CN115047207B - Early warning method for vehicle sinking of unmanned agricultural machine - Google Patents
Early warning method for vehicle sinking of unmanned agricultural machine Download PDFInfo
- Publication number
- CN115047207B CN115047207B CN202210389016.0A CN202210389016A CN115047207B CN 115047207 B CN115047207 B CN 115047207B CN 202210389016 A CN202210389016 A CN 202210389016A CN 115047207 B CN115047207 B CN 115047207B
- Authority
- CN
- China
- Prior art keywords
- agricultural machinery
- early warning
- vehicle
- trapping
- model
- 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
- G01P3/00—Measuring linear or angular speed; Measuring differences of linear or angular speeds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an early warning method for the sinking of an unmanned agricultural machine, which comprises the following steps: s1, acquiring motion state data of an unmanned agricultural machine, representing the sudden change of a stuck agricultural machine by taking the speed of the agricultural machine as a state variable, respectively solving a Spearman rank correlation coefficient with the speed of each dependent variable by adopting a correlation method, and determining a control variable of a sudden change model; s2, establishing a normal operation-bogging-down dovetail type mutation model of the agricultural machinery based on the dovetail type mutation model; s3, carrying out early warning of vehicle collapse according to a vehicle collapse dovetail type mutation model of normal operation of the agricultural machinery, and carrying out model inspection on error evaluation indexes; and S4, applying the model to actual agricultural machinery vehicle-trapping early warning. The invention designs the early warning mechanism of the sinking of the agricultural machinery by adopting the data and the mutation model of the unmanned agricultural machinery, can predict the sinking of the agricultural machinery in advance, and effectively reduces or even avoids the sinking accidents of the unmanned agricultural machinery.
Description
Technical Field
The invention belongs to the technical field of intelligent agricultural machinery, and particularly relates to an early warning method for vehicle sinking of an unmanned agricultural machine.
Background
China has rice planting area of about 4.5 hundred million mu throughout the year, and along with the continuous reduction of rural labor and the increase of production cost, the development of an agricultural unmanned technology is urgently needed to solve the problem of 'who comes' land. The unmanned agricultural machine easily causes the agricultural machine to sideslip and slide or even trap the vehicle in wet and slippery mud and paddy field environment with uneven height of a hard bottom layer, and if the unmanned agricultural machine is trapped, the unmanned agricultural machine cannot be timely removed from the vehicle or cannot be manually intervened in time, the unmanned agricultural machine can get deeper and cause operation accidents. The research and the related technology on the aspect of sinking the agricultural machinery are less at present. The invention patent CN 112462741 of China provides an unmanned agricultural machinery vehicle-sinking detection alarm system based on a cloud platform, the slip rate is obtained through comparison of the wheel speed and the vehicle speed, whether the agricultural machinery idles or not is judged, and then a vehicle-sinking alarm signal is generated through a 4G communication module. Chinese patents CN202514323U, CN212267166U and CN205631996U assist the self rescue of the sinking of the agricultural machinery by designing corresponding mechanical structures.
Disclosure of Invention
The invention mainly aims to overcome the defects and shortcomings of the prior art, and provides an early warning method for the sinking of an unmanned agricultural machine.
In order to achieve the purpose, the invention adopts the following technical scheme:
an early warning method for the sinking of an unmanned agricultural machine comprises the following steps:
s1, acquiring motion state data of an unmanned agricultural machine, representing the sudden change of a stuck agricultural machine by taking the speed v of the agricultural machine as a state variable, respectively solving a Spearman rank correlation coefficient with the speed v for each dependent variable by adopting a correlation method, and determining a control variable of a sudden change model;
s2, establishing a normal operation-bogging-down dovetail type mutation model of the agricultural machinery based on the dovetail type mutation model;
s3, carrying out early warning of vehicle collapse according to a vehicle collapse dovetail type mutation model which is normal operation of the agricultural machinery, carrying out model inspection on error evaluation indexes, and optimizing the mutation model;
and S4, applying the optimized mutation model to actual agricultural machinery vehicle trapping early warning.
Further, step S1 specifically includes:
the method comprises the following steps that a plurality of dependent variables exist in the state that the unmanned agricultural machine is trapped, and Spearman rank correlation coefficients are respectively obtained for the dependent variables by adopting a correlation method: note x i And y i Is agricultural machinery original position data, x' i And y' i The position data are respectively arranged according to the sequence from small to big:
where ρ is s Is rank correlation coefficient, n is data length;
respectively calculating rank correlation coefficients rho of each dependent variable and speed v according to formula (1) s ，ρ s The larger the absolute value is, the more relevant the dependent variable is to the agricultural machinery vehicle-trapping sudden change.
Further, step S2 includes:
s21, designing a cusp line set of the dovetail type mutation model;
s22, establishing an agricultural machinery vehicle trapping discriminant;
s23, establishing a vehicle collapse dovetail type mutation model for normal operation of the agricultural machinery.
Further, step S21 specifically includes:
the standard open-break potential function for dovetail mutations is:
wherein a, b and c are control variables, and x is a state variable;
and (3) obtaining a balance curved surface by derivation of the formula (2):
the set of mutation points also satisfies:
combining formula (3) and formula (4), eliminating x, and scoring the equation of fork set H;
from equation (3):
-x 4 -ax 2 -bx＝c (5)
taylor series expansion of F (X) at X:
wherein R is n (x) Is Lagrangian remainder;
according to the formula (6):
let the coefficients be:
wherein s is a constant;
performing transformation in a (p, q, r) three-dimensional space, and making x (p, q, r) = r, so as to obtain:
a(p,q,r)＝3q-6r 2
b(p,q,r)＝2p-6rq+8r 3 (9)
the prevalence of mutations is then set as:
{r,3q-6r 2 ,2p-6rq+8r 3 ,-2pr+3qr 2 -3r 4 } (10)
the singular set of the snap map x requires p =0, then the singular set is:
{r,3q-6r 2 ,-6rq+8r 3 ,3qr 2 -3r 4 } (11)
let q =0, the cubic term of the mutation prevalence set vanishes, and the singular set is:
{r,-6r 2 ,8r 3 ,-3r 4 } (12)
the bifurcation set H is represented as:
{3q-6r 2 ,-6rq+8r 3 ,3qr 2 -3r 4 } (13)
the set of cusp lines for the dovetail mutation model is:
{a,b,c}＝{-6r 2 ,8r 3 ,-3r 4 } (14)。
further, step S22 specifically includes:
based on the symmetry characteristic of the bifurcation set, a half-plane with b =0,a < 0 is selected for analysis, and formula (3) is rewritten as:
x 4 +ax 2 +c＝0 (15)
when the formula (15) is regarded as a completely flat mode, the agricultural machinery vehicle-trapping discriminant Δ is:
Δ＝a 2 -4c (16)
when the delta is less than 0, the formula (16) has no solid root, and the mutation is shown, namely the agricultural machinery is trapped;
when delta is larger than 0, the formula (16) has a solid root, which indicates that no mutation occurs and the agricultural machinery is in a stable working state;
when Δ =0, it indicates a critical state.
Further, step S23 specifically includes:
by height difference delta h and roll angle
And the transverse position deviation delta e is used as a control variable, the agricultural machinery speed v representing mutation is used as a state variable, a dovetail type mutation model is established, and the following steps are performed:
wherein, A, B and C are dovetail mutation model parameters;
substituting the formula (17) into the formulas (2) to (16), namely establishing a driving potential function of the dovetail type sudden change model for normal operation of the agricultural machinery:
further, step S3 specifically includes:
s31, establishing an agricultural machinery vehicle trapping early warning mechanism;
s32, evaluating the early warning accuracy of the agricultural machinery vehicle trapping;
and S33, optimizing the particle swarm optimization.
Further, step S31 specifically includes:
setting the prediction step length as N, the data length as N, and calculating the speed v of the agricultural machine and the control variable delta h (i),
Substituting the sequence of the delta e (i) into a formula (16) for training and judging, and carrying out data point classification on the dovetail type mutation model according to a judged result; when in the prediction time period t i ,t i +N]If delta < 0 exists in the agricultural machinery, the agricultural machinery is considered to be possibly stuck.
Further, step S32 specifically includes:
in order to evaluate the accuracy of the early warning of the sinking of the agricultural machinery, a prediction evaluation method is designed:
wherein, P trap 、F trap 、HSS、PSS、N tp 、N fn 、N fp And N tn Respectively representing the correct rate and the wrong rate of the trapped vehicle judgment, the Heidke score, the Peirce score, the number of times of the occurrence and the correct early warning of the trapped vehicle, the number of times of the occurrence and the wrong early warning of the trapped vehicle, the number of times of the non-occurrence and the non-early warning of the trapped vehicle, wherein all the evaluation index value domains are [0,1]；
In order to obtain maximum early warning accuracy, an objective function is designed:
f(p)＝max PSS (20)
the constraint conditions are as follows:
introduction of relaxation factor lambda 1 And λ 2 Equation (21) is changed to:
wherein an initial value λ is set 1 ＝0.7，λ 2 ＝0.3。
Further, step S33 is specifically:
and (3) performing objective function optimization solution on the formula (20) by adopting a particle swarm optimization algorithm and taking the formula (22) as measurement constraint, and repeatedly training and optimizing the trapping mutation model by evaluating the accuracy of prediction on experimental sample data to obtain the parameter values of the A, B and C models.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. according to the invention, information such as height difference, roll angle and transverse position deviation in the movement process of the agricultural machine, which is acquired by the unmanned agricultural machine pose sensing device, is adopted, a data driving method is adopted, the normal running operation and the stuck state of the agricultural machine are regarded as two stable states of an unmanned system based on a mutation theory, and the sudden transition threshold value from one stable state to the other stable state of the system is researched based on the mutation theory, so that the imminent stuck of the agricultural machine is judged, and the early warning of the stuck agricultural machine is realized.
2. The invention designs a vehicle trapping early warning mechanism aiming at the problem of vehicle trapping of the unmanned agricultural machine, realizes the parking of the unmanned agricultural machine and the waiting of manual rescue by remote alarm in time, can effectively avoid or reduce the probability of vehicle trapping accidents of the agricultural machine, and improves the operation safety of the unmanned agricultural machine.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart relating to the mutation model of the present invention;
fig. 3 is a schematic diagram of a trapping sudden change warning mechanism according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the embodiments of the present invention are not limited thereto.
Examples
As shown in fig. 1 and 2, the invention provides an early warning method for the sinking of an unmanned agricultural machine, which comprises the following steps:
s1, acquiring motion state data of the unmanned agricultural machine, representing the speed v of vehicle-trapping mutation as a state variable, respectively calculating Spearman rank correlation coefficients of all dependent variables by adopting a correlation relationship method, and determining a mutation model control variable; the method specifically comprises the following steps:
the unmanned agricultural machinery has a plurality of dependent variables in the state of sinking the vehicle, and x is recorded i And y i Respectively raw data, x' i And y' i Respectively calculating Spearman rank correlation coefficients of all the factors by adopting a correlation method for the data arranged from small to large respectively:
where ρ is s Is the rank correlation coefficient and n is the data length.
Respectively calculating rank correlation coefficients rho of each dependent variable and the speed v according to formula (1) s ，ρ s The larger the absolute value is, the more relevant the data is; in the embodiment, the elevation difference delta h and the roll angle are obtained by calculation
The three factors of the lateral position deviation delta e are closely related to the trapped car, and the influence is most obvious.
S2, establishing an agricultural machinery vehicle-trapping mutation model based on the dovetail mutation model; the method comprises the following steps:
s21, designing a cusp line set of the dovetail type mutation model; the method specifically comprises the following steps:
the standard opening potential function of the dovetail type mutation is
Wherein a, b and c are control variables, and x is a state variable.
The potential function of the formula (2) is derived to obtain a balanced curved surface:
the set of mutation points also satisfies:
combining formula (3) and formula (4), eliminating x, and scoring the equation of fork set H;
from equation (3):
-x 4 -ax 2 -bx＝c (5)
taylor series expansion of F (X) at X:
wherein R is n (x) Is the lagrange remainder.
According to the formula (6):
let the coefficients be:
where s is a constant, so a transformation is performed in (p, q, r) three-dimensional space, let x (p, q, r) = r, and obtain:
a(p,q,r)＝3q-6r 2
b(p,q,r)＝2p-6rq+8r 3 (9)
then, the mutation prevalence set (i.e., equilibrium surface) is:
{r,3q-6r 2 ,2p-6rq+8r 3 ,-2pr+3qr 2 -3r 4 } (10)
the singular set of the snap map x requires p =0, then the singular set is:
{r,3q-6r 2 ,-6rq+8r 3 ,3qr 2 -3r 4 } (11)
let q =0, the three terms of the mutation prevalence set disappear, and the singular set is:
{r,-6r 2 ,8r 3 ,-3r 4 } (12)
the set of forks H can be expressed as:
{3q-6r 2 ,-6rq+8r 3 ,3qr 2 -3r 4 } (13)
the set of cusp lines for the dovetail mutation model is:
{a,b,c}＝{-6r 2 ,8r 3 ,-3r 4 } (14)。
s22, establishing an unmanned agricultural machinery vehicle trapping discriminant; the method specifically comprises the following steps:
based on the symmetry characteristic of the bifurcation set, selecting a half plane with b =0,a < 0 for analysis, and rewriting the formula (3) as follows:
x 4 +ax 2 +c＝0 (15)
if equation (15) is considered to be a perfect flat mode, the discriminant Δ is:
Δ＝a 2 -4c (16)
when the delta is less than 0, the formula (16) has no solid root and corresponds to the part above the swallow wing, and the system is shown to have sudden change, namely the unmanned agricultural machinery is trapped.
When the delta is larger than 0, the formula (16) has a solid root which corresponds to the lower part or the dovetail part of the swallow wing, and the system is not mutated and is in a stable working state.
When Δ =0, the system is in a critical state.
S23, establishing a swallow-tail type mutation model of the unmanned agricultural machine; the method comprises the following specific steps:
by height difference delta h and roll angle
And the transverse position deviation delta e is used as a control variable, the speed v representing mutation is used as a state variable, a dovetail mutation model is established, and the following steps are performed:
wherein A, B and C are model parameters;
substituting the formula (17) into the formulas (2) to (16), namely establishing a driving potential function of the dovetail type sudden change model for normal operation of the agricultural machinery:
s3, carrying out vehicle trapping early warning according to a vehicle trapping sudden change model discriminant, and carrying out model inspection on error evaluation indexes; the method comprises the following steps:
s31, establishing an early warning mechanism for the sinking of the unmanned agricultural machinery; the method specifically comprises the following steps:
as shown in FIG. 3, a prediction step length is set to be N, a data length is set to be N, and the speed v of the agricultural machine and control variables delta h (i) are set,
And Δ e (i) into equation (16), and the model classifies data points according to the result of the training decision. When in the prediction time period [ t ] i ,t i +N]If delta < 0 exists in the agricultural machinery, the agricultural machinery is considered to be possibly stuck.
S32, evaluating the early warning accuracy of the sinking of the unmanned agricultural machinery; the method comprises the following specific steps:
in order to effectively evaluate the accuracy of the agricultural machinery vehicle-trapping early warning, a prediction evaluation method is designed:
wherein, P trap 、F trap 、HSS、PSS、N tp 、N fn 、N fp And N tn Respectively representing the correct rate and the wrong rate of the trapped vehicle judgment, the Heidke score, the Peirce score, the number of times of the occurrence and the correct early warning of the trapped vehicle, the number of times of the occurrence and the wrong early warning of the trapped vehicle, the number of times of the non-occurrence and the non-early warning of the trapped vehicle, wherein all the evaluation index value domains are [0,1]。
In order to obtain maximum early warning accuracy, an objective function is designed:
f(p)＝max PSS (20)
the constraint conditions are as follows:
the constraint of equation (21) is too absolute, which tends to result in no solution for the objective function of equation (20). For this purpose, a relaxation factor λ is introduced 1 And λ 2 The formula (21) is changed to:
the agricultural machinery in paddy field is stuck in the vehicle generally in a small probability event, and in order to reduce the misjudgment of the stuck vehicle, an initial value lambda is set according to experience 1 ＝0.7，λ 2 ＝0.3。
S33, optimizing a particle swarm algorithm; the method specifically comprises the following steps:
and (3) performing objective function optimization solution on the formula (20) by adopting a particle swarm optimization algorithm and taking the formula (22) as measurement constraint, and repeatedly training and optimizing the vehicle trapping sudden change prediction model by evaluating the accuracy of prediction on experimental sample data to obtain the parameter values of the A, B and C models.
The particle swarm optimization is realized by the following specific steps:
(1) taking the prediction accurate values as particles, taking all the prediction accurate values as particle swarms, initializing the positions and the speeds of all the particles in the population, substituting the positions and the speeds into a formula (20) to calculate the particle fitness value;
(2) evaluating the fitness of each particle, storing the position and the fitness value of each current particle, and screening the position and the fitness value of the optimal prediction accuracy value;
(3) updating the speed and the position of the particle, comparing the fitness value of each particle with the optimal position of each particle, and if the fitness value is better, taking the fitness value as the optimal position of the current particle;
(4) if the stopping condition is met (the preset precision or iteration times are reached), stopping searching and outputting a result, otherwise, returning to the step (3) to continue iteration;
(5) optimizing the trapping sudden change model and obtaining the parameter values of the A, B and C models.
And S4, using the optimized model for early warning of actual agricultural machinery vehicle collapse.
The invention designs the early warning mechanism of the sinking of the agricultural machinery by adopting the data of the unmanned agricultural machinery and the mutation model, can predict the sinking of the agricultural machinery in advance, effectively reduces or even avoids the sinking accidents of the unmanned agricultural machinery, improves the safety of the operation of the unmanned agricultural machinery, has stronger adaptability and effectively improves the applicability of the unmanned agricultural machinery.
It should also be noted that in the present specification, terms such as "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The unmanned agricultural machinery vehicle-trapping early warning method is characterized by comprising the following steps:
s1, acquiring motion state data of an unmanned agricultural machine, representing the sudden change of a stuck agricultural machine by taking the speed v of the agricultural machine as a state variable, respectively solving a Spearman rank correlation coefficient with the speed v for each dependent variable by adopting a correlation method, and determining a control variable of a sudden change model;
s2, establishing a normal operation-bogging-down dovetail type mutation model of the agricultural machinery based on the dovetail type mutation model;
s3, carrying out early warning of vehicle collapse according to a vehicle collapse dovetail type mutation model which is normal operation of the agricultural machinery, carrying out model inspection on error evaluation indexes, and optimizing the mutation model;
and S4, using the optimized mutation model for early warning of actual agricultural machinery vehicle collapse.
2. The unmanned agricultural machinery vehicle-trapping early warning method according to claim 1, wherein the step S1 specifically comprises:
the method comprises the following steps that a plurality of dependent variables exist in the state that the unmanned agricultural machine is trapped, and Spearman rank correlation coefficients are respectively obtained for the dependent variables by adopting a correlation method: note x i And y i As raw position data of agricultural machinery, x i ' and y i ' position data arranged in order from small to large are respectively:
where ρ is s Is rank correlation coefficient, n is data length;
respectively calculating rank correlation coefficients rho of each dependent variable and speed v according to formula (1) s ，ρ s The larger the absolute value is, the more relevant the dependent variable is to the agricultural machinery vehicle-trapping sudden change.
3. The unmanned agricultural machinery vehicle-trapping early warning method according to claim 1, wherein the step S2 comprises:
s21, designing a cusp line set of the dovetail type mutation model;
s22, establishing an agricultural machinery vehicle trapping discriminant;
s23, establishing a vehicle collapse dovetail type mutation model for normal operation of the agricultural machinery.
4. The unmanned agricultural machinery vehicle-trapping early warning method according to claim 3, wherein the step S21 is specifically as follows:
the standard open-break potential function for dovetail mutations is:
wherein a, b and c are control variables, and x is a state variable;
and (3) obtaining a balance curved surface by derivation of the formula (2):
the set of mutation points also satisfies:
combining formula (3) and formula (4), eliminating x, and scoring the equation of fork set H; from equation (3):
-x 4 -ax 2 -bx＝c (5)
taylor series expansion of F (X) at X:
wherein R is n (x) Is Lagrangian remainder;
according to the formula (6):
let the coefficients be:
r(x,a,b)＝x
wherein s is a constant;
performing transformation in a (p, q, r) three-dimensional space, and making x (p, q, r) = r, so as to obtain:
a(p,q,r)＝3q-6r 2
b(p,q,r)＝2p-6rq+8r 3 (9)
the prevalence of mutations is then set as:
{r,3q-6r 2 ,2p-6rq+8r 3 ,-2pr+3qr 2 -3r 4 } (10)
the singular set of the snap map x requires p =0, then the singular set is:
{r,3q-6r 2 ,-6rq+8r 3 ,3qr 2 -3r 4 } (11)
let q =0, the cubic term of the mutation prevalence set vanishes, and the singular set is:
{r,-6r 2 ,8r 3 ,-3r 4 } (12)
the bifurcation set H is represented as:
{3q-6r 2 ,-6rq+8r 3 ,3qr 2 -3r 4 } (13)
the set of cusp lines for the dovetail mutation model is:
{a,b,c}＝{-6r 2 ,8r 3 ,-3r 4 } (14)。
5. the unmanned agricultural machinery vehicle-trapping early warning method according to claim 4, wherein the step S22 is specifically as follows:
based on the symmetry characteristic of the bifurcation set, selecting a half plane with b =0,a < 0 for analysis, and rewriting the formula (3) as follows:
x 4 +ax 2 +c＝0 (15)
when the formula (15) is regarded as a completely flat mode, the agricultural machinery vehicle-trapping discriminant Δ is:
Δ＝a 2 -4c (16)
when the delta is less than 0, the formula (16) has no solid root, and the mutation is shown, namely the agricultural machinery is trapped;
when delta is larger than 0, the formula (16) has a solid root, which indicates that no mutation occurs and the agricultural machinery is in a stable working state;
when Δ =0, it indicates a critical state.
6. The unmanned agricultural machinery vehicle-trapping early warning method according to claim 5, wherein the step S23 specifically comprises:
by height difference delta h and roll angle
And the transverse position deviation delta e is used as a control variable, the agricultural machinery speed v representing mutation is used as a state variable, a dovetail type mutation model is established, and the following steps are performed:
a＝AΔh
c＝CΔe (17)
wherein, A, B and C are dovetail mutation model parameters;
substituting the formula (17) into the formulas (2) to (16), namely establishing a driving potential function of the dovetail type sudden change model for normal operation of the agricultural machinery:
7. the unmanned agricultural machinery vehicle-trapping early warning method according to claim 6, wherein the step S3 specifically comprises:
s31, establishing an agricultural machinery vehicle trapping early warning mechanism;
s32, evaluating the early warning accuracy of the agricultural machinery vehicle trapping;
and S33, optimizing the particle swarm optimization.
8. The unmanned agricultural machinery vehicle-trapping early warning method according to claim 7, wherein the step S31 specifically comprises:
setting the prediction step length as N, the data length as N, and calculating the speed v of the agricultural machine and the control variable delta h (i),
Substituting the sequence of the delta e (i) into a formula (16) for training and judging, and carrying out data point classification on the dovetail type mutation model according to a judged result; when in the prediction time period [ t ] i ,t i +N]If delta < 0 exists in the agricultural machinery, the agricultural machinery is considered to be possibly trapped.
9. The unmanned agricultural machinery vehicle-trapping early warning method according to claim 7, wherein the step S32 is specifically as follows:
in order to evaluate the accuracy of the early warning of the sinking of the agricultural machinery, a prediction evaluation method is designed:
wherein, P trap 、F trap 、HSS、PSS、N tp 、N fn 、N fp And N tn Respectively representing the correct rate and the wrong rate of the trapped vehicle judgment, the Heidke score, the Peirce score, the number of times of the occurrence and the correct early warning of the trapped vehicle, the number of times of the occurrence and the wrong early warning of the trapped vehicle, the number of times of the non-occurrence and the non-early warning of the trapped vehicle, wherein all the evaluation index value domains are [0,1]；
In order to obtain maximum early warning accuracy, an objective function is designed:
f(p)＝max PSS (20)
the constraint conditions are as follows:
introduction of relaxation factor lambda 1 And λ 2 Equation (21) is changed to:
wherein an initial value λ is set 1 ＝0.7，λ 2 ＝0.3。
10. The unmanned agricultural machinery vehicle-trapping early warning method according to claim 7, wherein the step S33 is specifically as follows:
and (3) performing objective function optimization solution on the formula (20) by adopting a particle swarm optimization algorithm and taking the formula (22) as measurement constraint, and repeatedly training and optimizing the trapping mutation model by evaluating the accuracy of prediction on experimental sample data to obtain the parameter values of the A, B and C models.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210389016.0A CN115047207B (en) | 2022-04-14 | 2022-04-14 | Early warning method for vehicle sinking of unmanned agricultural machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210389016.0A CN115047207B (en) | 2022-04-14 | 2022-04-14 | Early warning method for vehicle sinking of unmanned agricultural machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115047207A CN115047207A (en) | 2022-09-13 |
| CN115047207B true CN115047207B (en) | 2023-03-14 |
Family
ID=83156938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210389016.0A Active CN115047207B (en) | 2022-04-14 | 2022-04-14 | Early warning method for vehicle sinking of unmanned agricultural machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115047207B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116069043B (en) * | 2023-03-24 | 2023-08-15 | 华南农业大学 | Unmanned agricultural machinery operation speed autonomous decision-making method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103114554A (en) * | 2013-02-04 | 2013-05-22 | 河海大学 | Forewarning method of concrete dam damage field evolution state |
| JP2016193665A (en) * | 2015-03-31 | 2016-11-17 | 公益財団法人鉄道総合技術研究所 | Creation method for rolling stock and track interaction analytic model |
| CN109955810A (en) * | 2017-12-14 | 2019-07-02 | 西北农林科技大学 | A kind of sunken vehicle grading forewarning system system of wheeled tractor |
| CN110053628A (en) * | 2018-01-18 | 2019-07-26 | 西北农林科技大学 | A kind of sunken car test examining system of wheeled vehicle |
| CN112462741A (en) * | 2020-11-30 | 2021-03-09 | 华南农业大学 | Unmanned agricultural machinery vehicle-trapping detection alarm system based on cloud platform |
-
2022
- 2022-04-14 CN CN202210389016.0A patent/CN115047207B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103114554A (en) * | 2013-02-04 | 2013-05-22 | 河海大学 | Forewarning method of concrete dam damage field evolution state |
| JP2016193665A (en) * | 2015-03-31 | 2016-11-17 | 公益財団法人鉄道総合技術研究所 | Creation method for rolling stock and track interaction analytic model |
| CN109955810A (en) * | 2017-12-14 | 2019-07-02 | 西北农林科技大学 | A kind of sunken vehicle grading forewarning system system of wheeled tractor |
| CN110053628A (en) * | 2018-01-18 | 2019-07-26 | 西北农林科技大学 | A kind of sunken car test examining system of wheeled vehicle |
| CN112462741A (en) * | 2020-11-30 | 2021-03-09 | 华南农业大学 | Unmanned agricultural machinery vehicle-trapping detection alarm system based on cloud platform |
Non-Patent Citations (1)
| Title |
|---|
| 基于燕尾突变的车辆脱轨机理研究;刘文辉等;《机械工程与自动化》;20150215(第01期);1-3、6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115047207A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112347567B (en) | Vehicle intention and track prediction method | |
| CN107958269B (en) | Driving risk degree prediction method based on hidden Markov model | |
| Xing et al. | Energy oriented driving behavior analysis and personalized prediction of vehicle states with joint time series modeling | |
| CN107346460B (en) | Following operating mode Forecasting Methodology based on the lower front truck operation information of intelligent network contact system | |
| Tran et al. | A Hidden Markov Model based driver intention prediction system | |
| CN115047207B (en) | Early warning method for vehicle sinking of unmanned agricultural machine | |
| CN109219547A (en) | Method for estimating the probability distribution of the maximum friction coefficient at the current and/or following way point of vehicle | |
| CN106599827A (en) | Small target rapid detection method based on deep convolution neural network | |
| CN104331953A (en) | Car behavior data identification and management method based on internet of things | |
| CN113859266B (en) | Method and system for predicting lane change track of unstructured road target vehicle | |
| JP2020135243A (en) | Model creation device, prediction device, model creation method, and model creation program | |
| CN108510737B (en) | Unmanned vehicle power supply real-time monitoring method and device integrating wind environment | |
| CN110910531B (en) | Rapid pavement friction coefficient detection method based on vehicle-mounted OBD information | |
| Wirthmüller et al. | Predicting the time until a vehicle changes the lane using LSTM-based recurrent neural networks | |
| CN112677982B (en) | Vehicle longitudinal speed planning method based on driver characteristics | |
| JP5041160B2 (en) | Driving assistance device | |
| CN113204920B (en) | Intelligent vehicle lane change comfort evaluation and track planning method and device based on support vector machine | |
| CN115285135A (en) | Construction method of deep reinforcement learning vehicle following model fusing driving style | |
| CN111598142A (en) | Outdoor terrain classification method for wheeled mobile robot | |
| CN108549037B (en) | A kind of automatic driving vehicle power supply prediction technique and system based on parallel neural network | |
| CN108510130B (en) | Intelligent unmanned vehicle limit mileage intelligent multi-source evaluation method and device | |
| CN115675098A (en) | Intelligent network-connected automobile kinetic energy recovery system, method and equipment based on user characteristic difference and storage medium | |
| JP2013199222A (en) | Driving evaluation apparatus | |
| Ding et al. | An Extended Car‐Following Model in Connected and Autonomous Vehicle Environment: Perspective from the Cooperation between Drivers | |
| CN112632705B (en) | Road feel simulation method based on GMM and Gaussian process regression |
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 |