CN113655240B - Cargo falling posture recognition method and system - Google Patents
Cargo falling posture recognition method and system Download PDFInfo
- Publication number
- CN113655240B CN113655240B CN202111042913.6A CN202111042913A CN113655240B CN 113655240 B CN113655240 B CN 113655240B CN 202111042913 A CN202111042913 A CN 202111042913A CN 113655240 B CN113655240 B CN 113655240B
- Authority
- CN
- China
- Prior art keywords
- acceleration
- vector
- axis
- value
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P15/00—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
- G01P15/18—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration in two or more dimensions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a cargo falling posture identification method, which comprises the steps of obtaining triaxial acceleration information when a cargo falls, and carrying out vector synthesis on the triaxial acceleration to obtain vector acceleration; determining an impact section when the cargo falls based on the vector acceleration; acquiring the triaxial acceleration of an impact section, and calculating the ratio of the acceleration average value of each axis in the impact section to the square sum root of the triaxial acceleration average value based on the triaxial acceleration of the impact section; and determining the falling attitude of the cargo according to the ratio of the average acceleration value of each axis to the square sum root of the average acceleration values of the three axes. The cargo falling posture identification method can effectively identify the cargo falling posture in the bag transportation process, and is favorable for making a more reasonable scheme for examining the product strength and the buffering packaging performance.
Description
Technical Field
The invention belongs to the field of cargo transportation, and particularly relates to a cargo falling posture identification method and system.
Background
The product can go through links such as storage, transport and transportation from leaving the factory to the seller, wherein can meet behaviors such as vibration, impact, fall, wherein fall is the leading factor that leads to the product damage, falls the gesture and is the important parameter of formulating laboratory drop test standard. The posture detection and recognition are accurate, and a more reasonable laboratory drop test scheme is favorably made for checking the product strength and the buffering packaging performance, so that the product and packaging structure design is improved, and the transportation loss is reduced.
The present invention has been made in view of this situation.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method and a system for identifying the falling posture of goods, which can effectively identify the falling posture of the goods in the process of package transportation and are beneficial to making a more reasonable scheme for checking the strength and the buffering package performance of products.
In order to solve the technical problem, the invention provides a cargo falling posture identification method, which comprises the steps of
Acquiring triaxial acceleration information when the goods fall, and carrying out vector synthesis on the triaxial acceleration to obtain vector acceleration;
determining an impact section when the cargo falls based on the vector acceleration;
acquiring the triaxial acceleration of an impact section, and calculating the ratio of the acceleration average value of each axis in the impact section to the square sum root of the triaxial acceleration average value based on the triaxial acceleration of the impact section;
and determining the falling attitude of the cargo according to the ratio of the average acceleration value of each axis to the square sum root of the average acceleration values of the three axes.
Further optionally, the determining the impact section when the cargo falls based on the vector acceleration comprises
Determining a vector wave crest of the vector acceleration, and respectively moving to two sides of the vector wave crest along a track of the vector acceleration by taking the vector wave crest as a starting point until point values smaller than the judgment threshold value are respectively found at two sides of the vector wave crest, wherein a wave band between the point values smaller than the judgment threshold value at the two sides of the vector wave crest is the impact section.
Further optionally, when the point values smaller than the determination threshold are not found in the process of moving to the two sides of the vector peak along the track of the vector acceleration, the determination threshold is increased by a set value, and then the vector peak is taken as a starting point again, and the point values smaller than the new determination threshold are found by moving to the two sides of the vector peak along the track of the vector acceleration.
Further optionally, the determination threshold is a value close to a gravitational constant.
Further optionally, the determination threshold is 1.2g to 1.4g, and g is a gravity constant.
Further optionally, the obtaining of the three-axis acceleration of the impact section, and the calculating of the ratio of the average acceleration of each axis in the impact section to the square sum root of the average acceleration of the three axes based on the three-axis acceleration of the impact section include
Respectively acquiring the acceleration of the goods in the X-axis direction, the acceleration of the goods in the Y-axis direction and the acceleration of the goods in the Z-axis direction in the impact section;
respectively calculating the acceleration average values X, Y and Z of the goods in the impact section in the X axis, the Y axis and the Z axis and the square sum root of the three-axis acceleration average values based on the accelerations of the goods in the impact section in the X axis, the Y axis and the Z axis directions
Respectively calculating the ratio X1 of the average acceleration value of the goods in the impact section in the X axis to the square root of the average acceleration value of the three axes, the ratio Y1 of the average acceleration value of the Y axis to the square root of the average acceleration value of the three axes, and the ratio Z1 of the average acceleration value of the Z axis to the square root of the average acceleration value of the three axes, wherein the following conditions are met:
further optionally, the determining the acquired fall posture according to the magnitude of the ratio includes:
determining x1、y1、z1Maximum value of (a)maxMinimum value amidAnd an intermediate value amin；
By comparing said minimum values amidThe minimum value amidAnd said intermediate value aminAnd judging the falling state of the cargo according to the size of the set threshold.
Further optionally, the comparison of the minimum values amidThe minimum value amidAnd said intermediate value aminAnd the falling state of the goods is judged according to the size of the set threshold, and the method comprises the following steps:
when judgingBreak amaxFirst set threshold, amid< second set threshold value, aminIf the number is less than the second set threshold value, judging that the falling state of the goods is surface falling;
when judging amax-amid< a third set threshold, and aminIf the number is less than the fourth set threshold value, judging that the falling state of the goods is arris falling;
when the conditions are not met, judging that the falling state of the goods is angular falling;
wherein the first set threshold > the second set threshold > the third set threshold.
Further optionally, after vector synthesis is performed on the three-axis acceleration to obtain a vector acceleration, filtering processing is also performed on the vector acceleration.
The invention also provides a cargo falling posture recognition system, which comprises:
the data acquisition module is used for acquiring a triaxial acceleration value when the goods fall;
the data processing module is used for carrying out vector synthesis on the three-axis acceleration to obtain a vector acceleration, carrying out filtering processing on the vector acceleration and determining a vector peak of the vector acceleration;
and the algorithm module is used for determining an impact section when the cargo falls off based on the vector acceleration, calculating the ratio of the average acceleration value of each shaft in the impact section to the square sum root of the average acceleration value of the three shafts in the impact section based on the three-shaft acceleration of the impact section, and determining the falling attitude of the cargo according to the ratio of the average acceleration value of each shaft to the square sum root of the average acceleration value of the three shafts.
Further optionally, the cargo fall posture recognition method is adopted.
After adopting the technical scheme, compared with the prior art, the invention has the following beneficial effects:
according to the cargo falling posture identification method and system provided by the invention, the impact signal of the product in the actual transportation environment can be analyzed and calculated, whether the product falls or not is judged, and whether the falling posture is surface falling, edge falling or angle falling is determined by calculating the characteristic value of the impact interval, so that a scheme for more reasonably evaluating the product strength and the buffer packaging performance is favorably worked out.
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention without limiting the invention to the right. It is obvious that the drawings in the following description are only some embodiments, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
fig. 1 and 2: the invention discloses a flow chart of a cargo falling posture identification method;
FIG. 3: is a system operation diagram of an embodiment of the invention;
it should be noted that the drawings and the description are not intended to limit the scope of the inventive concept in any way, but to illustrate it by a person skilled in the art with reference to specific embodiments.
Detailed Description
In the description of the present invention, it should be noted that the terms "inside", "outside", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, which are only for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and operate, and thus, should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," "contacting," and "communicating" are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The product can go through links such as storage, transport and transportation from leaving the factory to the seller, wherein can meet behaviors such as vibration, impact, fall, wherein fall is the leading factor that leads to the product damage, falls the gesture and is the important parameter of formulating laboratory drop test standard. The posture detection and recognition are accurate, and a more reasonable laboratory drop test scheme is favorably made for checking the product strength and the buffering packaging performance, so that the product and packaging structure design is improved, and the transportation loss is reduced. In view of the above problems, the present embodiment provides a cargo fall posture recognition method, as shown in the flowchart of fig. 1, including the following steps:
s1, acquiring triaxial acceleration information when the goods fall, and carrying out vector synthesis on the triaxial acceleration to obtain a vector acceleration;
s2, determining an impact section when the cargo falls on the basis of the vector acceleration;
s3, acquiring triaxial acceleration of the impact section, and calculating the ratio of the acceleration average value of each axis in the impact section to the square sum root of the triaxial acceleration average value based on the triaxial acceleration of the impact section;
and S4, determining the falling attitude of the cargo according to the ratio of the acceleration average value of each axis to the square sum root of the acceleration average values of the three axes.
Specifically, a triaxial acceleration sensor is fixed on the goods and transported along with the goods, and the triaxial acceleration sensor acquires triaxial acceleration information when the goods fall. And then uploading the acquired triaxial acceleration information to a logistics environment transportation platform, wherein the logistics environment transportation platform mainly comprises a server, a database, client sides (a webpage side, a PC side and a mobile side) and the like, integrates data processing, cargo transportation state analysis and risk identification algorithms, and can realize functions of online detection, online storage, data processing, automatic identification, feature reproduction, statistical analysis, information release, management optimization, multi-user sharing and the like. By usingFormula (II)
And carrying out vector synthesis on the collected data of the triaxial acceleration to obtain the vector acceleration, wherein the vector acceleration is a waveform taking time as an abscissa and the acceleration as an ordinate. Wherein a denotes a resultant vector acceleration, ax、ayAnd azWhich respectively refer to X, Y and Z acceleration collected by the acceleration sensor. In order to reduce noise, the vector acceleration is put into a low-pass filter for filtering processing. The large impact force is caused to the falling platform when the goods fall, so that the vector acceleration value of the goods is rapidly increased within a certain time range in the contact process of the goods and the falling platform, and the impact section can be determined according to the change condition of the vector acceleration. After the impact section is determined, the falling attitude of the goods is determined by calculating the ratio of the average acceleration value of each shaft in the impact section to the square sum of the average acceleration value of the three shafts, and the falling attitude of the goods is determined according to the ratio of the average acceleration value of each shaft to the square sum of the average acceleration value of the three shafts, so that the goods are judged to fall from the surface, fall from the corner or fall from the edge, reference data are provided for improving the product and packaging structure design, and the transportation loss is reduced.
Further optionally, as shown in the flowchart of fig. 2, step S2 further includes:
and S21, determining a vector wave crest of the vector acceleration, and moving to the two sides of the vector wave crest along the track of the vector acceleration by taking the vector wave crest as a starting point until point values smaller than the judgment threshold value are found at the two sides of the vector wave crest respectively, wherein a wave band between the point values smaller than the judgment threshold value and positioned at the two sides of the vector wave crest is the impact section.
Specifically, the wave peak on the vector acceleration is the vector wave peak, the vector wave peak represents the moment of the maximum impact force on the falling platform, and when the cargo falls due to throwing, the vector acceleration has at least two wave peaks, and the vector wave peak is the maximum wave peak of the vector acceleration. After the vector wave crest is determined, the acceleration value at the vector wave crest is the maximum, so that the moment of maximum impact on the falling platform when the goods fall onto the falling platform is at the vector wave crest, the impact force of the goods on the falling platform is gradually increased, and the process that the maximum impact force (namely the vector wave crest) is gradually reduced is achieved, so that the impact sections are positioned in the areas on two sides of the vector wave crest. And confirming the impact section according to the acceleration change condition of the goods falling to the falling platform and the judgment threshold value. The threshold value is judged to be a value close to gravity, 1.2-1.4 g is generally taken, and g is a gravity constant. The judgment threshold is determined according to experiments, the judgment threshold is too small, an impact section cannot be found possibly, and the judgment threshold is too large, so that the impact section obtained by calculation is reduced, and the drop identification calculation is inaccurate.
One specific embodiment of identifying the impingement section is: moving leftward (i.e., a direction in which the time coordinate is decreased) from the vector peak, the point value being a left end point of the impact section when moving to a point value smaller than the determination threshold, and then moving rightward (i.e., a direction in which the time coordinate is increased) from the vector peak, the point value being a right end point of the impact section when moving to a point value smaller than the determination threshold; and after the left end point and the right end point are determined, the identification of the impact section is completed, and the wave band between the left end point and the right end point is the impact section. The left end point and the right end point are the impact starting time and the impact recovery off-ground time, the left end point and the right end point are searched for determining an impact interval, after the impact interval is identified, the three-axis acceleration characteristic value in the impact interval is calculated, and the characteristic value is the respective average value of the three-axis acceleration in the impact interval and is used for being input into a neural network subsequently to train an identified impact posture model.
Further optionally, when the point value smaller than the determination threshold is not found in the process of moving to the two sides of the vector peak along the track of the vector acceleration, the determination threshold is increased by a set value, and then the point value smaller than the new determination threshold is found by moving to the two sides of the vector peak along the track of the vector acceleration with the vector peak as a starting point.
Specifically, if the left end point of the impact interval cannot be found, the threshold value a is automatically adjusted, and the left end point of the wave crest is continuously searched after adjustment; if the right peak end point cannot be found, the threshold value a is automatically adjusted, and the right peak end point is continuously searched after the threshold value is automatically adjusted. Generally, two ends of an impact section are equivalent to goods placed on the ground, a sensor is only subjected to the action of gravity acceleration, the vector acceleration is a value close to 1g, but sometimes the acceleration deviates due to factors such as noise and interference, the acceleration on two sides of an impact wave is not close to 1g and is larger than 1g, the judgment threshold value a needs to be increased, otherwise, left and right end points cannot be found; however, the adjustment of the value needs to be very careful, the identified shock wave region becomes narrow due to too large adjustment, the judgment of the subsequent falling posture is influenced, and the set threshold value for judging the increase of the threshold value a can be 0.05-0.1g optionally.
Further optionally, the determination threshold is close to a value of a gravitational constant.
Further optionally, the determination threshold is 1.2g to 1.4g, and g is a gravity constant.
Generally, two ends of a shock wave are equivalent to that of a cargo placed on the ground, a sensor is only subjected to gravity acceleration, the vector acceleration is a value close to 1g, however, sometimes the acceleration deviates due to factors such as noise and interference, the acceleration on two sides of the shock wave is not close to 1g and is larger than 1g, the judgment threshold value a needs to be increased, otherwise, left and right end points cannot be found; however, the adjustment of the value needs to be very careful, and if the adjustment is too large, the recognized shock wave zone becomes debt, and the subsequent falling posture judgment is influenced.
Further optionally, as shown in the flowchart of fig. 2, step S3 includes:
s31, respectively acquiring accelerations of the goods in the X-axis direction, the Y-axis direction and the Z-axis direction in the impact section;
s32, calculating the average values X, Y and Z of the accelerations of the goods in the impact section in the X axis, the Y axis and the Z axis and the square sum root of the average value of the accelerations of the three axes based on the accelerations of the goods in the impact section in the X axis, the Y axis and the Z axis directions respectively
S33, respectively calculating the addition of the goods in the impact section on the X axisThe ratio x1 of the average value of the speed to the square sum root of the average value of the three-axis acceleration, the ratio Y1 of the average value of the acceleration of the Y axis to the square sum root of the average value of the three-axis acceleration, and the ratio Z1 of the average value of the acceleration of the Z axis to the square sum root of the average value of the three-axis acceleration satisfy the following conditions:
further optionally, as shown in the flowchart of fig. 2, step S4 includes:
s41, determining x1、y1、z1Maximum value of (a)maxMinimum value amidAnd an intermediate value amin；
S42, comparing the minimum value amidThe minimum value amidAnd said intermediate value aminAnd judging the falling state of the cargo according to the size of the set threshold.
When judging amaxFirst set threshold, amid< second set threshold value, aminIf the number is less than the second set threshold value, namely the impact in a certain direction is dominant, judging that the falling state of the goods is surface falling; when judging amax-amid< third set threshold, and aminIf the difference is less than a second set threshold value, namely the impacts in a certain two directions are dominant and the difference is small, the falling state of the goods is judged to be arris falling; when the conditions are not met, judging that the falling state of the goods is angular falling; wherein the first set threshold > the second set threshold > the third set threshold. The first set threshold, the second set threshold and the third set threshold are determined according to a plurality of tests. The first set threshold is optionally 0.8, the second set threshold is optionally 0.2, and the third set threshold is optionally 0.1.
In the process of transporting goods, after the goods have a motion event on the placing platform relative to the placing platform, the motion event can not be judged to be falling. Therefore, before judging the falling state of the cargo, whether the motion event of the cargo is falling needs to be judged. The specific judgment method is as follows:
performing time domain integration on the vector acceleration in the cargo movement process, comparing the absolute value of the time domain integration result with a first judgment threshold value, and determining whether the cargo displacement process is an impact event or a vibration event according to the comparison result; and when the absolute value of the time domain integration result is larger than a first set threshold, judging the shock event, otherwise, judging the shock event.
When the displacement process of the cargo is judged to be an impact event, the absolute value of the time domain integration result is further compared with a second judgment threshold value, and whether the impact event is a falling event or a common impact event is determined according to the comparison result; and when the absolute value of the time domain integration result is less than a second set threshold value, judging the falling event, otherwise, judging the common impact.
Wherein the first judgment threshold is less than the second judgment threshold and less than the gravity constant g.
Further, when the absolute value of the time domain integration result is smaller than a second set threshold, whether the duration t of the weightless interval is larger than the set time threshold is judged, and if the duration t of the weightless interval is larger than the set time threshold, the falling event is judged.
Firstly, data of triaxial acceleration is transmitted into an algorithm program, the triaxial acceleration data is subjected to vector synthesis, and an acceleration waveform subjected to vector synthesis is put into a Butterworth low-pass filter for filtering; then, performing time domain integration on the vector acceleration, judging the vector acceleration as an impact event when the absolute value of the integration is greater than a first judgment threshold a1 (the first judgment threshold can be 0.1-0.3 g optionally), otherwise judging the vector acceleration as a vibration event because the vibration is reciprocating around a balance position, the time domain integral value is small, the impact is instantaneous acceleration change, and the time domain integral value is large; then, further judging the acceleration data of the impact event, if the weight loss condition exists, namely the acceleration is smaller than a certain second judgment threshold value a2 (the second judgment threshold value is 0.6-0.8 g optionally), the event is probably falling, otherwise, the event is judged to be a common impact event; in order to avoid misjudgment caused by signal disturbance, the acceleration weightlessness can be judged to fall only after a certain time, so that the acceleration data with weightlessness is further judged, and the specific weightlessness time is calculated, and specifically: firstly, searching for the moment when the vector acceleration is smaller than a gravity constant g on the vector acceleration, namely the free falling body starting moment T2, then searching for a vector peak to obtain a vector peak moment Tmax, searching for the moment when the vector acceleration is smaller than a third judgment threshold a3 (0.6-0.8 g selectable by a second judgment threshold) from the vector peak moment Tmax to the direction of time coordinate reduction, namely the impact moment T3, calculating the weight loss time T as T3-T2 according to the free falling body starting moment T3 and the impact moment T2, judging as a falling event if the weight loss time T is larger than a set time threshold T '(0.1 s selectable by the set time threshold T'), and otherwise, still judging as a common impact event; it is worth noting that: the threshold values (a1, a2, a3 and t') related to the algorithm are determined through repeated verification of multiple groups of vibration, impact, falling and throwing experiments in a laboratory, so that the algorithm distinguishing accuracy is improved.
This embodiment has still provided a goods falling gesture recognition system, includes:
the data acquisition module is used for acquiring triaxial acceleration values when the goods fall;
the data processing module is used for carrying out vector synthesis on the triaxial acceleration to obtain a vector acceleration;
and the algorithm module is used for determining an impact section when the cargo falls off based on the vector acceleration, calculating the ratio of the average acceleration value of each shaft in the impact section to the square sum root of the average acceleration value of the three shafts in the impact section based on the three-shaft acceleration of the impact section, and determining the falling attitude of the cargo according to the ratio of the average acceleration value of each shaft to the square sum root of the average acceleration value of the three shafts.
Specifically, a black box with a built-in triaxial acceleration sensor and components for data acquisition, storage, transmission and the like is placed in a product package, and the black box is started; as shown in the operation flow chart of fig. 3, the black box is transported along with the product, and the fall data during the transportation process is collected; and then, the acquired data is uploaded to a logistics environment analysis platform through wireless remote transmission or local connection, the logistics environment analysis platform mainly comprises a server, a database, client sides (a webpage side, a PC side and a mobile side) and the like, data processing, cargo transportation state analysis and risk identification algorithms are integrated, and functions of online detection, online storage, data processing, automatic identification, feature reproduction, statistical analysis, information release, management optimization, multi-user sharing and the like can be realized. And operating a data processing and falling posture identification and analysis algorithm on the logistics environment analysis platform to identify falling posture information, then summarizing corresponding information to generate an analysis report, closing the black box, and ending the whole operation process.
Further optionally, the cargo fall posture recognition method is adopted.
Although the present invention has been described with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope of the present invention.
Claims (7)
1. A cargo falling posture identification method is characterized by comprising
Acquiring triaxial acceleration information when the goods fall, and carrying out vector synthesis on the triaxial acceleration to obtain a vector acceleration;
determining an impact section when the cargo falls based on the vector acceleration;
acquiring the triaxial acceleration of an impact section, and calculating the ratio of the acceleration average value of each axis in the impact section to the square sum root of the triaxial acceleration average value based on the triaxial acceleration of the impact section;
determining the falling attitude of the cargo according to the ratio of the acceleration average value of each axis to the square sum root of the three-axis acceleration average value;
the method comprises the steps of obtaining the triaxial acceleration of an impact section, and calculating the ratio of the average acceleration value of each axis in the impact section to the square sum root of the average acceleration value of the three axes based on the triaxial acceleration of the impact section, wherein the ratio comprises
Respectively acquiring the acceleration of the goods in the X-axis direction, the acceleration of the goods in the Y-axis direction and the acceleration of the goods in the Z-axis direction in the impact section;
respectively calculating the acceleration average values X, Y and Z of the goods in the impact section in the X axis, the Y axis and the Z axis and the square sum root of the three-axis acceleration average values based on the accelerations of the goods in the impact section in the X axis, the Y axis and the Z axis directions
Respectively calculating the ratio X1 of the average value of the acceleration of the goods in the impact section on the X axis to the square sum root of the average value of the three-axis acceleration, the ratio Y1 of the average value of the acceleration of the Y axis to the square sum root of the average value of the three-axis acceleration, and the ratio Z1 of the average value of the acceleration of the Z axis to the square root of the average value of the three-axis acceleration, wherein the following conditions are met:
the determining the falling posture of the cargo according to the magnitude of the ratio comprises the following steps:
determining x1、y1、z1Maximum value of (a)maxMiddle value of amidAnd a minimum value amin；
By comparing said maximum values amaxThe intermediate value amidAnd the minimum value aminAnd judging the falling state of the cargo according to the size of the set threshold.
2. The cargo fall attitude identification method according to claim 1, wherein the determining of the impact section of the cargo fall based on the vector acceleration comprises
Determining a vector wave crest of the vector acceleration, and respectively moving to two sides of the vector wave crest along a track of the vector acceleration by taking the vector wave crest as a starting point until point values smaller than a judgment threshold value are respectively found at two sides of the vector wave crest, wherein a wave band between the point values smaller than the judgment threshold value at the two sides of the vector wave crest is the impact section.
3. The cargo falling posture identification method according to claim 2, wherein when the point value smaller than the judgment threshold value is not found in the process of moving to the two sides of the vector peak along the trajectory of the vector acceleration, the judgment threshold value is increased by a set value, and then the point value smaller than the new judgment threshold value is searched by moving to the two sides of the vector peak along the trajectory of the vector acceleration with the vector peak as a starting point again.
4. The cargo falling posture identification method according to claim 3, wherein the judgment threshold is 1.2g to 1.4g, and g is a gravity constant.
5. The cargo falling posture identification method according to claim 1, characterized in that the maximum value a is comparedmaxThe intermediate value amidAnd the minimum value aminAnd the falling state of the goods is judged according to the size of the set threshold, and the method comprises the following steps:
when judging amaxFirst set threshold, amid< second set threshold value, aminIf the number is less than the second set threshold value, judging that the falling state of the goods is surface falling;
when judging amax-amid< third set threshold, and aminIf the number is less than the second set threshold value, judging that the falling state of the goods is arris falling;
when the conditions are not met, judging that the falling state of the goods is angular falling;
wherein the first set threshold > the second set threshold > the third set threshold.
6. The cargo fall attitude identification method according to claim 1, wherein after vector synthesis is performed on the three-axis acceleration to obtain a vector acceleration, filtering processing is further performed on the vector acceleration.
7. A cargo fall attitude recognition system using the cargo fall attitude recognition method according to any one of claims 1 to 6, comprising:
the data acquisition module is used for acquiring triaxial acceleration values when the goods fall;
the data processing module is used for carrying out vector synthesis on the triaxial acceleration to obtain a vector acceleration;
and the algorithm module is used for determining an impact section when the cargo falls based on the vector acceleration, calculating the ratio of the average value of the acceleration of each axis in the impact section to the square sum root of the average value of the three-axis acceleration based on the three-axis acceleration of the impact section, and determining the falling attitude of the cargo according to the magnitude of the ratio of the average value of the acceleration of each axis to the square sum root of the average value of the three-axis acceleration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111042913.6A CN113655240B (en) | 2021-09-07 | 2021-09-07 | Cargo falling posture recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111042913.6A CN113655240B (en) | 2021-09-07 | 2021-09-07 | Cargo falling posture recognition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113655240A CN113655240A (en) | 2021-11-16 |
| CN113655240B true CN113655240B (en) | 2022-07-12 |
Family
ID=78493576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111042913.6A Active CN113655240B (en) | 2021-09-07 | 2021-09-07 | Cargo falling posture recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113655240B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000241442A (en) * | 1999-02-22 | 2000-09-08 | Sharp Corp | Protective mechanism and portable device for drop detection mechanism and magnetic disk device |
| CN108392208A (en) * | 2018-02-23 | 2018-08-14 | 大同公元三九八智慧养老服务有限公司 | A kind of tumble judgment method based on multiphase confinement |
| CN110217241A (en) * | 2019-06-19 | 2019-09-10 | 麦特汽车服务股份有限公司 | A kind of method and device for judging vehicle collision and bringing to a halt |
| CN111812356A (en) * | 2020-06-05 | 2020-10-23 | 厦门亿联网络技术股份有限公司 | Fall detection method and device based on triaxial accelerometer |
-
2021
- 2021-09-07 CN CN202111042913.6A patent/CN113655240B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000241442A (en) * | 1999-02-22 | 2000-09-08 | Sharp Corp | Protective mechanism and portable device for drop detection mechanism and magnetic disk device |
| CN108392208A (en) * | 2018-02-23 | 2018-08-14 | 大同公元三九八智慧养老服务有限公司 | A kind of tumble judgment method based on multiphase confinement |
| CN110217241A (en) * | 2019-06-19 | 2019-09-10 | 麦特汽车服务股份有限公司 | A kind of method and device for judging vehicle collision and bringing to a halt |
| CN111812356A (en) * | 2020-06-05 | 2020-10-23 | 厦门亿联网络技术股份有限公司 | Fall detection method and device based on triaxial accelerometer |
Non-Patent Citations (2)
| Title |
|---|
| 应用MEMS陀螺仪和加速度计的汽车运动姿态测量;曹景伟;《重庆理工大学学报（自然科学）》;20180430;第32卷(第4期);48-54 * |
| 手机跌落实验及其计算机模拟技术研究;段良;《中国优秀硕士学位论文全文数据库 信息科技辑》;20100515;第24-26页，图2-9-2-11，表2-7，2-8 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113655240A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10717196B2 (en) | Machine learning device, robot system, and machine learning method for learning workpiece picking operation | |
| CN105184325B (en) | Mobile intelligent terminal | |
| CN110621984B (en) | Method and system for improving quality inspection | |
| US8725452B2 (en) | Method of confirming motion parameters apparatus for the same, and motion assisting device | |
| US9689887B1 (en) | Fall event monitoring | |
| CN103814279A (en) | Mass measurement device | |
| CN106346513A (en) | Device and method for identifying kinetic parameters of terminal loads of six-degree-of-freedom robot | |
| CN113220119A (en) | Motion capture device of inertial sensor | |
| CN111735523B (en) | Vehicle weight detection method and device based on video identification and storage medium | |
| CN111860446A (en) | Detection system and method for unknown mode of satellite remote measurement time sequence data | |
| US11783471B2 (en) | Method and device for determining whether object includes defect | |
| US20180285684A1 (en) | Object attitude detection device, control device, and robot system | |
| CN104535077A (en) | Pedestrian step length estimation method based on intelligent mobile terminal equipment | |
| Yun et al. | Autoencoder-based anomaly detection of industrial robot arm using stethoscope based internal sound sensor | |
| Windau et al. | Inertial machine monitoring system for automated failure detection | |
| CN113655240B (en) | Cargo falling posture recognition method and system | |
| Lu et al. | MFE-HAR: multiscale feature engineering for human activity recognition using wearable sensors | |
| CN113793097B (en) | Analysis method and system for cargo transportation risk | |
| CN111839527A (en) | Fall detection method and device and computer readable storage medium | |
| CN117226836A (en) | Industrial robot diagnosis system and diagnosis method | |
| CN113624996B (en) | Cargo throwing state identification method and system | |
| US11534915B1 (en) | Determining vehicle integrity based on observed behavior during predetermined manipulations | |
| Tang et al. | Study of IMU installation position for posture estimation of excavators | |
| Huang et al. | Impact of camera vibration frequencies on image noise for unmanned aerial system applications | |
| CN114255435A (en) | Method and device for detecting abnormality of transport device, electronic apparatus, 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 | ||
| GR01 | Patent grant |