CN108572648B - Unmanned vehicle power supply multi-source fusion prediction method and system - Google Patents
Unmanned vehicle power supply multi-source fusion prediction method and system Download PDFInfo
- Publication number
- CN108572648B CN108572648B CN201810372830.5A CN201810372830A CN108572648B CN 108572648 B CN108572648 B CN 108572648B CN 201810372830 A CN201810372830 A CN 201810372830A CN 108572648 B CN108572648 B CN 108572648B
- Authority
- CN
- China
- Prior art keywords
- value
- neural network
- road
- unmanned vehicle
- snow depth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004927 fusion Effects 0.000 title claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 3
- 238000013528 artificial neural network Methods 0.000 claims description 84
- 238000012545 processing Methods 0.000 claims description 73
- 239000002245 particle Substances 0.000 claims description 69
- 230000005540 biological transmission Effects 0.000 claims description 32
- 238000005259 measurement Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 238000013519 translation Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 230000002028 premature Effects 0.000 claims description 9
- 238000007499 fusion processing Methods 0.000 claims description 6
- 230000010152 pollination Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 241000196324 Embryophyta Species 0.000 claims description 3
- 235000009413 Ratibida columnifera Nutrition 0.000 claims description 3
- 241000510442 Ratibida peduncularis Species 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 210000002364 input neuron Anatomy 0.000 claims description 3
- 238000000691 measurement method Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000009825 accumulation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- 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]
-
- 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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention provides a multi-source fusion prediction method and a multi-source fusion prediction system for a power supply of an unmanned vehicle. The system is simple in structure, gets rid of dependence on the fixed accumulated snow depth measuring device along the road, realizes resource optimization configuration of the power supply system of the unmanned vehicle, and improves the cruising ability of the unmanned vehicle to a certain degree.
Description
Technical Field
The invention belongs to the field of unmanned vehicles, and particularly relates to a multi-source fusion prediction method and system for an unmanned vehicle power supply.
Background
In recent years, with the higher and higher requirements of the market on vehicle safety and intellectualization, unmanned vehicles become a popular technology, and more enterprises and scientific research institutions participate in the field. Companies such as google and wolvo are always dedicated to research and development of new technologies of unmanned vehicles, but most of the technologies are distributed in aspects of improving navigation technologies of unmanned vehicles, improving positioning accuracy, optimizing decision control systems, distributing right of way, performing intelligent traffic comprehensive planning and the like. However, as a power source of the vehicle, the vehicle-mounted power source is the basis for all technical realization of the unmanned vehicle. Without an efficient vehicle-mounted power supply, advanced vehicle-mounted unmanned technologies and related control technologies become decorations.
At present, the technology is rarely disclosed at home and abroad, and the residual electric quantity of the unmanned vehicle in dynamic ice and snow weather can be accurately predicted. The current general technical means is to make simple mathematical calculation according to the target mileage, the battery capacity and the running speed to obtain the current real-time running mileage which can be continued by the residual vehicle-mounted capacity, and then guide the unmanned vehicle to charge before the power supply is exhausted. However, in practical situations, the use of the vehicle-mounted power supply of the vehicle is closely related to road conditions (such as ascending and descending), and vehicle driving environments (such as weather, rain and snow), and physical parameters between the vehicle-mounted power supply and the vehicle-mounted power supply are strong and nonlinear and cannot be obtained through simple mathematical calculation, and the problem can be solved only through the fusion of the road and the weather parameters and the online intelligent learning of collected physical data.
In summary, accurate calculation of the electric quantity on board the unmanned vehicle, especially prediction of the electric quantity of the unmanned vehicle in severe weather such as ice and snow environment, is crucial. The application prospect of the technology is very wide and remarkable.
Disclosure of Invention
The invention provides a multi-source fusion prediction method and system for a power supply of an unmanned vehicle, and aims to solve the problems that a prediction method for the battery power of the unmanned vehicle in the prior art is poor in adaptability to external environment interference, poor in system prediction feasibility and poor in practicability, and particularly, in an ice and snow environment, various collected parameters such as effective accumulated snow depth, road gradient and battery temperature are fused into a comprehensive prediction model for the battery power of the unmanned vehicle, so that high-reliability and high-precision prediction of a battery is realized.
A multi-source fusion prediction method for a power supply of an unmanned vehicle comprises the following steps:
step 1: acquiring historical driving data of the unmanned vehicle in the ice and snow environment;
the driving data comprises road accumulated snow depth, road gradient, battery temperature, power consumption rate and residual electric quantity at each moment;
step 2: constructing a battery power consumption rate fitting model of the unmanned vehicle based on the wavelet neural network;
training a wavelet neural network by taking the road snow depth, the road gradient and the battery temperature in the historical driving data as input data and taking the power consumption rate as output data to obtain a wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle;
the number of input layer nodes of the wavelet neural network is 3, the number of hidden layer wavelet elements is 6, the number of output layer nodes is 1, the hidden layer wavelet neurons adopt Mexican Hat wavelet functions, and the output layer nodes adopt Sigmoid functions; the maximum iteration number in the training process is set to be 1500, the training learning rate is 0.1, and the threshold value is 0.0002;
and step 3: constructing a prediction model of the remaining electric quantity of the unmanned vehicle based on a BP neural network;
training a BP neural network by taking the power consumption rate and the corresponding residual electric quantity at the time t in the historical driving data as input data and taking the residual electric quantity at the time t +1 as output data to obtain a residual electric quantity prediction model based on the BP neural network;
the input layer of the BP neural network comprises 2 nodes, the maximum iteration number is set to be 200, and the training learning rate is 0.1;
and 4, step 4: predicting the remaining capacity at the next moment;
inputting effective road accumulated snow depth, road gradient and battery temperature data obtained in real time into a wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle to obtain the battery power consumption rate at the current moment, and inputting a BP neural network-based residual power prediction model based on the obtained current battery power consumption rate and real-time residual power to obtain the residual power at the next moment;
the effective road snow depth is obtained by weighting and fusing a road snow depth measured value and an observed value;
the measured value of the road accumulated snow depth is obtained by real-time measurement and calculation through vehicle-mounted laser sensors and inclination sensors which are arranged on two sides of the bottom of the unmanned vehicle;
the road snow depth observation value is obtained by acquiring a road image by using an image acquisition device, extracting shape characteristics of the road image, extracting an area contour from edges of the shape characteristics and calculating the area contour.
The road snow depth measurement values comprise road snow depths measured from two sides, and when the road snow depths are weighted and fused, H-d 1H 1+ d 2H 2+ d 3H 3, d1+ d2+ d3 are 1; h1 and H2 are measured values of the snow depth of the road surface measured at two sides respectively, H3 is an observed value of the snow depth of the road surface, and d1, d2 and d3 are weights for obtaining the snow depth of the effective road surface;
further, in the wavelet neural network-based unmanned vehicle battery power consumption rate fitting model, the process of obtaining the weight of the effective road snow depth, the weight of the wavelet neural network, the threshold and the telescopic translation coefficient by optimizing with the adaptive pollination algorithm is as follows:
step C1: the positions of the population pollen individuals are used as a weight for acquiring the accumulated snow depth of the effective road surface, a weight of a wavelet neural network, a threshold and a telescopic translation coefficient, and a population is initialized;
the value range of the population scale is [55,220], the value range of the initial value of the variation factor is [0.02,0.15], the value range of the maximum iteration number is [110,400], and the value range of the maximum search precision is [0.035,0.12 ];
step C2: setting a fitness function and acquiring the optimal individual in the population;
substituting a weight value used for acquiring the effective road surface snow depth, a weight value of a wavelet neural network, a threshold value and a telescopic translation coefficient corresponding to the individual population position into a power consumption rate prediction model based on the wavelet neural network, calculating an output value by using the power consumption rate prediction model based on the weight value, the threshold value and the telescopic translation coefficient of the wavelet neural network determined by the individual population position, and taking the reciprocal of the Mean Square Error (MSE) of the output value and an actual value as a first fitness function f1 (x);
step C3: calculating the adaptive value of each individual, and keeping the individual with the minimum adaptive value and the current optimal solution g*；
Step C4: randomly generating rand1Calculating the transition probability p according to the formula (1) to adjust the global search in the flower pollination algorithmAnd translation between local searches;
p＝0.8+0.2×rand1(1)
step C5: randomly generating rand belonging to [0, 1], and if the conversion probability p is greater than rand, carrying out global search by using a formula (2);
wherein the content of the first and second substances,
denotes the position of pollen at the t-th iteration, g*The optimal solution in the current population is represented, the parameter L represents the step length and is taken as 0.5;
step C6: if the conversion probability p is less than or equal to rand, calculating according to the formula (3), and substituting the value into the formula (4) for local search;
wherein, rand2,rand3Is [0, 1]]The random number generated in the above-mentioned step (2),tis the value of the time-varying factor of the t-th iteration, lambda,1All are taken as 0.1;
wherein the content of the first and second substances,
and
respectively representing pollen of different flowers corresponding to the extreme learning machine parameters on the same plant;
step C7: calculating the fitness value and the optimal individual value g of all the updated individuals*Judging whether the maximum iteration times or the maximum search precision is reached, if so, taking the individual with the maximum fitness as the optimal individual, and outputting a base corresponding to the optimal individualAnd C4, obtaining the weight of the effective road surface snow depth, the weight of the wavelet neural network, the threshold and the expansion translation coefficient in the power consumption rate prediction model of the wavelet neural network, and returning to the step C4 for the next iteration if not.
Further, the specific process for acquiring the road snow depth observation value is as follows:
step A1: carrying out gray processing on the collected road surface image to obtain a gray image;
step A2: performing Gaussian filtering and gradient processing on the gray level image to obtain a filtered amplitude image;
step A3: extracting edge points from the filtered amplitude image by using a canny edge detection algorithm;
step A4: and detecting and connecting the extracted edge points by using a double-threshold algorithm to obtain an accumulated snow area contour line, and scanning the accumulated snow area contour line by adopting a field division standard block scanning pixel point method to obtain a road accumulated snow depth observation value.
Further, the pavement snow depth measurement value is corrected by utilizing the pavement image acquired by the image acquisition device, and the method specifically comprises the following steps:
step B1: converting the collected continuous multi-frame pavement images into gray level images;
step B2: the gray level of the gray level image of two continuous frames of road surface images is subjected to difference processing to obtain the gray level difference value D of the two frames of road surface imagesgreyAnd comparing the road condition with a preset difference threshold value, and judging the road condition according to the following formula:
step B3: multiplying the snow depth correction coefficient corresponding to the road condition with the road snow depth measurement value to obtain a correction value of the road snow depth measurement value;
the value range of the correction coefficient is as follows:
when the road is only accumulated with snow, the snow depth correction coefficient is 1.0;
when water is accumulated on the road, the snow depth correction coefficient is 0.6-0.7;
when the road is frozen, the snow depth correction coefficient is 0.7-0.8.
Further, the process of optimizing the weight and the threshold of the BP neural network in the residual power prediction model based on the BP neural network by using a quantum particle swarm algorithm with a self-adaptive weight is as follows:
step D1: taking the position vector of each quantum particle individual in the quantum particle swarm as the weight and the threshold of the BP neural network, and initializing the position vector parameters of the quantum particle swarm individual into random numbers of [ -1,1 ];
the value range of the number of the quantum particle swarm is [25,70], the value range of the number of the particles of the quantum particle swarm is [5,50], the value range of the maximum iteration number is [400,1000], the value range of the iteration number for constructing the elite swarm is [60,180], the value range of the premature convergence judgment threshold is [0.01,0.45], and the value range of the worst particle variation proportion% of the swarm is [ 2%, 7%);
step D2: setting a fitness function, and determining an initial optimal quantum particle individual position vector and iteration times t, wherein t is 1;
substituting the weight value and the threshold value corresponding to the quantum particle individual position vector into a face recognition model based on a BP (back propagation) neural network, calculating the current residual capacity by using a residual capacity prediction model based on the BP neural network determined by the quantum particle individual position vector, and taking the inverse of the mean square error of the predicted residual capacity and the actual value as a second fitness function f2 (x);
step D3: calculating the group fitness variance of each quantum particle swarm, and performing premature convergence judgment;
if the group fitness variance of the quantum particle swarm is smaller than the premature convergence judgment threshold gamma, performing variation on% of the worst fitness particles and the extreme population particles in the quantum particle swarm, and taking the particles with the best current fitness as the global optimal quantum particle individuals;
step D4: judging whether to establish an elite population;
when the iteration times are larger than the iteration times of the elite population, extracting extreme values of all the populations through information sharing among the populations to establish the elite population, and turning to the step D8, otherwise, turning to the step D5;
step D5: updating parameters of each population of particles;
step D6: recalculating and comparing the fitness value of each particle, and updating the individual extreme value if the fitness value is superior to the current individual extreme value; comparing the global extreme value particles, if the particle fitness value is superior to the current group extreme value, updating the global extreme value particles, enabling t to be t +1, and turning to the step D3;
step D7: the elite population continues to evolve;
step D8: and D3, judging whether the maximum iteration times are met, if so, exiting, otherwise, making t equal to t +1, switching to the step D3 until a global optimal value is found, and outputting the weight and the threshold of the BP neural network.
And further, sensing an included angle between the direction of the vehicle body and the horizontal direction by using an MEMS gyroscope in the vehicle-mounted inertial navigation system of the unmanned vehicle as a road gradient measured value.
Furthermore, the battery temperature of the unmanned vehicle is collected in real time by utilizing 16 non-contact temperature sensors uniformly distributed on the surface of the battery, a three-dimensional temperature distribution data graph on the surface of the battery is fitted through interpolation processing, and the maximum value is taken as the battery temperature.
A multi-source fusion prediction system for a power supply of an unmanned vehicle comprises a sensing layer, a transmission layer, a first processing layer and a second processing layer;
the sensing layer is used for sending the data information acquired by the sensing equipment to the transmission layer;
the sensing equipment comprises a laser sensor, an inclination angle sensor, a high-definition camera, a vehicle-mounted gyroscope and a non-contact temperature sensor which are arranged on the unmanned vehicle; the laser sensor and the inclination angle sensor are arranged at the middle points of wheel track lines on two sides of the bottom of the unmanned vehicle body, and the high-definition camera is arranged in the middle of the front end of the unmanned vehicle;
the laser sensor and the inclination angle sensor are used for measuring the effective accumulated snow depth in real time and uploading information to the transmission layer;
the high-definition camera is used for shooting road snow accumulation images at the front end of the actual position of the unmanned vehicle and sending each frame of shot images to the transmission layer;
the transmission layer forwards the data transmitted by the sensing layer to the first processing layer and the second processing layer;
the transmission layer comprises a wireless forwarding module and has a signal wireless forwarding function. The wireless forwarding module of the transmission layer is provided with a plurality of RS485 interfaces, supports a Zigbee short-distance wireless transmission mode with a plurality of transmission protocols and functions, and has a DTU (data transmission unit) function.
A sensor group consisting of a laser sensor and an inclination angle sensor and a non-contact temperature sensor are connected with a front-end processing module in the first processing layer through an RS485 interface;
the high-definition camera is connected with the front-end processing module in the first processing layer through a twisted pair and is accessed through the IP address of the network camera.
The first processing layer is used for processing the data information in real time and sending the data information to the transmission layer;
the first processing layer comprises a data information calculation module, an image processing module and a data fusion processing module, wherein the data information calculation module carries out comprehensive calculation processing on information collected by a laser sensor, an inclination angle sensor, a vehicle-mounted MEMS gyroscope and a temperature sensor in the sensing layer to obtain an effective accumulated snow depth measurement value, and calculates an optimal road gradient and an optimal battery temperature; the image processing module extracts snow contour features in an image acquired by the high-definition camera and performs feature recognition to form a snow contour envelope line to obtain an effective snow depth measurement value; the data fusion processing module performs weighted fusion on the effective snow depth measurement values obtained by the two measurement methods to obtain an optimal effective snow depth measurement value;
the second processing layer is used for predicting the battery electric quantity of the data processed by the first processing layer in real time;
the second processing layer comprises a wavelet neural network-based battery power consumption rate fitting network of the unmanned vehicle and a BP neural network-based unmanned vehicle residual electric quantity prediction network, the effective accumulated snow depth, the road gradient and the battery temperature after data fusion sent by the transmission layer are used as model input values, the battery power consumption rate corresponding to each acquisition unit is used as a model output value, data information acquired by a plurality of nodes is used as a training sample, the battery power consumption rate output by the previous layer of wavelet neural network-based unmanned vehicle battery power consumption rate fitting network is used as a next layer of BP neural network-based input neuron, and an intelligent prediction model of the battery electric quantity of the unmanned vehicle is constructed; and then, the intelligent prediction model of the battery power of the unmanned vehicle is transmitted to the second processing layer through the transmission layer after the data acquired by the sensing layer in real time through the first processing layer is processed, so that the real-time prediction of the battery power of the vehicle is obtained.
The data processing method in the unmanned vehicle power supply multi-source fusion prediction method is adopted in the data processing process of the first processing layer and the second processing layer.
Advantageous effects
The invention provides a multi-source fusion prediction method for a power supply of an unmanned vehicle, which realizes intelligent comprehensive calculation of battery power of the unmanned vehicle in complex environments such as an accumulated snow road environment and the like, organically combines real-time detection of road effective accumulated snow depth with calculation of the battery power of the unmanned vehicle, and provides more complete consideration for the design and research field of unmanned vehicle batteries.
The system comprehensively considers various factors such as the effective snow depth of the road, the road gradient and the battery temperature of the unmanned vehicle in the ice and snow environment, realizes vehicle-mounted accurate measurement of the effective snow depth of the road, gets rid of the dependence on a fixed snow depth measuring device along the road, realizes resource optimization configuration of an unmanned vehicle power supply system, and improves the cruising ability of the unmanned vehicle to a certain degree.
Drawings
FIG. 1 is a flow chart of an intelligent electric quantity prediction method for an unmanned vehicle in ice and snow weather;
FIG. 2 is a schematic view of a laser sensor and a tilt sensor measuring effective snow depth;
FIG. 3 is a frame diagram of an intelligent prediction system for electric quantity of an unmanned vehicle;
FIG. 4 is a schematic side view of the laser sensor and tilt sensor mounting locations;
FIG. 5 is a bottom view of the laser sensor and tilt sensor mounting locations.
Detailed Description
The invention will be further described with reference to the following figures and examples.
As shown in fig. 1, a multi-source fusion prediction method for a power supply of an unmanned vehicle includes the following steps:
step 1: acquiring historical driving data of the unmanned vehicle in the ice and snow environment;
the driving data comprises road accumulated snow depth, road gradient, battery temperature, power consumption rate and residual electric quantity at each moment;
an MEMS gyroscope in a vehicle-mounted inertial navigation system of the unmanned vehicle is used for sensing an included angle between the direction of a vehicle body and the horizontal direction to be used as a road gradient measured value.
The battery temperature of the unmanned vehicle is collected in real time by 16 non-contact temperature sensors uniformly distributed on the surface of the battery, a three-dimensional temperature distribution data graph on the surface of the battery is fitted through interpolation processing, and the maximum value is taken as the battery temperature.
Step 2: constructing a battery power consumption rate fitting model of the unmanned vehicle based on the wavelet neural network;
training a wavelet neural network by taking the road snow depth, the road gradient and the battery temperature in the historical driving data as input data and taking the power consumption rate as output data to obtain a wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle;
the number of input layer nodes of the wavelet neural network is 3, the number of hidden layer wavelet elements is 6, the number of output layer nodes is 1, the hidden layer wavelet neurons adopt Mexican Hat wavelet functions, and the output layer nodes adopt Sigmoid functions; the maximum iteration number in the training process is set to be 1500, the training learning rate is 0.1, and the threshold value is 0.0002;
the process of optimizing the weight used for obtaining the effective road surface accumulated snow depth, the weight of the wavelet neural network, the threshold and the telescopic translation coefficient by adopting the self-adaptive pollination algorithm in the wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle is as follows:
step C1: the positions of the population pollen individuals are used as a weight for acquiring the accumulated snow depth of the effective road surface, a weight of a wavelet neural network, a threshold and a telescopic translation coefficient, and a population is initialized;
the value range of the population scale is [55,220], the value range of the initial value of the variation factor is [0.02,0.15], the value range of the maximum iteration number is [110,400], and the value range of the maximum search precision is [0.035,0.12 ];
step C2: setting a fitness function and acquiring the optimal individual in the population;
substituting a weight value used for acquiring the effective road surface snow depth, a weight value of a wavelet neural network, a threshold value and a telescopic translation coefficient corresponding to the individual population position into a power consumption rate prediction model based on the wavelet neural network, calculating an output value by using the power consumption rate prediction model based on the weight value, the threshold value and the telescopic translation coefficient of the wavelet neural network determined by the individual population position, and taking the reciprocal of the Mean Square Error (MSE) of the output value and an actual value as a first fitness function f1 (x);
step C3: calculating the adaptive value of each individual, and keeping the individual with the minimum adaptive value and the current optimal solution g*；
Step C4: randomly generating rand1Calculating a conversion probability p according to the formula (1) to adjust the conversion between the global search and the local search in the flower pollination algorithm;
p＝0.8+0.2×rand1(1)
step C5: randomly generating rand belonging to [0, 1], and if the conversion probability p is greater than rand, carrying out global search by using a formula (2);
wherein the content of the first and second substances,
denotes the position of pollen at the t-th iteration, g*The optimal solution in the current population is represented, the parameter L represents the step length and is taken as 0.5;
step C6: if the conversion probability p is less than or equal to rand, calculating according to the formula (3), and substituting the value into the formula (4) for local search;
wherein, rand2,rand3Is [0, 1]]The random number generated in the above-mentioned step (2),tis the value of the time-varying factor of the t-th iteration, lambda,1All are taken as 0.1;
wherein the content of the first and second substances,
and
respectively representing pollen of different flowers corresponding to the extreme learning machine parameters on the same plant;
step C7: calculating the fitness value and the optimal individual value g of all the updated individuals*And judging whether the maximum iteration times or the maximum search precision is reached, if so, outputting a weight value used for acquiring the effective road surface snow depth, the weight value, the threshold value and the telescopic translation coefficient in the wavelet neural network-based power consumption rate prediction model corresponding to the optimal individual by taking the individual with the maximum fitness as the optimal individual, otherwise, returning to the step C4 to perform the next iteration.
And step 3: constructing a prediction model of the remaining electric quantity of the unmanned vehicle based on a BP neural network;
training a BP neural network by taking the power consumption rate and the corresponding residual electric quantity at the time t in the historical driving data as input data and taking the residual electric quantity at the time t +1 as output data to obtain a residual electric quantity prediction model based on the BP neural network;
the input layer of the BP neural network comprises 2 nodes, the maximum iteration number is set to be 200, and the training learning rate is 0.1;
the weight and the threshold of the BP neural network in the residual electric quantity prediction model based on the BP neural network are optimized by adopting a quantum particle swarm algorithm with a self-adaptive weight, and the process is as follows:
step D1: taking the position vector of each quantum particle individual in the quantum particle swarm as the weight and the threshold of the BP neural network, and initializing the position vector parameters of the quantum particle swarm individual into random numbers of [ -1,1 ];
the value range of the number of the quantum particle swarm is [25,70], the value range of the number of the particles of the quantum particle swarm is [5,50], the value range of the maximum iteration number is [400,1000], the value range of the iteration number for constructing the elite swarm is [60,180], the value range of the premature convergence judgment threshold is [0.01,0.45], and the value range of the worst particle variation proportion% of the swarm is [ 2%, 7%);
step D2: setting a fitness function, and determining an initial optimal quantum particle individual position vector and iteration times t, wherein t is 1;
substituting the weight value and the threshold value corresponding to the quantum particle individual position vector into a face recognition model based on a BP (back propagation) neural network, calculating the current residual capacity by using a residual capacity prediction model based on the BP neural network determined by the quantum particle individual position vector, and taking the inverse of the mean square error of the predicted residual capacity and the actual value as a second fitness function f2 (x);
step D3: calculating the group fitness variance of each quantum particle swarm, and performing premature convergence judgment;
if the group fitness variance of the quantum particle swarm is smaller than the premature convergence judgment threshold gamma, performing variation on% of the worst fitness particles and the extreme population particles in the quantum particle swarm, and taking the particles with the best current fitness as the global optimal quantum particle individuals;
step D4: judging whether to establish an elite population;
when the iteration times are larger than the iteration times of the elite population, extracting extreme values of all the populations through information sharing among the populations to establish the elite population, and turning to the step D8, otherwise, turning to the step D5;
step D5: updating parameters of each population of particles;
step D6: recalculating and comparing the fitness value of each particle, and updating the individual extreme value if the fitness value is superior to the current individual extreme value; comparing the global extreme value particles, if the particle fitness value is superior to the current group extreme value, updating the global extreme value particles, enabling t to be t +1, and turning to the step D3;
step D7: the elite population continues to evolve;
step D8: and D3, judging whether the maximum iteration times are met, if so, exiting, otherwise, making t equal to t +1, switching to the step D3 until a global optimal value is found, and outputting the weight and the threshold of the BP neural network.
And 4, step 4: predicting the remaining capacity at the next moment;
inputting effective road accumulated snow depth, road gradient and battery temperature data obtained in real time into a wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle to obtain the battery power consumption rate at the current moment, and inputting a BP neural network-based residual power prediction model based on the obtained current battery power consumption rate and real-time residual power to obtain the residual power at the next moment;
the effective road snow depth is obtained by weighting and fusing a road snow depth measured value and an observed value;
the measured value of the road accumulated snow depth is obtained by real-time measurement and calculation through vehicle-mounted laser sensors and inclination sensors which are arranged on two sides of the bottom of the unmanned vehicle;
as shown in fig. 2, the laser sensor and the tilt sensor collect data with a 5s collection period. The laser sensor simultaneously emits laser to two preset directions, wherein one laser beam which is vertical to the ground and downward is received by a receiver of the laser sensor, and the propagation time of the laser is t1The other bundle willReceived by the receiver on the opposite side, and the laser propagation time is t2(ii) a The inclination angle sensor measures the inclination angle theta of the two laser beams; the data information calculation module in the front-end processing module of the processing layer 1 calculates the effective snow depth H on one side by using the laser propagation time length, the laser beam inclination angle and the propagation speed of the laser in the normal state1. The working principle diagram is shown in fig. 2.
From fig. 2, it can be derived:
H1＝L1-L2·cosθ
wherein v is the propagation speed of the laser in the normal state, and is 3 × 108m/s；H1Is a single side effective snow depth measurement.
Obtaining effective accumulated snow depth value H measured by sensor group on the other side of vehicle bottom by using same principle2。
The road snow depth observation value is obtained by acquiring a road image by using an image acquisition device, extracting shape characteristics of the road image, extracting an area contour from edges of the shape characteristics and calculating the area contour.
The specific process for acquiring the road accumulated snow depth observation value is as follows:
step A1: carrying out gray processing on the collected road surface image to obtain a gray image;
step A2: performing Gaussian filtering and gradient processing on the gray level image to obtain a filtered amplitude image;
step A3: extracting edge points from the filtered amplitude image by using a canny edge detection algorithm;
step A4: and detecting and connecting the extracted edge points by using a double-threshold algorithm to obtain an accumulated snow area contour line, and scanning the accumulated snow area contour line by adopting a field division standard block scanning pixel point method to obtain a road accumulated snow depth observation value.
The method comprises the following steps of correcting a pavement accumulated snow depth measurement value by utilizing a pavement image acquired by an image acquisition device, and specifically comprises the following steps:
step B1: converting the collected continuous multi-frame pavement images into gray level images;
wherein F (x, y) represents a gray image, F (x, y) is a road surface image corresponding to F (x, y), and FmaxThe saturation brightness value of the human eye visual system is 225; m is the maximum value of the user-defined gray function value domain, and the value is 255;
step B2: the gray level of the gray level image of two continuous frames of road surface images is subjected to difference processing to obtain the gray level difference value D of the two frames of road surface imagesgreyAnd comparing the road condition with a preset difference threshold value, and judging the road condition according to the following formula:
step B3: multiplying the snow depth correction coefficient corresponding to the road condition with the road snow depth measurement value to obtain a correction value of the road snow depth measurement value;
the value range of the correction coefficient is as follows:
when the road is only accumulated with snow, the snow depth correction coefficient is 1.0;
when water is accumulated on the road, the snow depth correction coefficient is 0.6-0.7;
when the road is frozen, the snow depth correction coefficient is 0.7-0.8.
As shown in fig. 3, a multi-source fusion prediction system for a power supply of an unmanned vehicle includes a sensing layer, a transmission layer, a first processing layer and a second processing layer;
the sensing layer is used for sending the data information acquired by the sensing equipment to the transmission layer;
the sensing equipment comprises a laser sensor, an inclination angle sensor, a high-definition camera, a vehicle-mounted gyroscope and a non-contact temperature sensor which are arranged on the unmanned vehicle; as shown in fig. 4 and 5, the laser sensor and the tilt sensor are arranged at the middle points of the track lines on the two sides of the bottom of the unmanned vehicle body, and the high-definition camera is arranged in the middle of the front end of the unmanned vehicle;
the laser sensor and the inclination angle sensor are used for measuring the effective accumulated snow depth in real time and uploading information to the transmission layer;
the high-definition camera is used for shooting road snow accumulation images at the front end of the actual position of the unmanned vehicle and sending each frame of shot images to the transmission layer;
the transmission layer forwards the data transmitted by the sensing layer to the first processing layer and the second processing layer;
the transmission layer comprises a wireless forwarding module and has a signal wireless forwarding function. The wireless forwarding module of the transmission layer is provided with a plurality of RS485 interfaces, supports a Zigbee short-distance wireless transmission mode with a plurality of transmission protocols and functions, and has a DTU (data transmission unit) function.
A sensor group consisting of a laser sensor and an inclination angle sensor and a non-contact temperature sensor are connected with a front-end processing module in the first processing layer through an RS485 interface;
the high-definition camera is connected with the front-end processing module in the first processing layer through a twisted pair and is accessed through the IP address of the network camera.
The first processing layer is used for processing the data information in real time and sending the data information to the transmission layer;
the first processing layer comprises a data information calculation module, an image processing module and a data fusion processing module, wherein the data information calculation module carries out comprehensive calculation processing on information collected by a laser sensor, an inclination angle sensor, a vehicle-mounted MEMS gyroscope and a temperature sensor in the sensing layer to obtain an effective accumulated snow depth measurement value, and calculates an optimal road gradient and an optimal battery temperature; the image processing module extracts snow contour features in an image acquired by the high-definition camera and performs feature recognition to form a snow contour envelope line to obtain an effective snow depth measurement value; the data fusion processing module performs weighted fusion on the effective snow depth measurement values obtained by the two measurement methods to obtain an optimal effective snow depth measurement value;
the second processing layer is used for predicting the battery electric quantity of the data processed by the first processing layer in real time;
the second processing layer comprises a wavelet neural network-based battery power consumption rate fitting network of the unmanned vehicle and a BP neural network-based unmanned vehicle residual electric quantity prediction network, the effective accumulated snow depth, the road gradient and the battery temperature after data fusion sent by the transmission layer are used as model input values, the battery power consumption rate corresponding to each acquisition unit is used as a model output value, data information acquired by a plurality of nodes is used as a training sample, the battery power consumption rate output by the previous layer of wavelet neural network-based unmanned vehicle battery power consumption rate fitting network is used as a next layer of BP neural network-based input neuron, and an intelligent prediction model of the battery electric quantity of the unmanned vehicle is constructed; and then, the intelligent prediction model of the battery power of the unmanned vehicle is transmitted to the second processing layer through the transmission layer after the data acquired by the sensing layer in real time through the first processing layer is processed, so that the real-time prediction of the battery power of the vehicle is obtained.
The data processing method in the unmanned vehicle power supply multi-source fusion prediction method is adopted in the data processing process of the first processing layer and the second processing layer.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (8)
1. A multi-source fusion prediction method for a power supply of an unmanned vehicle is characterized by comprising the following steps:
step 1: acquiring historical driving data of the unmanned vehicle in the ice and snow environment;
the historical driving data comprises road accumulated snow depth, road gradient, battery temperature, battery power consumption rate and residual electric quantity at each moment;
step 2: constructing a battery power consumption rate fitting model of the unmanned vehicle based on the wavelet neural network;
training a wavelet neural network by taking the road snow depth, the road gradient and the battery temperature in the historical driving data as input data and taking the battery power consumption rate as output data to obtain a wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle;
the number of input layer nodes of the wavelet neural network is 3, the number of hidden layer wavelet elements is 6, the number of output layer nodes is 1, the hidden layer wavelet neurons adopt Mexican Hat wavelet functions, and the output layer nodes adopt Sigmoid functions; the maximum iteration number in the training process is set to be 1500, the training learning rate is 0.1, and the threshold value is 0.0002;
and step 3: constructing a prediction model of the remaining electric quantity of the unmanned vehicle based on a BP neural network;
training a BP neural network by taking the power consumption rate and the corresponding residual electric quantity at the time t in the historical driving data as input data and taking the residual electric quantity at the time t +1 as output data to obtain a residual electric quantity prediction model based on the BP neural network;
the input layer of the BP neural network comprises 2 nodes, the maximum iteration number is set to be 200, and the training learning rate is 0.1;
and 4, step 4: predicting the remaining capacity at the next moment;
inputting effective road accumulated snow depth, road gradient and battery temperature data obtained in real time into a wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle to obtain the battery power consumption rate at the current moment, and inputting a BP neural network-based residual power prediction model based on the obtained current battery power consumption rate and real-time residual power to obtain the residual power at the next moment;
the effective road surface snow depth is obtained by weighting and fusing a road surface snow depth measured value and a road surface snow depth observed value;
the measured value of the road accumulated snow depth is obtained by real-time measurement and calculation through vehicle-mounted laser sensors and inclination sensors which are arranged on two sides of the bottom of the unmanned vehicle;
the road snow depth observation value is obtained by acquiring a road image by using an image acquisition device, extracting shape characteristics of the road image, extracting an area contour from edges of the shape characteristics and calculating the area contour.
2. The method of claim 1, wherein the weight for obtaining the effective road snow depth, the weight of the wavelet neural network, the threshold and the telescopic translation coefficient in the wavelet neural network-based unmanned vehicle battery power consumption rate fitting model are obtained by optimizing with an adaptive pollination algorithm as follows:
step C1: the positions of the population pollen individuals are used as a weight for acquiring the accumulated snow depth of the effective road surface, a weight of a wavelet neural network, a threshold and a telescopic translation coefficient, and a population is initialized;
the value range of the population scale is [55,220], the value range of the initial value of the variation factor is [0.02,0.15], the value range of the maximum iteration number is [110,400], and the value range of the maximum search precision is [0.035,0.12 ];
step C2: setting a fitness function and acquiring the optimal individual in the population;
substituting a weight value used for acquiring the effective road surface snow depth, a weight value of a wavelet neural network, a threshold value and a telescopic translation coefficient corresponding to the individual population position into a power consumption rate prediction model based on the wavelet neural network, calculating an output value by using the power consumption rate prediction model based on the weight value, the threshold value and the telescopic translation coefficient of the wavelet neural network determined by the individual population position, and taking the reciprocal of the Mean Square Error (MSE) of the output value and an actual value as a first fitness function f1 (x);
step C3: calculating the adaptive value of each individual, and keeping the individual with the minimum adaptive value and the optimal solution g in the current population*；
Step C4: randomly generating rand1Calculating a conversion probability p according to the formula (1) to adjust the conversion between the global search and the local search in the flower pollination algorithm;
p＝0.8+0.2×rand1(1)
step C5: randomly generating rand belonging to [0, 1], and if the conversion probability p is greater than rand, carrying out global search by using a formula (2);
wherein the content of the first and second substances,
denotes the position of pollen at the t-th iteration, g*The optimal solution in the current population is represented, the parameter L represents the step length and is taken as 0.5;
step C6: if the conversion probability p is less than or equal to rand, calculating according to the formula (3), and substituting the value into the formula (4) for local search;
wherein, rand2,rand3Is [0, 1]]The random number generated in the above-mentioned step (2),tis the value of the time-varying factor of the t-th iteration, lambda,1All are taken as 0.1;
wherein the content of the first and second substances,
and
pollen of different flowers on the same plant corresponding to the parameters of the wavelet neural network-based battery power consumption rate fitting model of the unmanned vehicle is respectively represented;
step C7: calculating the fitness value and the optimal individual value g of all the updated individuals*Judging whether the maximum iteration times or the maximum search precision is reached, if so, taking the individual with the maximum fitness as an optimal individual, and outputting the power consumption prediction based on the wavelet neural network corresponding to the optimal individualAnd C4 is returned to for the next iteration if the weight of the effective road surface snow depth, the weight of the wavelet neural network, the threshold and the expansion translation coefficient are not obtained.
3. The method according to claim 1, characterized in that the specific process for obtaining the observed value of the depth of the accumulated snow on the road surface is as follows:
step A1: carrying out gray processing on the collected road surface image to obtain a gray image;
step A2: performing Gaussian filtering and gradient processing on the gray level image to obtain a filtered amplitude image;
step A3: extracting edge points from the filtered amplitude image by using a canny edge detection algorithm;
step A4: and detecting and connecting the extracted edge points by using a double-threshold algorithm to obtain an accumulated snow area contour line, and scanning the accumulated snow area contour line by adopting a field division standard block scanning pixel point method to obtain a road accumulated snow depth observation value.
4. The method according to claim 2, characterized in that the road surface snow depth measurement value is corrected by using the road surface image collected by the image collecting device, and the method comprises the following specific steps:
step B1: converting the collected continuous multi-frame pavement images into gray level images;
step B2: the gray level of the gray level image of two continuous frames of road surface images is subjected to difference processing to obtain the gray level difference value D of the two frames of road surface imagesgreyAnd comparing the road condition with a preset difference threshold value, and judging the road condition according to the following formula:
step B3: multiplying the snow depth correction coefficient corresponding to the road condition with the road snow depth measurement value to obtain a correction value of the road snow depth measurement value;
the value range of the correction coefficient is as follows:
when the road is only accumulated with snow, the snow depth correction coefficient is 1.0;
when water is accumulated on the road, the snow depth correction coefficient is 0.6-0.7;
when the road is frozen, the snow depth correction coefficient is 0.7-0.8.
5. The method according to any one of claims 2 to 4, wherein the weight and the threshold of the BP neural network in the BP neural network-based residual capacity prediction model are obtained by performing optimization by using a quantum particle swarm algorithm with adaptive weight as follows:
step D1: taking the position vector of each quantum particle individual in the quantum particle swarm as the weight and the threshold of the BP neural network, and initializing the position vector parameters of the quantum particle swarm individual into random numbers of [ -1,1 ];
the value range of the number of the quantum particle swarm is [25,70], the value range of the number of the particles of the quantum particle swarm is [5,50], the value range of the maximum iteration number is [400,1000], the value range of the iteration number for constructing the elite swarm is [60,180], the value range of the premature convergence judgment threshold is [0.01,0.45], and the value range of the worst particle variation proportion% of the swarm is [ 2%, 7%);
step D2: setting a fitness function, and determining an initial optimal quantum particle individual position vector and iteration times t, wherein t is 1;
substituting the weight value and the threshold value corresponding to the quantum particle individual position vector into a face recognition model based on a BP (back propagation) neural network, calculating the current residual capacity by using a residual capacity prediction model based on the BP neural network determined by the quantum particle individual position vector, and taking the inverse of the mean square error of the predicted residual capacity and the actual value as a second fitness function f2 (x);
step D3: calculating the group fitness variance of each quantum particle swarm, and performing premature convergence judgment;
if the group fitness variance of the quantum particle swarm is smaller than the premature convergence judgment threshold gamma, performing variation on% of the worst fitness particles and the extreme population particles in the quantum particle swarm, and taking the particles with the best current fitness as the global optimal quantum particle individuals;
step D4: judging whether to establish an elite population;
when the iteration times are larger than the iteration times of the elite population, extracting extreme values of all the populations through information sharing among the populations to establish the elite population, and turning to the step D8, otherwise, turning to the step D5;
step D5: updating parameters of each population of particles;
step D6: recalculating and comparing the fitness value of each particle, and updating the individual extreme value if the fitness value is superior to the current individual extreme value; comparing the global extreme value particles, if the particle fitness value is superior to the current group extreme value, updating the global extreme value particles, enabling t to be t +1, and turning to the step D3;
step D7: the elite population continues to evolve;
step D8: and D3, judging whether the maximum iteration times are met, if so, exiting, otherwise, making t equal to t +1, switching to the step D3 until a global optimal value is found, and outputting the weight and the threshold of the BP neural network.
6. The method of claim 2, wherein the angle between the body direction and the horizontal direction is sensed as a road grade measurement using a MEMS gyroscope in an inertial navigation system onboard the unmanned vehicle.
7. The method of claim 2, wherein the battery temperature of the unmanned vehicle is collected in real time by 16 non-contact temperature sensors uniformly distributed on the surface of the battery, and a three-dimensional temperature distribution data map of the surface of the battery is fitted by interpolation processing, and the maximum value is taken as the battery temperature.
8. A multi-source fusion prediction system for a power supply of an unmanned vehicle is characterized by comprising a sensing layer, a transmission layer, a first processing layer and a second processing layer;
the sensing layer is used for sending the data information acquired by the sensing equipment to the transmission layer;
the sensing equipment comprises a laser sensor, an inclination angle sensor, a high-definition camera, a vehicle-mounted gyroscope and a non-contact temperature sensor which are arranged on the unmanned vehicle; the laser sensor and the inclination angle sensor are arranged at the middle points of wheel track lines on two sides of the bottom of the unmanned vehicle body, and the high-definition camera is arranged in the middle of the front end of the unmanned vehicle;
the transmission layer forwards the data transmitted by the sensing layer to the first processing layer and the second processing layer;
the first processing layer is used for processing the data information in real time and sending the data information to the transmission layer;
the first processing layer comprises a data information calculation module, an image processing module and a data fusion processing module, wherein the data information calculation module carries out comprehensive calculation processing on information collected by a laser sensor, an inclination angle sensor, a vehicle-mounted MEMS gyroscope and a temperature sensor in the sensing layer to obtain an effective accumulated snow depth measurement value, and calculates an optimal road gradient and an optimal battery temperature; the image processing module extracts snow contour features in an image acquired by the high-definition camera and performs feature recognition to form a snow contour envelope line to obtain an effective snow depth measurement value; the data fusion processing module performs weighted fusion on the effective snow depth measurement values obtained by the two measurement methods to obtain an optimal effective snow depth measurement value;
the second processing layer is used for predicting the battery electric quantity of the data processed by the first processing layer in real time;
the second processing layer comprises a wavelet neural network-based battery power consumption rate fitting network of the unmanned vehicle and a BP neural network-based unmanned vehicle residual electric quantity prediction network, the effective accumulated snow depth, the road gradient and the battery temperature after data fusion sent by the transmission layer are used as model input values, the battery power consumption rate corresponding to each acquisition unit is used as a model output value, data information acquired by a plurality of nodes is used as a training sample, the battery power consumption rate output by the previous layer of wavelet neural network-based unmanned vehicle battery power consumption rate fitting network is used as a next layer of BP neural network-based input neuron, and an intelligent prediction model of the battery electric quantity of the unmanned vehicle is constructed; and then, the intelligent prediction model of the battery power of the unmanned vehicle is transmitted to the second processing layer through the transmission layer after the data acquired by the sensing layer in real time through the first processing layer is processed, so that the real-time prediction of the battery power of the vehicle is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810372830.5A CN108572648B (en) | 2018-04-24 | 2018-04-24 | Unmanned vehicle power supply multi-source fusion prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810372830.5A CN108572648B (en) | 2018-04-24 | 2018-04-24 | Unmanned vehicle power supply multi-source fusion prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108572648A CN108572648A (en) | 2018-09-25 |
| CN108572648B true CN108572648B (en) | 2020-08-25 |
Family
ID=63574433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810372830.5A Active CN108572648B (en) | 2018-04-24 | 2018-04-24 | Unmanned vehicle power supply multi-source fusion prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108572648B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109459037A (en) * | 2018-12-29 | 2019-03-12 | 南京师范大学镇江创新发展研究院 | A kind of environment information acquisition method and system based on SLAM intelligence carrier |
| CN110395286B (en) * | 2019-08-02 | 2020-08-07 | 中南大学 | Method and system for monitoring air quality and regulating ventilation in train |
| CN110333325B (en) * | 2019-08-02 | 2021-09-17 | 中南大学 | Train operation protection method and system in atmosphere pollution environment |
| CN110648343B (en) * | 2019-09-05 | 2022-09-23 | 电子科技大学 | Image edge detection method based on six-order spline scale function |
| CN110667434A (en) * | 2019-09-11 | 2020-01-10 | 南京航空航天大学 | Working condition-adaptive pure electric vehicle driving mileage estimation method and system |
| CN112326684B (en) * | 2020-10-21 | 2022-05-24 | 阳光电源股份有限公司 | Photovoltaic module dust accumulation detection method, device, equipment and storage medium |
| CN112734097B (en) * | 2020-12-31 | 2023-09-05 | 中南大学 | Unmanned train energy consumption prediction method, system and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004027704A1 (en) * | 2002-09-20 | 2004-04-01 | Ecole Polytechnique Federale De Lausanne (Epfl) | Spiking neural network device |
| CN102156918A (en) * | 2011-04-19 | 2011-08-17 | 中国科学院深圳先进技术研究院 | Smart grid broadcast system and method |
| CN102458946A (en) * | 2009-06-10 | 2012-05-16 | 丰田自动车株式会社 | Power supply system for electric vehicle and method for controlling same |
| CN104616121A (en) * | 2015-02-28 | 2015-05-13 | 南京飞腾电子科技有限公司 | Regional energy comprehensive coordination management and control system |
| CN105512623A (en) * | 2015-12-02 | 2016-04-20 | 吉林大学 | Foggy-day driving visual enhancement and visibility early warning system and method based on multiple sensors |
| CN105719030A (en) * | 2016-03-29 | 2016-06-29 | 武汉大学 | Method for electric vehicle load prediction based on efficiency maximization principle |
| CN106779069A (en) * | 2016-12-08 | 2017-05-31 | 国家电网公司 | A kind of abnormal electricity consumption detection method based on neutral net |
| CN105162151B (en) * | 2015-10-22 | 2017-06-16 | 国家电网公司 | A kind of grid-connected real-time control method of intelligent energy-storage system based on artificial fish-swarm algorithm |
| CN107272705A (en) * | 2017-07-31 | 2017-10-20 | 中南大学 | A kind of multiple neural network controlling planning method of robot path under intelligent environment |
| CN107688343A (en) * | 2017-08-01 | 2018-02-13 | 北京理工大学 | A kind of energy control method of motor vehicle driven by mixed power |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6690134B1 (en) * | 2001-01-24 | 2004-02-10 | Irobot Corporation | Method and system for robot localization and confinement |
-
2018
- 2018-04-24 CN CN201810372830.5A patent/CN108572648B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004027704A1 (en) * | 2002-09-20 | 2004-04-01 | Ecole Polytechnique Federale De Lausanne (Epfl) | Spiking neural network device |
| CN102458946A (en) * | 2009-06-10 | 2012-05-16 | 丰田自动车株式会社 | Power supply system for electric vehicle and method for controlling same |
| CN102156918A (en) * | 2011-04-19 | 2011-08-17 | 中国科学院深圳先进技术研究院 | Smart grid broadcast system and method |
| CN104616121A (en) * | 2015-02-28 | 2015-05-13 | 南京飞腾电子科技有限公司 | Regional energy comprehensive coordination management and control system |
| CN105162151B (en) * | 2015-10-22 | 2017-06-16 | 国家电网公司 | A kind of grid-connected real-time control method of intelligent energy-storage system based on artificial fish-swarm algorithm |
| CN105512623A (en) * | 2015-12-02 | 2016-04-20 | 吉林大学 | Foggy-day driving visual enhancement and visibility early warning system and method based on multiple sensors |
| CN105719030A (en) * | 2016-03-29 | 2016-06-29 | 武汉大学 | Method for electric vehicle load prediction based on efficiency maximization principle |
| CN106779069A (en) * | 2016-12-08 | 2017-05-31 | 国家电网公司 | A kind of abnormal electricity consumption detection method based on neutral net |
| CN107272705A (en) * | 2017-07-31 | 2017-10-20 | 中南大学 | A kind of multiple neural network controlling planning method of robot path under intelligent environment |
| CN107688343A (en) * | 2017-08-01 | 2018-02-13 | 北京理工大学 | A kind of energy control method of motor vehicle driven by mixed power |
Non-Patent Citations (1)
| Title |
|---|
| 《基于季节调整与神经网络融合算法的售电量预测》;陈耀红等;《技术应用》;20180131;第30-31页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108572648A (en) | 2018-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108572648B (en) | Unmanned vehicle power supply multi-source fusion prediction method and system | |
| CN112561146B (en) | Large-scale real-time traffic flow prediction method based on fuzzy logic and depth LSTM | |
| CN108508372B (en) | A kind of calculating of unmanned electricity and method for early warning and system based on environmental visual fusion | |
| CN106156748B (en) | Traffic scene participant's recognition methods based on vehicle-mounted binocular camera | |
| CN108573545B (en) | A kind of ice and snow environment automatic driving vehicle power source model prediction technique and system | |
| CN112698302B (en) | Sensor fusion target detection method under bumpy road condition | |
| CN108621844B (en) | Electric quantity prediction method and early warning system for unmanned vehicle on rainstorm road | |
| CN107397658B (en) | Multi-scale full-convolution network and visual blind guiding method and device | |
| CN112001958B (en) | Virtual point cloud three-dimensional target detection method based on supervised monocular depth estimation | |
| CN107145846A (en) | A kind of insulator recognition methods based on deep learning | |
| CN108876799B (en) | Real-time step detection method based on binocular camera | |
| CN107750364A (en) | Detected using the road vertically profiling of stable coordinate system | |
| CN109596078A (en) | Multi-information fusion spectrum of road surface roughness real-time testing system and test method | |
| CN108549037B (en) | A kind of automatic driving vehicle power supply prediction technique and system based on parallel neural network | |
| CN110378416A (en) | A kind of coefficient of road adhesion estimation method of view-based access control model | |
| CN104899866A (en) | Intelligent infrared small target detection method | |
| CN113516108B (en) | Construction site dust suppression data matching processing method based on data identification | |
| CN107340298A (en) | Balance car system monitoring method based on camera pavement detection | |
| CN110388926A (en) | A kind of indoor orientation method based on mobile phone earth magnetism and scene image | |
| CN106096246B (en) | Aerosol optical depth method of estimation based on PM2.5 and PM10 | |
| CN111123953B (en) | Particle-based mobile robot group under artificial intelligence big data and control method thereof | |
| CN113538357B (en) | Shadow interference resistant road surface state online detection method | |
| CN108656992B (en) | Intelligent prediction method and device for unmanned vehicle power supply in extreme rainstorm environment | |
| CN113255553A (en) | Sustainable learning method based on vibration information supervision | |
| CN104240268B (en) | A kind of pedestrian tracting method based on manifold learning and rarefaction representation |
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 |