrum mean value, a Z-axis angular acceleration skewness, an X-axis angular acceleration variance, an X-axis angular acceleration frequency spectrum mean value, an X-axis acceleration maximum value minus minimum value and an X-axis acceleration direct-current component.

S803: and forming a corresponding feature set by using the data corresponding to each target feature, wherein the feature set is a first feature set when the data in the data stage is historical operating data, and the feature set is a second feature set when the data in the data stage is current operating data.

By selecting the time domain features and/or the frequency domain features for training the data model, on one hand, the problem of insufficient computing resources caused by excessive features can be avoided, and on the other hand, the accuracy of the obtained use model and the baseline model can be ensured through the selection.

In one embodiment of the present invention, the step of evaluating the current operating condition of the automated guided vehicle may include: calculating a health assessment value of the automated guided vehicle using the usage model and the stored baseline model; when the health assessment value does not satisfy the preset health condition, it is determined that there is a problem with the current operation of the automated guided vehicle.

Wherein the health condition may include: when the historical operation data is derived from the automatic guided vehicle in a good condition, the health assessment value is not lower than a preset first health threshold value; when the historical operation data is derived from the automatic guided vehicle with poor conditions (such as the problem of parts), the health assessment value is not higher than a preset second health threshold value; wherein the first health threshold and the second health threshold can be set according to the actual needs of the user.

Based on this, the health assessment value not meeting the preset health condition means that the health assessment value is lower than a first health threshold value when the historical operation data is derived from the well-conditioned automated guided vehicle; the health assessment value is above a preset second health threshold when historical operating data is derived from a poorly conditioned (e.g., part-problematic) automated guided vehicle.

The process of training the data model is to train the data model by using the data in each second feature set, and then, the features of each first feature set correspondingly obtain a usage model, that is:

using a set of models S_new＝{pdf_c1，pdf_c2...pdf_cu}; wherein S is_newRespectively training the data model by adopting a plurality of second characteristic sets to obtain a use model set; pdf (pdf)_ctCharacterizing usage model setsA usage model corresponding to the t-th target feature (the usage model corresponding to the t-th target feature is obtained by a second feature set training data model corresponding to the t-th target feature), wherein the value of t is 1, 2,. u; u represents the total number of the target features selected in the step S802.

The process of obtaining the baseline model is to train the data model by using the data in each first feature set, so that the features of each first feature set correspond to one baseline model, that is:

set of baseline models S_base＝{pdf₁，pdf₂...pdf_u}; wherein S is_baseRespectively training a data model by using data in a plurality of first characteristic sets to obtain a baseline model set; pdf (pdf)_tCharacterizing a baseline model corresponding to a tth target feature in a baseline model set (the baseline model corresponding to the tth target feature is obtained by a first feature set training data model corresponding to the tth feature), wherein the value of t is 1, 2,. u; u represents the total number of the target features selected in the step S802.

In the embodiment of the invention, the preset data model is a probability density function of a Gaussian mixture model.

The basic calculation formula of the probability density function of the gaussian mixture model is shown in the following calculation formula (2).

Wherein the pdf is_dProbability density function corresponding to the d type of target feature; mu.s_dMean, σ, of feature set corresponding to characterization d-th target feature_dCharacterizing the standard deviation of a feature set corresponding to the d-th target feature; x is the number of_dkCharacterizing the kth value in a feature set corresponding to the d-th target feature; p represents the total number of data contained in the feature set corresponding to the d-th target feature. When the feature set comes from historical operating data, then the pdf₁，pdf₂...pdf_uObtained from the above calculation formula (2); when the feature set is derived from the current operating data, then the pdf_c1，pdf_c2...pdf_cuObtained from the above calculation formula (2).

Namely: the usage model may be multiple (e.g., S)_newA plurality of usage models included in (1) are

pdf_c1，pdf_c2...pdf_cu) Wherein each usage model corresponds to a target feature; the stored baseline model may also be multiple (e.g., S)_baseMultiple baseline models included

pdf₁，pdf₂...pdf_u) Each baseline model corresponds to one target feature, and the plurality of baseline models are matched with the target features corresponding to the plurality of usage models one by one; accordingly, as shown in fig. 9, the calculating of the health assessment value of the automated guided vehicle may include:

for each usage model, performing:

s901: matching the corresponding target baseline model for the use model according to the characteristic category corresponding to the use model;

for example, to use a model pdf_c1Matching corresponding baseline model pdfs₁To use the model pdf_cuMatching corresponding baseline model pdfs_uAnd the like.

S902: calculating a characteristic health evaluation value by using the use model and the target baseline model;

s903: a health assessment value is calculated using the plurality of characteristic health assessment values.

Fig. 10 shows the relationship between a certain baseline model and a matching usage model based on the probability density function of the gaussian mixture model. In fig. 10, the dark color area (I) is a baseline model, and the light color area (II) is a usage model, and it can be seen that the trend between the baseline model and the usage model is substantially consistent, but there is a gap between the covered area or edge.

Based on the baseline model and the usage model example given in fig. 10, the above step S902 can be implemented in two specific embodiments.

The first embodiment:

the characteristic health assessment value is calculated using the intersection area between the baseline model and the usage model.

For example, the maximum value and the minimum value obtained by the baseline model corresponding to the tth target feature are respectively recorded as: b_tmax，b_tminThe probability density function is pdf_t. The probability density function of the usage model corresponding to the t-th target feature is pdf_ctThe maximum and minimum values in the usage model are respectively noted as: c. C_tmax，c_tmin。

If b is_tmin≥c_tmaxOr b_tmax≤c_tminTwo models are explained

(the baseline model corresponding to the tth target feature and the usage model corresponding to the tth target feature) do not intersect in data representation, and the feature health assessment value HI corresponding to the tth target feature_t＝0。

If there is an intersection between the two models (the baseline model corresponding to the tth target feature and the usage model corresponding to the tth target feature) in the data representation (b)_tmin＜c_tmaxAnd b is_tmax＞c_tmin) The characteristic health evaluation value is calculated using the following calculation formula (3).

Calculation formula (3):

wherein the content of the first and second substances,

characterizing pdf_tIn the interval [ b_min，b_max]The area of the inner;

characterizing pdf_t，pdf_ctIn the interval [ b_min，b_max]The overlap area within; HI (high-intensity)_tAnd characterizing the characteristic health assessment value corresponding to the t-th target characteristic.

Second embodiment:

based on the distance between the two probability density functions, a feature health assessment value is calculated.

For example, the probability density function corresponding to the baseline model corresponding to the tth target feature is pdf_t. The probability density function of the usage model corresponding to the t-th target feature is pdf_ctThe characteristic health evaluation value is calculated using the following calculation formula (4).

Calculating formula (4):

wherein x represents a feature value of a data point in the first feature set corresponding to the tth target feature or a feature value of a data point in the second feature set corresponding to the tth target feature; x represents the combination of a first feature set corresponding to the tth target feature and a second feature set corresponding to the tth target feature; pdf (pdf)_t(x) Representing a probability density function corresponding to a baseline model corresponding to the tth target characteristic; pdf (pdf)_ct(x) Representing a probability density function corresponding to the use data model corresponding to the tth target feature; HI (high-intensity)_tCharacterizing a characteristic health assessment value corresponding to the tth target characteristic; it is worth mentioning that for pdf_t(x) For example, x is a feature value of a data point in the first feature set corresponding to the tth target feature; for pdf_ct(x) In other words, x is the feature value of the data point in the second feature set corresponding to the tth target feature.

The above step S903 may be realized by the following calculation formula (5).

Calculating formula (5):

h represents a health assessment value; u represents the total number of the target features selected in the step S802.

Generally, when historical operating data is derived from an automated guided vehicle with good operating conditions, the health assessment value is larger, which indicates that the health state of each component or part of the automated guided vehicle is better, and the overall performance is better; when the historical operation data is derived from the automatic guided vehicle with the problem of operation conditions, the smaller the health evaluation value is, the better the health state of each component or part of the automatic guided vehicle is, and the better the overall performance is.

In one embodiment of the present invention, the automated guided vehicle operation condition evaluation method may further include: when the current running condition indicates that the running of the automatic guided vehicle has a problem, generating warning information; warning information is provided to maintenance personnel to maintain the automated guided vehicle and/or replace the automated guided vehicle.

The above-described embodiments are applicable to a carrier robot, a meal delivery robot, and the like, in addition to the automated guided vehicle.

It should be noted that the historical operation data may be derived from an automated guided vehicle with good operation conditions or from an automated guided vehicle with a problem in operation conditions. Preferably, the historical operating data is derived from well-performing automated guided vehicles. Different baseline models are tested through test data, and the baseline model trained from historical operation data of the automatic guided vehicle with good operation condition is found to be more accurate.

As shown in fig. 11, an embodiment of the present invention provides an automatic guided vehicle operation condition evaluation apparatus 1100, where the automatic guided vehicle operation condition evaluation apparatus 1100 may include: an acquisition unit 1101, a training unit 1102, and an evaluation unit 1103, wherein,

an acquisition unit 1101 for acquiring current operation data of the automated guided vehicle;

a training unit 1102, configured to train a training data model by using the current operation data acquired by the acquisition unit 1101, so as to obtain a usage model;

an evaluation unit 1103 configured to evaluate the current operating condition of the automated guided vehicle using the usage model obtained by the training unit 1102 and a stored baseline model, where the baseline model is obtained from a historical operating data training data model.

In one embodiment of the present invention, the automated guided vehicle operation condition evaluation apparatus may further include: a storage unit (not shown in the drawings) in which,

a training unit 1102, further configured to obtain historical operating data of the automated guided vehicles; dividing the historical operating data into at least one data phase, and executing the following steps aiming at the historical operating data of each data phase: extracting a plurality of first feature sets from the historical operating data, wherein each first feature set corresponds to a time domain feature or a frequency domain feature; performing, for each of the first feature sets: training the data model by using the data in the first feature set to obtain a corresponding baseline model;

a storage unit (not shown in the figure) for storing the plurality of baseline models obtained by the training unit 1102.

In an embodiment of the present invention, the training unit 1102 is further configured to divide the current operation data into at least one data phase; executing, for the current running data of each data phase: extracting a plurality of second feature sets from the current data, wherein feature categories corresponding to the second feature sets correspond to feature categories corresponding to the first feature sets in a one-to-one manner; performing for each second feature set: the data model is trained using the data in the second feature set.

In an embodiment of the present invention, the training unit 1102 is configured to determine a motion state indicated by each data point in the historical operating data and/or the current operating data, where the motion state includes any one of a deceleration state, a uniform speed state, and an acceleration state; and dividing at least one data phase for the historical operating data and/or the current operating data according to the motion state indicated by each data point, wherein the data included in each data phase indicates the same motion state.

In an embodiment of the present invention, the training unit 1102 is configured to perform, for each data phase: extracting a plurality of time domain characteristics and a plurality of frequency domain characteristics by using data in the data stage; selecting a plurality of target features from a plurality of time domain features and a plurality of frequency domain features; and forming a corresponding feature set by using the data corresponding to each target feature, wherein the feature set is a first feature set when the data in the data stage is historical operating data, and the feature set is a second feature set when the data in the data stage is current operating data.

In an embodiment of the invention, the evaluation unit 1103 is configured to calculate a health evaluation value of the automated guided vehicle using the usage model and the stored baseline model; when the health assessment value does not satisfy the preset health condition, it is determined that there is a problem with the current operation of the automated guided vehicle.

The number of models used in one embodiment of the present invention is plural; the number of the baseline models is multiple; wherein the feature classes of the plurality of feature usage models correspond one-to-one to the feature classes of the plurality of baseline models; an evaluation unit 1103 configured to, for each usage model, perform: matching the corresponding target baseline model for the use model according to the characteristic category corresponding to the use model; calculating a characteristic health evaluation value by using the use model and the target baseline model; a health assessment value is calculated using the plurality of characteristic health assessment values.

In an embodiment of the present invention, the automated guided vehicle operation condition evaluation apparatus 1100 further includes:

an alarm unit (not shown in the drawings) for generating alarm information when the current operation condition indicates that there is a problem in the operation of the automated guided vehicle; warning information is provided to maintenance personnel to maintain the automated guided vehicle and/or replace the automated guided vehicle.

One embodiment of the present invention provides an automated guided vehicle operation condition evaluation system (not shown), which includes: a plurality of automated guided vehicles and the apparatus for evaluating the operation status of an automated guided vehicle according to any of the above embodiments, wherein,

the automatic guided vehicle is used for acquiring the current operation data of the automatic guided vehicle in real time and providing the current operation data to the automatic guided vehicle operation condition evaluation device.

Fig. 12 illustrates an exemplary system architecture 1200 to which the automated guided vehicle operation condition evaluation method or the automated guided vehicle operation condition evaluation apparatus of the embodiments of the present invention can be applied.

As shown in fig. 12, the system architecture 1200 may include

terminal devices

1201, 1202, 1203, a network 1204, a server 1205, and automated guided

vehicles

1206, 1207. The network 1204 is used to provide the medium for communication links between the

terminal devices

1201, 1202, 1203 and the server X05, between the automated guided

vehicles

1206, 1207 and the server 1205, between the automated guided

vehicles

1206, 1207 and the

terminal devices

1201, 1202, 1203. Network 1204 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.

A user may use

terminal devices

1201, 1202, 1203 to interact with a server 1205 through a network 1204 to receive or send messages, etc. The

terminal devices

1201, 1202, 1203 may have installed thereon various messenger client applications such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).

The

terminal devices

1201, 1202, 1203 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 1205 may be a server that provides automated guided vehicle operation condition evaluation services, such as a background management server that provides analytical support for current operation data generated by the automated guided

vehicles

1206, 1207, and may also provide support for historical operation data sent by users using the

terminal devices

1201, 1202, 1203 (for example only). The background management server may analyze and perform other processing on the received data such as the historical operating data and the current operating data, and feed back a processing result (for example, the early warning information and the evaluation result — only an example) to the terminal device.

It should be noted that the method for evaluating the operation status of the automated guided vehicle provided by the embodiment of the present invention is generally executed by the server 1205, and accordingly, the apparatus for evaluating the operation status of the automated guided vehicle is generally disposed in the server 1205.

It should be understood that the number of terminal devices, networks, servers, and automated guided vehicles in fig. 12 are merely illustrative. There may be any number of terminal devices, networks, servers, and automated guided vehicles, as desired for implementation.

Referring now to FIG. 13, shown is a block diagram of a computer system 1300 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 13 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.

As shown in fig. 13, the computer system 1300 includes a Central Processing Unit (CPU)1301 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)1302 or a program loaded from a storage section 1308 into a Random Access Memory (RAM) 1303. In the RAM 1303, various programs and data necessary for the operation of the system 1300 are also stored. The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input/output (I/O) interface 1305 is also connected to bus 1304.

The following components are connected to the I/O interface 1305: an input portion 1306 including a keyboard, a mouse, and the like; an output section 1307 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1308 including a hard disk and the like; and a communication section 1309 including a network interface card such as a LAN card, a modem, or the like. The communication section 1309 performs communication processing via a network such as the internet. A drive 1310 is also connected to the I/O interface 1305 as needed. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1310 as necessary, so that a computer program read out therefrom is mounted into the storage portion 1308 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications component 1309 and/or installed from removable media 1311. The computer program executes the above-described functions defined in the system of the present invention when executed by a Central Processing Unit (CPU) 1301.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

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

The units described in the embodiments of the present invention may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a training unit, and an evaluation unit. The names of the units do not in some cases constitute a limitation on the units themselves, and for example, the acquisition unit may also be described as a "unit that acquires current operation data of the automated guided vehicle".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: acquiring current operation data of the automatic guided vehicle; training a data model by using current operation data to obtain a use model; the current operating conditions of the automated guided vehicle are evaluated using the usage model and a stored baseline model, wherein the baseline model is derived from a historical operating data training data model.

According to the technical scheme of the embodiment of the invention, the operation data use model generated by the automatic guided transport vehicle in the normal operation process is obviously different from the operation data use model generated by the automatic guided transport vehicle in the abnormal operation process, so that the current operation condition of the automatic guided transport vehicle can be evaluated by utilizing the current operation data training data model and the use model and the baseline model obtained by the historical operation data training data model, and the possible operation problems of the automatic guided transport vehicle can be found in time.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An evaluation method for the operation condition of an Automated Guided Vehicle (AGV), comprising:

acquiring current operation data of the automatic guided vehicle;

2. The automated guided vehicle operation condition evaluation method according to claim 1, characterized by further comprising:

dividing the historical operating data into at least one data phase;

storing a plurality of the baseline models.

3. The automated guided vehicle operation condition evaluation method according to claim 2,

dividing the current operating data into at least one data phase;

the step of training a data model using the current operating data comprises:

4. The automated guided vehicle operation condition evaluation method according to claim 3, wherein the step of dividing into at least one data phase comprises:

5. The automated guided vehicle operation condition evaluation method according to claim 4, wherein the step of extracting a plurality of first feature sets and/or a plurality of second feature sets, which is performed for each of the data phases, includes:

for each of the data phases, performing:

6. The automated guided vehicle operation condition evaluation method according to claim 1, wherein the evaluating the current operation condition of the automated guided vehicle step comprises:

7. The automated guided vehicle operation condition evaluation method according to claim 6,

the number of the usage models is multiple;

the number of the baseline models is multiple;

for each of the usage models, performing:

8. The automated guided vehicle operation condition evaluation method according to any one of claims 1 to 7, characterized by further comprising:

9. An automated guided vehicle operation condition evaluation device, comprising: an acquisition unit, a training unit and an evaluation unit, wherein,

10. The automated guided vehicle operation condition evaluation device according to claim 9, characterized by further comprising: a memory cell, wherein,

11. An automated guided vehicle operation condition evaluation system, comprising: an automated guided vehicle and the automated guided vehicle operation condition evaluation device according to claim 9 or 10, wherein,

12. An automated guided vehicle operation condition evaluation electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.

13. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-8.