CN114739493A - Material weighing method and device in operation machine and operation machine - Google Patents
Material weighing method and device in operation machine and operation machine Download PDFInfo
- Publication number
- CN114739493A CN114739493A CN202210451582.XA CN202210451582A CN114739493A CN 114739493 A CN114739493 A CN 114739493A CN 202210451582 A CN202210451582 A CN 202210451582A CN 114739493 A CN114739493 A CN 114739493A
- Authority
- CN
- China
- Prior art keywords
- parameter
- moment
- working
- working device
- weighing
- 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.)
- Granted
Links
- 239000000463 material Substances 0.000 title claims abstract description 127
- 238000005303 weighing Methods 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000004364 calculation method Methods 0.000 claims abstract description 53
- 238000013528 artificial neural network Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 18
- 239000003921 oil Substances 0.000 claims description 51
- 230000007246 mechanism Effects 0.000 claims description 44
- 230000009471 action Effects 0.000 claims description 41
- 230000005484 gravity Effects 0.000 claims description 27
- 230000001133 acceleration Effects 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 239000010720 hydraulic oil Substances 0.000 claims description 6
- 239000012080 ambient air Substances 0.000 claims description 5
- 239000000295 fuel oil Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 17
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G9/00—Methods of, or apparatus for, the determination of weight, not provided for in groups G01G1/00 - G01G7/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Operation Control Of Excavators (AREA)
Abstract
The invention relates to the field of operation machinery, and provides a material weighing method and device in operation machinery and the operation machinery, wherein the method comprises the following steps: acquiring a first parameter and a second parameter of the working machine; inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by a working device in an unloaded state; and obtaining a weighing value of the material based on the moment generated by the working device and the second parameter. The moment that the working device produced can directly be obtained according to first parameter through the moment calculation model that founds in advance, and then obtains the value of weighing of material based on moment and the second parameter that the working device produced, need not complicated calculation process and can obtain the result of weighing, and the precision of efficiency of weighing and the result of weighing all obtains effectual improvement, has solved traditional weighing mode and has weighed inefficiency and the not accurate problem of result of weighing inadequately.
Description
Technical Field
The invention relates to the technical field of operation machinery, in particular to a material weighing method and device in operation machinery and the operation machinery.
Background
The weighing system of the existing working machine generally utilizes a weighing algorithm built based on dynamics and kinematics to weigh materials.
The traditional weighing algorithm has the core that the moment tau generated by a working device is calculatedlinkMoment tau generated by working meanslinkSpecifically, the calculation can be obtained by the following formula:
wherein D (theta) is a generalized quality matrix,
is a second order velocity force, G (theta) is gravity, theta,
Respectively, the angle, angular velocity and angular acceleration of the work implement relative to the ground.
The above parameters are in addition to theta,
In addition to this, the length l, mass m, center of gravity R and moment of inertia I of the working device are involved, and therefore, it is necessary to periodically calibrate the relevant parameters.
It is not difficult to discover that, in the traditional material weighing mode, because the moment that the equipment that works produced needs to be calculated through complicated mathematical formula in the weighing process and obtains, need regularly mark the relevant parameter in the moment computational formula, the calibration process is comparatively loaded down with trivial details, and the computational process of weighing result is complicated, has the problem that the efficiency of weighing is low and the weighing result is accurate inadequately.
Disclosure of Invention
The invention provides a material weighing method and device in an operating machine and the operating machine, which are used for solving the defects that the traditional weighing mode in the prior art is low in weighing efficiency and inaccurate in weighing result and realizing an efficient and accurate material weighing process.
In a first aspect, the present disclosure provides a method of weighing a material in a work machine, comprising:
acquiring a first parameter and a second parameter of a working machine;
inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by the working device in an idle state;
and obtaining a weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter.
According to the method for weighing the material in the working machine, the moment calculation model is obtained by the following method:
collecting a first parameter sample corresponding to the operation machine in the no-load state when the operation machine executes any action;
measuring the thrust of an oil cylinder of an action mechanism in the working device and the intercept of the oil cylinder of the action mechanism relative to the rotation center of the action mechanism when the working machine executes any action in the no-load state;
determining a torque sample generated by the working device in the no-load state based on the thrust of the oil cylinder of the action mechanism and the intercept;
and training a pre-constructed neural network through the first parameter sample and the moment sample generated by the working device to obtain a moment calculation model.
According to the method for weighing a material in a working machine provided by the invention, the moment sample generated by the working device in the no-load state is determined based on the thrust of the oil cylinder of the action mechanism and the intercept, and the method comprises the following steps:
multiplying the thrust of the oil cylinder of the actuating mechanism by the intercept to obtain an oil cylinder torque sample;
and under the no-load state, taking the oil cylinder torque sample as a torque sample generated by the working device.
According to the method for weighing a material in a working machine, the obtaining of the second parameter of the working machine includes:
acquiring the thrust of an oil cylinder of an action mechanism in a working device of the working machine in the current working state, the intercept of the oil cylinder of the action mechanism relative to the rotation center of the action mechanism and the distance value between the gravity center of a material and the rotation center of the working device;
multiplying the thrust of the oil cylinder of the action mechanism in the current working state by the intercept to obtain the actually measured thrust of the oil cylinder;
and taking the actually measured oil cylinder thrust and the distance value between the material gravity center and the rotation center of the working device as the second parameter.
According to the method for weighing a material in a working machine provided by the present invention, the obtaining of the weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter includes:
subtracting the actually measured oil cylinder moment in the second parameter from the moment generated by the working device to obtain a moment difference value;
multiplying a preset gravity coefficient by a distance value between the center of gravity of the material in the second parameter and the rotation center of the working device to obtain a product value;
and taking the quotient of the moment difference value and the product value to obtain a weighing value of the material acted by the working device.
According to the method for weighing a material in a working machine of the present invention, after obtaining a weighing value of the material applied by the working device based on the torque generated by the working device and the second parameter, the method further includes:
and if the operation machine is judged to be in an idle state according to the weighing value of the material acted by the working device, updating the moment calculation model based on the first parameter.
According to the material weighing method in the working machine, the first parameter comprises more than one of a pose parameter of the working device, a working condition parameter of the working machine and an environment parameter.
According to the material weighing method in the operation machinery, the position and posture parameters of the working device comprise more than one of acceleration, angular velocity, pitch angle and roll angle of the working device;
the working condition parameters of the working machine comprise more than one of working mode, engine gear, engine rotating speed, fuel oil surplus and hydraulic oil temperature;
the environmental parameter includes more than one of ambient temperature, ambient air pressure and ambient humidity.
In a second aspect, the present disclosure also provides a material weighing device in a working machine, the device being applied to the working machine, including:
the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring a first parameter and a second parameter of the working machine;
the first processing module is used for inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by the working device in an idle state;
and the second processing module is used for obtaining a weighing value of the material acted by the working device based on the torque generated by the working device of the working machine and the second parameter.
In a third aspect, the invention also provides a working machine using a method for weighing a material in a working machine as described above or comprising a device for weighing a material in a working machine as described above.
According to the method and the device for weighing the material in the working machine and the working machine, the moment generated by the working device of the working machine can be directly obtained according to the first parameter through the pre-constructed moment calculation model, the weighing value of the material acted by the working device is further obtained based on the moment generated by the working device of the working machine and the second parameter, the weighing result can be obtained without a complex calculation process, and the weighing efficiency and the precision of the weighing result are effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method of weighing a material in a work machine according to the present disclosure;
FIG. 2 is a schematic structural view of an excavator according to an embodiment of the present invention;
FIG. 3 is a schematic view of a mechanical analysis of an excavator in an embodiment of the present invention;
FIG. 4 is a schematic structural architecture of a neural network;
FIG. 5 is a schematic diagram illustrating an implementation of a method for weighing material in a work machine according to the present disclosure;
FIG. 6 is a schematic diagram of a material weighing apparatus in a work machine according to the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A method for weighing a material in a work machine, a device for weighing a material in a work machine, and an electronic apparatus constructed based on the method for weighing a material in a work machine according to embodiments of the present invention will be described below with reference to fig. 1 to 7.
Fig. 1 illustrates a method for weighing a material in a working machine, which may be applied to the working machine, and in particular, to a main controller of the working machine, according to an embodiment of the present invention, where the method includes:
step 101: acquiring a first parameter and a second parameter of the working machine;
step 102: inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by a working device in an idle state;
step 103: and obtaining a weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter.
In an exemplary embodiment, the first parameter may specifically include one or more of a pose parameter of the working device, a working condition parameter of the working machine, and an environmental parameter.
Specifically, the pose parameters of the working device may include one or more of an acceleration, an angular velocity, a pitch angle, and a roll angle of the working device, and taking the working machine as an excavator as an example, the working device may be a bucket, an arm, a boom, an upper frame, and other working mechanisms, and in this embodiment, the pose parameters may be detected by using a pose sensor on the excavator, as shown in fig. 2, a bucket pose sensor 201 is installed on the bucket of the excavator and may be used to acquire the pose parameters of the bucket; the bucket rod is provided with a bucket rod pose sensor 202 which can be used for collecting pose parameters of the bucket rod; a movable arm position sensor 203 is arranged on the movable arm and can be used for collecting position and posture parameters of the movable arm; a vehicle body pose sensor 204 is mounted on the vehicle body and can be used for acquiring pose parameters of the upper vehicle frame; in addition, the working device can also be a slewing mechanism, and a slewing pose sensor 205 is installed on the slewing mechanism and can be used for acquiring pose parameters of the slewing mechanism.
The attitude parameters in this embodiment may specifically include accelerations of the working device on the X axis, the Y axis, and the Z axis, angular velocities around the X axis, the Y axis, and the Z axis, a pitch angle, and a roll angle.
The working condition parameters of the working machine can specifically comprise more than one of a working mode, an engine gear, an engine rotating speed, fuel oil surplus and hydraulic oil temperature;
the environmental parameter may specifically include one or more of an ambient temperature, an ambient air pressure, and an ambient humidity.
In an exemplary embodiment, the second parameter may specifically include a measured cylinder moment and an intercept of a center of gravity of the material with a center of rotation of the working device.
In this embodiment, taking an excavator as an example, referring to fig. 2, since the excavator is further provided with a boom cylinder sensor 206, a main controller 207 and a display 208, the boom cylinder sensor 206 can detect pressure data of a cylinder size cavity, and can further obtain thrust of the boom cylinder, that is, cylinder thrust of the actuating mechanism, and further can calculate and obtain a moment of the boom cylinder relative to a boom rotation center, where a specific calculation formula is as follows:
τcy＝Fcy·dcy (1)
wherein, taucyMoment of the boom cylinder with respect to the boom rotation center, FcyThrust of boom cylinder, dcyThe intercept of the boom cylinder relative to the boom rotation center can be obtained by indirect measurement of a pose sensor on the boom.
According to the classical mechanical balance principle, referring to fig. 3, the moment tau of the boom cylinder relative to the boom rotation centercyMoment tau generated by working device relative to rotation center of boomlinkAnd the moment tau generated by the material relative to the rotation center of the movable armmatBalancing, namely:
τcy＝τlink+τmat (2)
wherein, taucyMoment of the boom cylinder with respect to the center of rotation of the boom, τlinkMoment generated by the working device with respect to the center of rotation of the boom, i.e. moment generated by the working device, τmatThe moment generated by the material relative to the rotation center of the movable arm.
Wherein the moment tau of the material relative to the center of rotation of the boommatSpecifically, the calculation can be obtained by the following formula:
τmat＝mmatg·lmat (3)
wherein, taumatMoment, m, generated for the material relative to the centre of rotation of the boommatIs the mass of the material,. lmatThe distance from the gravity center of the material to the rotation center of the movable arm can be obtained through indirect measurement of the position and posture sensor.
Accordingly, the mass of the material (i.e. the weight value of the material) can be calculated by the following formula:
wherein m ismatIs the mass of the material, i.e. the weight value, τ, of the materialcyMoment of the boom cylinder with respect to the center of rotation of the boom, τlinkMoment generated for the working device with respect to the center of rotation of the boom,/matThe distance from the gravity center of the material to the rotation center of the movable arm.
The traditional material weighing method is mainly used for calculating the moment tau generated by a working devicelinkSpecifically, the moment generated by the working device relative to the rotation center of the boom, and the moment τ generated by the working devicelinkSpecifically, the calculation can be obtained by the following formula:
wherein D (theta) is a generalized quality matrix,
is a second order velocity force, G (theta) is gravity, theta,
Respectively representing angle, angular velocity and angular acceleration of the working device relative to the groundTheta in FIG. 31Representing the angle of the boom relative to the ground, theta2Representing the angle of the stick relative to the ground, theta3Representing the angle of the bucket relative to the ground, other than θ,
In addition to this, the length l, mass m, center of gravity R, and moment of inertia I of the working device are involved. Therefore, the above-mentioned related parameters need to be calibrated periodically.
Taking an excavator as an example, the working devices may be a boom, an arm and a bucket, and the mass of the boom, the arm and the bucket, the center of gravity in each direction in a plane and the moment of inertia in each direction need to be calibrated to obtain a parameter set C to be calibratedcalThe formula for calculating the material weighing value is as follows:
wherein m ismatIs the mass of the material, i.e. the weight value of the material, FcyThrust of boom cylinder, dcyIs an intercept of a boom cylinder with respect to a boom rotation center, theta,
Respectively representing the angle, angular velocity and angular acceleration of the working device relative to the ground, CcalFor the set of parameters to be calibrated, /)matThe distance from the gravity center of the material to the rotation center of the movable arm.
O in FIG. 31、O2、O3Indicating the centre of rotation, cog, of the boom, arm and bucket, respectively1、cog2、cog3、cogmatRespectively representing the center of gravity, m, of the boom, stick, bucket, and material1g、m2g、m3g、mmatg represents the weight of the boom, arm, bucket, and material, respectively.
Because the excavator is under no-load state, the moment that the movable arm hydro-cylinder produced is balanced with the moment that the equipment (such as movable arm, arm and bucket) produced, that is the moment that the material produced is zero, promptly:
so the parameter set C to be calibratedcalMay pass through different Fcy、dcy、θ、
And
the joint calculation results in that:
therefore, the traditional calibration method needs to calibrate parameters through a plurality of groups of specific actions, the calibration operation has high requirements on operators, the operators need to level open fields, time and labor are wasted, and meanwhile, the parameters to be calibrated are influenced by environmental factors, calibration results have errors, and the reliability of weighing results is difficult to guarantee.
For this purpose, the embodiment directly obtains the torque τ generated by the working device through the torque calculation model by using the parameters measurable by the sensorlinkCombined with a previously obtained moment τ of the boom cylinder with respect to the center of rotation of the boomcyThe material weighing value can be quickly obtained by actually measuring the moment of the oil cylinder.
In an exemplary embodiment, the moment calculation model may be obtained specifically as follows:
collecting a first parameter sample corresponding to the operation machine in an idle state when the operation machine executes any action;
measuring the thrust of an oil cylinder of an action mechanism in the working device and the intercept of the oil cylinder of the action mechanism relative to the rotation center of the action mechanism when the working machine executes any action in an unloaded state;
determining a torque sample generated by a working device in an unloaded state based on the thrust and intercept of an oil cylinder of an action mechanism;
and training the pre-constructed neural network through the first parameter sample and the moment sample generated by the working device to obtain a moment calculation model.
In an exemplary embodiment, determining a torque sample generated by the working device in an idle state based on the thrust and intercept of the cylinder of the actuating mechanism may specifically include:
multiplying the thrust of the oil cylinder of the action mechanism by the intercept to obtain an oil cylinder torque sample;
and under the no-load state, taking the oil cylinder torque sample as a torque sample generated by the working device.
Taking an excavator as an example, when a new excavator is off-line, an operator can obtain a sample data set for training a neural network through a series of random actions, wherein the sample data set comprises a first parameter sample and a torque sample generated by a working device.
In the present embodiment, the neural network may adopt a deep learning neural network, and the network architecture of the network can be shown in fig. 4, the neural network includes 7 hidden layers, 1 input layer and 1 output layer, and an activation layer is added before the output layer for dimension conversion. The input layer may be a matrix of 40 × 1 dimensions, and taking an excavator as an example, the data of each dimension of the input layer may be referred to the following table 1:
TABLE 1 deep learning neural network input layer dimension data
| Data dimension | Data name |
| 0-31 | Pose parameter of working device |
| 32 | Working mode of excavator |
| 33 | Engine gear |
| 34 | Rotational speed of engine |
| 35 | Residual amount of fuel |
| 36 | Temperature of hydraulic oil |
| 37 | Ambient temperature |
| 38 | Ambient air pressure |
| 39 | Humidity of the environment |
The 0 th to 31 th dimensions are IMU (Inertial Measurement Unit), namely pose data which can be directly measured by the pose sensor, and the 32 th to 39 th dimensions increase the working mode of the excavator, the engine gear, the hydraulic oil temperature and other parameters, thereby enhancing the adaptability of the torque calculation model.
Further, each of the hidden layers is 160 × 1-dimensional, and the active layer and the output layer are 1-dimensional.
In an exemplary embodiment, the obtaining the second parameter of the work machine may specifically include:
acquiring the thrust of an oil cylinder of an action mechanism in a working device of the working machine in the current working state, the intercept of the oil cylinder of the action mechanism relative to the rotation center of the action mechanism and the distance value between the gravity center of a material and the rotation center of the working device;
multiplying the thrust of the oil cylinder of the actuating mechanism in the current working state by the intercept to obtain the actually measured thrust of the oil cylinder, taking an excavator as an example, and referring to the formula (1) in the process;
and taking the actually measured thrust of the oil cylinder and the distance value between the gravity center of the material and the rotation center of the working device as second parameters.
In an exemplary embodiment, the process of obtaining the weighing value of the material acted on by the working device based on the torque generated by the working device and the second parameter may specifically include:
the moment of the oil cylinder actually measured in the second parameter is differed from the moment generated by the working device to obtain a moment difference value;
multiplying the preset gravity coefficient by the distance value between the material gravity center in the second parameter and the rotation center of the working device to obtain a product value;
and (4) making the quotient of the moment difference value and the product value to obtain a weighing value of the material acted by the working device, namely the calculation mode of the weighing value of the material shown in the formula (4).
In an exemplary embodiment, after obtaining the weighing value of the material acted by the working device based on the torque generated by the working device and the second parameter, the method may further include:
and if the operation machine is judged to be in the no-load state according to the weighing value of the material acted by the working device, updating the moment calculation model based on the first parameter.
Further, the process of determining that the working machine is in the unloaded state according to the weighing value of the material acted by the working device may specifically include:
and if the weighing value of the material acted by the working device is smaller than the preset weight lower limit threshold, judging that the working machine is in an idle state.
In an actual application process, the torque calculation model may be arranged in a main controller of a working machine, that is, an ECU (Electronic Control Unit) of a vehicle, that is, a vehicle computer, and a specific working principle is as shown in fig. 5, a training set, that is, a sample data set is first constructed by offline no-load calibration data and user no-load calibration data, and a neural network is trained to obtain the torque calculation model.
When the working machine works, the pose data consisting of the pose parameters of each working device and other data comprising working condition parameters and environment parameters are input into the torque calculation model to obtain the torque generated by the working devices output by the model, the working condition judgment module judges whether the working machine is in an unloaded state, if so, the torque calculation model is updated based on the data input into the model, and if so, the weighing value of the material is output.
It should be noted that the present embodiment passes through the mass (i.e. the weighing value) m of the materialmatCan determine whether the work machine is unloaded, if mmatIf the weight is less than the lower threshold weight, it may be determined that the work machine is unloaded, and in this embodiment, the lower threshold weight may be set to 30kg, for example, if m is m, for an excavatormatAnd if the weight is less than 30kg, the excavator is considered to be in an idle state, and the measurement data of the sensor, namely the data of the input model, can be recorded at the moment and is used for self-updating of the moment calculation model.
In an exemplary embodiment, after obtaining the weighing value of the material acted by the working device based on the torque generated by the working device and the second parameter, the method may further include:
and if the weighing value of the material acted by the working device is larger than the preset upper weight limit threshold, outputting the weighing value of the material.
In the practical application process, the working state of the working machine can be further judged, and if the working machine is judged to be in the working state according to the weighing value of the material, the weighing value of the material is output.
In this embodiment, an upper weight threshold is further set, and if the weighing value of the material is higher than the preset upper weight threshold, it is determined that the working machine is in a working state.
Also for example, in the case of an excavator, the upper threshold weight may be set at 300kg, e.g.Fruit mmatIf the weight of the excavator is more than 300kg, the excavator can be judged to be loading, and the weighing value of the material can be output at the moment, so that data basis is provided for the operation process.
Therefore, according to the method for weighing the material in the working machine, provided by the embodiment of the invention, the moment generated by the working device can be directly obtained by utilizing the first parameter through the moment calculation model, and then the weighing value of the material can be calculated by utilizing the second parameter, the process does not need dimension measurement, the requirements on the installation position and the precision of the sensor are lower, a large number of calculation processes and the parameter calibration process are omitted, and the weighing process is more efficient and convenient; meanwhile, the data of the input torque calculation model comprises working condition parameters and environment parameters of the working machine, namely, error influence factors are considered, so that the finally obtained weighing value of the material is more accurate and reliable.
The following describes a material weighing device in a working machine according to the present invention, and the material weighing device in the working machine described below and the material weighing method in the working machine described above may be referred to in correspondence with each other.
Fig. 6 shows a material weighing apparatus in a work machine according to an embodiment of the present invention, including:
an obtaining module 601, configured to obtain a first parameter and a second parameter of a work machine;
the first processing module 602 is configured to input a first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the work machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by a working device in an idle state;
and the second processing module 603 is configured to obtain a weighing value of the material acted on by the working device based on the torque generated by the working device and the second parameter.
In an exemplary embodiment, the material weighing apparatus in the above-described work machine may further include:
the model training module is used for acquiring a first parameter sample corresponding to the operation machine in an idle state when the operation machine executes any action;
measuring the thrust of an oil cylinder of an actuating mechanism in the working device and the intercept of the oil cylinder of the actuating mechanism relative to the rotation center of the actuating mechanism when the working machine executes any action in an unloaded state;
determining a torque sample generated by a working device in an unloaded state based on the thrust and intercept of an oil cylinder of an action mechanism;
and training the pre-constructed neural network through the first parameter sample and the moment sample generated by the working device to obtain a moment calculation model.
Further, the model training module can specifically determine a torque sample generated by the working device in an idle state based on the thrust and intercept of the oil cylinder of the action mechanism in the following manner:
multiplying the thrust of the oil cylinder of the action mechanism by the intercept to obtain an oil cylinder torque sample;
and under the no-load state, taking the oil cylinder torque sample as a torque sample generated by the working device.
In an exemplary embodiment, the obtaining module 601 may specifically obtain the second parameter of the work machine by:
acquiring the thrust of an oil cylinder of an action mechanism in a working device of the working machine in the current working state, the intercept of the oil cylinder of the action mechanism relative to the rotation center of the action mechanism and the distance value between the gravity center of a material and the rotation center of the working device;
multiplying the thrust of the oil cylinder of the actuating mechanism in the current working state by the intercept to obtain the actually measured thrust of the oil cylinder;
and taking the actually measured thrust of the oil cylinder and the distance value between the gravity center of the material and the rotation center of the working device as second parameters.
In an exemplary embodiment, the second processing module 603 may specifically be configured to:
the moment of the oil cylinder actually measured in the second parameter is differed from the moment generated by the working device to obtain a moment difference value;
and calculating the weighing value of the material acted by the working device by taking the product of the moment difference value and the preset gravity coefficient and the distance value between the gravity center of the material in the second parameter and the rotation center of the working device as a quotient.
In an exemplary embodiment, the material weighing apparatus in the working machine may further include:
and the no-load judging module is used for updating the moment calculation model based on the first parameter when judging that the operation machine is in the no-load state according to the weighing value of the material.
Further, the no-load determination module may specifically determine that the operation machine is in the no-load state according to the weighing value of the material by the following method, including:
and if the weighing value of the material is smaller than the preset weight lower limit threshold, judging that the operation machine is in an idle state.
In an exemplary embodiment, the material weighing apparatus in the working machine may further include:
and the output module is used for outputting the weighing value of the material when the weighing value of the material acted by the working device is greater than a preset upper weight limit threshold value.
Specifically, in this embodiment, the first parameter may include one or more of a pose parameter of the working device, a working condition parameter of the working machine, and an environmental parameter.
Specifically, the pose parameters of the working device in this embodiment may include one or more of an acceleration, an angular velocity, a pitch angle, and a roll angle of the working device;
the working condition parameters of the working machine can comprise more than one of a working mode, an engine gear, an engine rotating speed, fuel surplus and hydraulic oil temperature;
the environmental parameter may include one or more of an ambient temperature, an ambient air pressure, and an ambient humidity.
Specifically, the second parameter in this embodiment may include the measured cylinder moment and the intercept between the center of gravity of the material and the rotation center of the working device.
Therefore, the material weighing device in the working machine provided by the embodiment of the invention can directly obtain the moment generated by the working device of the working machine according to the first parameter through the pre-constructed moment calculation model, further obtain the weighing value of the material based on the moment generated by the working device of the working machine and the second parameter, obtain the weighing result without a complex calculation process, and has higher weighing efficiency.
In addition, the embodiment of the invention also provides the operating machine, and the operating machine can realize the efficient and accurate material weighing function by using the material weighing method in the operating machine or comprising the material weighing device in the operating machine. It will be appreciated that the work machine may be an excavator.
Fig. 7 illustrates a physical structure diagram of an electronic device, and as shown in fig. 7, the electronic device may include: a processor (processor)701, a communication Interface (Communications Interface)702, a memory (memory)703 and a communication bus 704, wherein the processor 701, the communication Interface 702 and the memory 703 complete communication with each other through the communication bus 704. Processor 701 may invoke logic instructions in memory 703 to perform a method of weighing material in a work machine, the method comprising: acquiring a first parameter and a second parameter of the working machine; inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by a working device in an idle state; and obtaining a weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter.
In addition, the logic instructions in the memory 703 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which when executed by a computer, enable the computer to perform the method for weighing material in a working machine provided in the above embodiments, the method including: acquiring a first parameter and a second parameter of the working machine; inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by a working device in an unloaded state; and obtaining a weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the method for weighing a material in a work machine provided in the above embodiments, the method comprising: acquiring a first parameter and a second parameter of the working machine; inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by a working device in an idle state; and obtaining a weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of weighing a material in a work machine, comprising:
acquiring a first parameter and a second parameter of the working machine;
inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by the working device in an idle state;
and obtaining a weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter.
2. The method of weighing a material in a work machine according to claim 1, wherein the moment calculation model is obtained by:
collecting a first parameter sample corresponding to the operation machine in the no-load state when the operation machine executes any action;
measuring the thrust of an oil cylinder of an action mechanism in the working device and the intercept of the oil cylinder of the action mechanism relative to the rotation center of the action mechanism when the working machine executes any action in the no-load state;
determining a torque sample generated by the working device in the no-load state based on the thrust of the oil cylinder of the action mechanism and the intercept;
and training a pre-constructed neural network through the first parameter sample and the moment sample generated by the working device to obtain a moment calculation model.
3. The method of claim 2, wherein determining the torque sample generated by the work implement in the unloaded state based on the thrust of the ram and the intercept of the actuator comprises:
multiplying the thrust of the oil cylinder of the action mechanism by the intercept to obtain an oil cylinder torque sample;
and under the no-load state, taking the oil cylinder torque sample as a torque sample generated by the working device.
4. The method of claim 1, wherein said obtaining a second parameter of the work machine comprises:
acquiring the thrust of an oil cylinder of an action mechanism in a working device of the working machine in the current working state, the intercept of the oil cylinder of the action mechanism relative to the rotation center of the action mechanism and the distance value between the gravity center of a material and the rotation center of the working device;
multiplying the thrust of the oil cylinder of the actuating mechanism in the current working state by the intercept to obtain the actually measured thrust of the oil cylinder;
and taking the actually measured oil cylinder thrust and the distance value between the material gravity center and the rotation center of the working device as the second parameter.
5. The method of claim 1, wherein obtaining the weight of the material applied by the work implement based on the torque generated by the work implement and the second parameter comprises:
subtracting the actually measured oil cylinder moment in the second parameter from the moment generated by the working device to obtain a moment difference value;
multiplying a preset gravity coefficient by a distance value between the center of gravity of the material in the second parameter and the rotation center of the working device to obtain a product value;
and taking the quotient of the moment difference value and the product value to obtain a weighing value of the material acted by the working device.
6. The method for weighing a material in a working machine according to any one of claims 1 to 5, wherein after obtaining the weighing value of the material acted on by the working device based on the torque generated by the working device and the second parameter, the method further comprises:
and if the operation machine is judged to be in an unloaded state according to the weighing value of the material acted by the working device, updating the moment calculation model based on the first parameter.
7. The method of claim 1, wherein the first parameter comprises one or more of a pose parameter of the work implement, a work condition parameter of the work machine, and an environmental parameter.
8. The method of claim 7, wherein the pose parameters of the work implement comprise one or more of acceleration, angular velocity, pitch angle, and roll angle of the work implement;
the working condition parameters of the working machine comprise more than one of working mode, engine gear, engine rotating speed, fuel oil surplus and hydraulic oil temperature;
the environmental parameter includes more than one of ambient temperature, ambient air pressure and ambient humidity.
9. A material weighing apparatus in a work machine, comprising:
the acquisition module is used for acquiring a first parameter and a second parameter of the working machine;
the first processing module is used for inputting the first parameter into a pre-constructed moment calculation model to obtain a moment generated by a working device of the working machine; the moment calculation model is obtained by training a neural network based on a first parameter sample and a moment sample generated by the working device in an idle state;
and the second processing module is used for obtaining a weighing value of the material acted by the working device based on the moment generated by the working device and the second parameter.
10. A working machine, characterized in that it uses a method for weighing material in a working machine according to any one of claims 1-8 or comprises a device for weighing material in a working machine according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210451582.XA CN114739493B (en) | 2022-04-26 | 2022-04-26 | Material weighing method and device in working machine and working machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210451582.XA CN114739493B (en) | 2022-04-26 | 2022-04-26 | Material weighing method and device in working machine and working machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114739493A true CN114739493A (en) | 2022-07-12 |
| CN114739493B CN114739493B (en) | 2024-01-26 |
Family
ID=82283511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210451582.XA Active CN114739493B (en) | 2022-04-26 | 2022-04-26 | Material weighing method and device in working machine and working machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114739493B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3820757A1 (en) * | 1988-06-18 | 1989-12-28 | Bosch Gmbh Robert | Apparatus for determining the weight of suspended loads |
| JPH11189136A (en) * | 1997-12-26 | 1999-07-13 | Toyota Central Res & Dev Lab Inc | Vehicle state quantity estimating device |
| CN103407890A (en) * | 2013-07-24 | 2013-11-27 | 徐州赫思曼电子有限公司 | Apparatus and method used for excavator hanging object weighing |
| CN110709563A (en) * | 2017-10-04 | 2020-01-17 | 株式会社小松制作所 | Work machine, system including work machine, and control method for work machine |
| CN111591893A (en) * | 2020-05-27 | 2020-08-28 | 太原科技大学 | Method for measuring hoisting load of automobile crane based on neural network |
| CN113124972A (en) * | 2021-03-12 | 2021-07-16 | 中国航空工业集团公司西安飞行自动控制研究所 | Excavator material weighing method and system |
| CN113124988A (en) * | 2021-04-21 | 2021-07-16 | 上海三一重机股份有限公司 | Automatic weighing calibration method and system for excavator |
| CN113566943A (en) * | 2021-07-29 | 2021-10-29 | 上海三一重机股份有限公司 | Material weighing method and device for excavator, excavator and readable storage medium |
| CN113988369A (en) * | 2021-09-23 | 2022-01-28 | 上海三一重机股份有限公司 | Prediction model training method and prediction method based on prediction model |
| WO2022069467A1 (en) * | 2020-10-02 | 2022-04-07 | Robert Bosch Gmbh | Method for determining the weight of a load of a mobile work machine, learning method for a data-based model, and mobile work machine |
-
2022
- 2022-04-26 CN CN202210451582.XA patent/CN114739493B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3820757A1 (en) * | 1988-06-18 | 1989-12-28 | Bosch Gmbh Robert | Apparatus for determining the weight of suspended loads |
| JPH11189136A (en) * | 1997-12-26 | 1999-07-13 | Toyota Central Res & Dev Lab Inc | Vehicle state quantity estimating device |
| CN103407890A (en) * | 2013-07-24 | 2013-11-27 | 徐州赫思曼电子有限公司 | Apparatus and method used for excavator hanging object weighing |
| CN110709563A (en) * | 2017-10-04 | 2020-01-17 | 株式会社小松制作所 | Work machine, system including work machine, and control method for work machine |
| CN111591893A (en) * | 2020-05-27 | 2020-08-28 | 太原科技大学 | Method for measuring hoisting load of automobile crane based on neural network |
| WO2022069467A1 (en) * | 2020-10-02 | 2022-04-07 | Robert Bosch Gmbh | Method for determining the weight of a load of a mobile work machine, learning method for a data-based model, and mobile work machine |
| CN113124972A (en) * | 2021-03-12 | 2021-07-16 | 中国航空工业集团公司西安飞行自动控制研究所 | Excavator material weighing method and system |
| CN113124988A (en) * | 2021-04-21 | 2021-07-16 | 上海三一重机股份有限公司 | Automatic weighing calibration method and system for excavator |
| CN113566943A (en) * | 2021-07-29 | 2021-10-29 | 上海三一重机股份有限公司 | Material weighing method and device for excavator, excavator and readable storage medium |
| CN113988369A (en) * | 2021-09-23 | 2022-01-28 | 上海三一重机股份有限公司 | Prediction model training method and prediction method based on prediction model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114739493B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5890101A (en) | Neural network based method for estimating helicopter low airspeed | |
| US7444888B2 (en) | Method and sensor arrangement for load measurement on rolling element bearing | |
| US20100219987A1 (en) | Rotor system health monitoring using shaft load measurements and virtual monitoring of loads | |
| JP5618066B2 (en) | Force control robot calibration apparatus and method | |
| CN109680738B (en) | Hydraulic excavator material online weighing device and method | |
| CN101835974A (en) | Be used for determining the method for fatigue damage of the dynamical system of wind turbine | |
| CN111104729A (en) | System and method for determining payload mass moved by a work device | |
| WO2022222393A1 (en) | Excavator automatic weighing calibration method and system and excavator | |
| CN113010979A (en) | Excavator weighing method and system | |
| CN117077455B (en) | Large logistics simulation method and system based on digital twin technology | |
| CN114739493B (en) | Material weighing method and device in working machine and working machine | |
| CN110761957B (en) | Calibration method and device for optical fiber load sensor of wind generating set | |
| CN116305564A (en) | Design method of digital twin model test bed of aero-engine rotor system | |
| CN112497193B (en) | Six-degree-of-freedom parallel robot electric cylinder thrust estimation method and system | |
| CN113821869A (en) | Multi-source data fusion-based aircraft force load online prediction method | |
| Tran et al. | Developing an Approach for Fault Detection and Diagnosis of Angular Velocity Sensors | |
| Sayeed et al. | In-motion weight sensor array for dynamic weighing of nonsingulated objects | |
| CN115408919B (en) | Method and system for predicting drop impact of reloading airdrop based on neural network | |
| CN116430160B (en) | Device and method for testing shell stress of electric drive system | |
| CN115452251B (en) | Large-scale high-speed rotation equipment rotational inertia measurement method based on unified reference of rotation shaft and inertia main shaft | |
| CN118094770A (en) | Excavator bucket load calculation method and device | |
| CN115099083A (en) | Real-time solution method and system for dynamic stress of arm support, server and engineering machinery | |
| CN116776716A (en) | Method and device for determining dynamic stress of arm support, electronic equipment and readable storage medium | |
| CN118095110A (en) | Method, system, equipment and storage medium for acquiring furnace temperature of coal-fired unit | |
| CN116818159A (en) | Dynamic torque identification method for transmission chain |
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 |