CN112149888A - Real-time travel time prediction method for unmanned mine card for strip mine - Google Patents
Real-time travel time prediction method for unmanned mine card for strip mine Download PDFInfo
- Publication number
- CN112149888A CN112149888A CN202010934034.3A CN202010934034A CN112149888A CN 112149888 A CN112149888 A CN 112149888A CN 202010934034 A CN202010934034 A CN 202010934034A CN 112149888 A CN112149888 A CN 112149888A
- Authority
- CN
- China
- Prior art keywords
- time
- travel time
- real
- prediction
- mine
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000005065 mining Methods 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000012795 verification Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 239000000428 dust Substances 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention belongs to the field of integrated traffic prediction, and relates to a method for predicting real-time travel time of an unmanned mine card for strip mines, which comprises the following steps: establishing a mine road network graph; selecting a prediction factor of the real-time travel time of the unmanned mine card; acquiring a complete prediction factor and acquiring the travel time of the unmanned mine card on each road section; constructing a time sequence data set and dividing the time sequence data set into a training set, a verification set and a test set; training and verifying the initial neural network by utilizing a training set and a verifying set, establishing a real-time travel time prediction model, and verifying the effectiveness of the real-time travel time prediction model by utilizing a testing set. The invention can predict the driving time of all vehicles in each road section in the mining area, and for the condition that two empty and heavy vehicles run to the same road section at the same time, the principle of avoiding heavy vehicles by the empty vehicles is followed, so that the empty vehicles wait and the heavy vehicles pass, thereby optimizing the vehicle allocation in the mining area.
Description
Technical Field
The invention belongs to the field of integrated traffic prediction, and relates to a real-time travel time prediction method for an unmanned mine card for strip mines.
Background
In an open pit environment, when a vehicle with a mine car can let or pass through a crossing on a one-way road, the empty car can be controlled to stop in an artificial way in an open pit area generally according to the principle that the empty car avoids the heavy car in consideration of potential safety hazards and economic benefit loss of the heavy car stopping and restarting. The unmanned mine truck vehicle also follows the principle that empty vehicles avoid heavy vehicles, but the unmanned mine truck vehicle lacks manual control, needs to autonomously decide an avoidance strategy, and realizes automatic control. The running time of the vehicle on the path is an important basis for controlling the mine vehicle, and the real-time performance and reliability of the control decision can be directly influenced by the accuracy of the time prediction. Therefore, research into real-time travel time prediction for unmanned mining vehicles is particularly important.
The current travel time prediction methods are mainly divided into two categories: one is the traditional statistical methods such as linear regression, autoregressive moving average, etc. (for example, chinese patent CN201610940816.1), but these methods cannot predict the travel time with nonlinear characteristics well; another class is machine learning methods such as fuzzy inference systems, support vector machines, and neural networks. The fuzzy inference system (Chinese patent CN201410149283.6) lacks self-learning ability, and the support vector machine (Chinese patent CN201710507146.9) can not process large-scale data well. At present, the neural network has better performance in the aspects of nonlinearity, local minimum value, large-scale data processing and the like, and has wide application. However, most of the real-time travel time prediction methods based on the neural network are directed at a single road, and once the road changes, the training needs to be carried out again even if the road conditions are basically similar. Furthermore, many road conditions within an open pit mine scenario are highly similar and the run time of the mine card exhibits randomness even for the same road segment.
Disclosure of Invention
Aiming at the following technical problems existing at present: the method has the advantages that the method is less in estimation research of the travel time of unmanned vehicles in a mine area in a road network; the current travel time prediction is mostly single-factor prediction, and the travel time change is large due to factors such as empty vehicles, heavy vehicles and the like when the automatic driving vehicles in the mining area are in a specific path, so that a large error exists, and the real-time performance is not realized; the current travel time prediction method carries out prediction aiming at a single road section by multi-prediction. For a plurality of road sections to be predicted, data of each road section is needed, and for a plurality of road sections in the same scene, the data utilization is insufficient, and the training results are not universal.
The invention provides a method for predicting real-time travel time of an unmanned mine card for strip mines, which comprises the following steps:
s1: obtaining a mining area map, dividing the whole mining area environment according to the characteristics of the road sections of the mining area, and establishing a mining area road network map;
s2: selecting prediction factors of real-time travel time of the unmanned mine card, wherein the prediction factors comprise a road surface type, a road section gradient, a road section length, a sensing condition, a vehicle type, a vehicle load type and the like;
s3: acquiring the real mine area position, the vehicle type, the vehicle load type and the sensing condition of the unmanned mine card, mapping the real mine area position into the mine area road network map established in the step S1 according to the mine area map, acquiring the road surface type, the road gradient and the road length of the road section driven by the unmanned mine card, and acquiring a complete prediction factor; meanwhile, the travel time of the unmanned mine card on each road section is collected;
s4: taking the prediction factor obtained in the step S3 and the travel time of the unmanned mine card on each road section as original historical data, constructing a time sequence data set, and dividing the time sequence data set into a training set, a verification set and a test set;
s5: training and verifying the initial neural network by utilizing a training set and a verification set, establishing a real-time travel time prediction model, inputting a test set into the real-time travel time prediction model, and performing anti-standardization processing to obtain a corresponding travel time prediction value so as to verify the effectiveness of the real-time travel time prediction model;
s6: and S3, acquiring a prediction factor of the real-time travel time of the unmanned mine card to be predicted, inputting the prediction factor into the real-time travel time prediction model established in the S5, and outputting the predicted value of the real-time travel time of the unmanned mine card.
Further, in step S1, the characteristics of the mine section include a gradient, a step and an intersection.
Further, in step S2, the road surface types include three types, namely a trunk line, a half trunk line and a moving line; the vehicle load types comprise empty vehicles and heavy vehicles; the value range of the road section gradient is-8% to + 8%, wherein-represents a downhill slope, and + represents an uphill slope; the sensing conditions comprise day, night, dust emission and illumination conditions.
Further, in step S4, the original history data is preprocessed, and the specific process is as follows: taking every 5min as a time interval, calculating the average value of the travel time of each time interval as the travel time of the time interval, and then mapping the travel time of each time interval to be between [0,1] by adopting a minimum and maximum standardization technology.
Further, in step S5, the training set and the verification set are input into the initial neural network, and the error is calculated using the loss function:
wherein, FlossIs a loss function; n is the number of samples in the training set; y isiThe actual value of the travel time is taken as the actual value; y isi' is a travel time prediction output value;
the specific training process is as follows:
setting the global learning rate as eta; the decay rates of the first order moment estimate and the second order moment estimate are respectively beta1And beta2(ii) a Weight matrix W of initialization time step0(ii) a Initializing a first moment of momentum m0And second moment of momentum v0All the time is 0, the initialization time step t is 0, and then the following steps are executed in a circulating mode until the stop requirement is met;
s51: calculating the gradient:
wherein, gtIs the gradient value of the t time step, J is the cost function, Wt-1A weight matrix representing the t-1 time step;
s52: updating the time step t;
s53: updating the first order biased estimate and the second order biased estimate:
mt＝β1mt-1+(1-β1)gt
vt＝β1vt-1+(1-β1)gt
wherein m istAnd vtRespectively a first moment and a second moment of momentum at the t-th time step;
s54: and (3) correcting the deviation of the first-order moment and the second-order moment:
wherein m ist' represents the second moment of momentum after correction; v. oft' represents the second moment of momentum after correction;
and
respectively representing the decay rates of the first and second moment estimates at the tth time step;
s55: calculating parameter update amount
Wherein, Δ w represents a weight increment, which is a deviation term constant;
s56: updating parameters:
Wt＝Wt-1+Δw。
the invention has the beneficial effects that:
1) the neural network is adopted to predict the journey time of the open-air automatic driving mine truck, factors influencing the automatic driving mine truck are screened as prediction factors while the scene is divided according to the mine truck environment, and the neural network has good adaptability to the mine area environment;
2) aiming at the problems that the neural network method time prediction is not universal and real-time, the method adopts the multi-road-section multi-travel time factor input in a single scene and uniformly trains, so that the training result is more universal and real-time, and the data dependence is reduced.
Drawings
FIG. 1 is a flow chart of a method for predicting real-time travel time of an unmanned mine card according to an embodiment of the invention;
FIG. 2 is a raw line drawing of a mine site according to an embodiment of the present invention;
fig. 3 is an abstract road network diagram of a mining area according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, the method for predicting the real-time travel time of the unmanned mine card for the open pit mine in the embodiment includes the following steps:
s1: the method comprises the steps of obtaining a mining area map by adopting positioning technologies such as a GPS (global positioning system) or an SLAM (SLAM), setting nodes according to the special characteristics of mining area road sections such as gradients, steps and intersections, dividing the whole open-air mining area environment (shown in figure 2), and establishing a mining area road network map (shown in figure 3), wherein letters in the map respectively represent the nodes on the mining area road network map. In the present embodiment, for example, the BG link in fig. 2 is originally the entire link, but the BC link and the CG link have different slopes, and therefore the BG link is divided into two links.
S2: selecting n main factors influencing the real-time travel time of the unmanned ore card as prediction factors of the travel time of the unmanned ore card of the strip mine: x is the number of1,x2,…,xn。
x1Represents a road surface type, including three types of a main line, a half main line and a travel line, and therefore, x13 values can be taken, and l, 2 and 3 are respectively used for representing three types of a trunk line, a half trunk line and a mobile line; x is the number of2Representing a vehicle type; x is the number of3Representing the load type of the vehicle, including two types of empty vehicle and heavy vehicle; x is the number of4Representing the slope of the road section (-8% to + 8%), and the variables may be [ -8, + 8%]A median value ("+" indicates an uphill slope, "-" indicates a downhill slope); x is the number of5The sensing conditions (day, night, dust emission, illumination conditions and the like) are represented, and the factors are selected as prediction factors, so that the influence on the driving time caused by different automation degrees due to different sensor reliability under different sensing conditions of the automatic driving vehicle is mainly considered; x is the number of6Indicating the length of the link.
S3: the position of the unmanned mine vehicle is positioned in real time through positioning technologies such as a GPS (global positioning system) or a SLAM (SLAM), and the real mine position is mapped into the obtained mine road network map according to the mine map, so that travel time prediction factors such as road surface type, road grade, road length and the like of a running road section are obtained; meanwhile, a complete prediction factor is obtained according to the type of the vehicle, the type of the load of the vehicle, the sensing condition and the like. And according to the positioning information, the travel time of the unmanned mine card vehicle running on each road section is collected.
S4: and using the obtained complete prediction factor and the travel time of the unmanned mine card on each road section as original historical data, preprocessing the original historical data, constructing a time sequence data set by using the preprocessed original historical data, and dividing the time sequence data set into a training set, a verification set and a test set.
Since the running environment of the strip mine is simpler than that of a city and the running time of each road section changes greatly, in the embodiment, every 5min is taken as a time interval, the average value of the travel time of each time interval is calculated to be taken as the travel time x' required by the time interval, and then the travel time of each time interval is mapped to the range between [0 and 1] by adopting the minimum and maximum standardization technology.
S5: constructing an initial neural network structure, training and verifying the initial neural network by using a training set and a verification set, and establishing a real-time travel time prediction model; and inputting the test set into the real-time travel time prediction model, and performing anti-standardization processing to obtain a corresponding travel time prediction value so as to verify the effectiveness of the real-time travel time prediction model.
In this embodiment, when the initial neural network structure is constructed, the input variables are set to 6 (i.e., the 6 prediction factors selected in step S2), the output variables are 1 (i.e., the real-time travel time of the unmanned mine card), the number of the intermediate hidden layers can be arbitrarily determined from 4 to 20, the number of the selected hidden layer nodes is not yet determined, and multiple hidden layers can be selected. In establishing the real-time travel time prediction model of the present invention, a large number of experiments are often required, and adjustments are made continuously until the most suitable number of nodes (i.e., the error is minimized) is found.
After the initial neural network is constructed, connection weights among layers and bias of each neuron are initialized randomly, and appropriate activation functions and loss functions are selected.
The present embodiment uses the mean square error as a loss function:
in the formula, FlossIs a loss function; n is the number of samples in the training set; y isiThe actual value of the travel time is taken as the actual value; y isi' is a travel time prediction output value.
Inputting the training set and the verification set into an initial neural network, wherein the input is x (x)1,x2,…,xnX') and calculates the error using a loss function. The present embodiment uses Adam optimization methods to optimize network parameters. The training algorithm is as follows:
firstly, setting the global learning rate as eta and the default value as 0.9; the decay rates of the first and second order moment estimates, respectively, are beta1And beta2Generally, 0.9 and 0.999 are respectively taken; initializing weight matrix W0Initializing a first moment of momentum m0And second moment of momentum v0Both are 0 and the initialization time step t is 0, then the following steps are executed in a loop until the stop requirement is met.
S51: calculating the gradient:
wherein, gtIs the gradient value of the t time step, J is the cost function, Wt-1A weight matrix representing the t-1 time step;
s52: updating the time step t;
s53: updating the first order biased estimate and the second order biased estimate:
mt＝β1mt-1+(1-β1)gt
vt＝β1vt-1+(1-β1)gt
wherein m istAnd vtRespectively a first moment and a second moment of momentum at the t-th time step;
s54: and (3) correcting the deviation of the first-order moment and the second-order moment:
wherein m ist' represents the first moment of momentum after correction; v. oft' represents the second moment of momentum after correction;
and
respectively representing the decay rates of the first moment estimate and the second moment estimate at the tth time step;
s55: calculating parameter update amount
Wherein, Δ w represents a weight increment, which is a deviation term constant;
s56: updating parameters:
Wt＝Wt-1+Δw。
s6: and S3, acquiring a prediction factor of the real-time travel time of the unmanned mine card to be predicted, inputting the prediction factor into the real-time travel time prediction model established in the S5, and outputting the predicted value of the real-time travel time of the unmanned mine card.
In conclusion, the invention can predict the driving time of all vehicles in the mining area in each road section, and for the condition that two empty and heavy vehicles run to the same road section at the same time, the principle of empty vehicle avoiding heavy vehicle is followed, so that the empty vehicles wait and the heavy vehicles pass, thereby optimizing the vehicle allocation in the mining area.
It will be apparent to those skilled in the art that various modifications and improvements can be made to the embodiments of the present invention without departing from the inventive concept thereof, and these modifications and improvements are intended to be within the scope of the invention.
Claims (5)
1. A real-time travel time prediction method for an unmanned mine card for an open-pit mine is characterized by comprising the following steps:
s1: obtaining a mining area map, dividing the whole mining area environment according to the characteristics of the road sections of the mining area, and establishing a mining area road network map;
s2: selecting prediction factors of real-time travel time of the unmanned mine card, wherein the prediction factors comprise road surface types, road section gradients, road section lengths, sensing conditions, vehicle types, vehicle load types and driving time periods;
s3: acquiring the real mine area position, the vehicle type, the vehicle load type, the sensing condition and the driving time period of the unmanned mine card, mapping the real mine area position into the mine area road network map established in the step S1 according to the mine area map, acquiring the road surface type, the road slope and the road length of the road section driven by the unmanned mine card, and acquiring a complete prediction factor; meanwhile, the travel time of the unmanned mine card on each road section is collected;
s4: taking the prediction factor obtained in the step S3 and the travel time of the unmanned mine card on each road section as original historical data, constructing a time sequence data set, and dividing the time sequence data set into a training set, a verification set and a test set;
s5: training and verifying the initial neural network by utilizing a training set and a verification set, and establishing a real-time travel time prediction model; inputting the test set into a real-time travel time prediction model, and performing anti-standardization processing to obtain a corresponding travel time prediction value so as to verify the effectiveness of the real-time travel time prediction model;
s6: and S3, acquiring a prediction factor of the real-time travel time of the unmanned mine card to be predicted, inputting the prediction factor into the real-time travel time prediction model established in the S5, and outputting the predicted value of the real-time travel time of the unmanned mine card.
2. The method of claim 1, wherein in step S1, the mine section features include grade, step, and intersection.
3. The method according to claim 1, wherein in step S2, the road surface types include three types of trunk lines, half trunk lines and moving lines; the vehicle load types comprise empty vehicles and heavy vehicles; the value range of the road section gradient is-8% to + 8%, wherein-represents a downhill slope, and + represents an uphill slope; the sensing conditions comprise day, night, dust, lighting conditions and the like.
4. The method according to claim 1, wherein in step S4, the raw history data is preprocessed by the following specific processes: taking every 5min as a time interval, calculating the average value of the travel time of each time interval as the travel time of the time interval, and then mapping the travel time of each time interval to be between [0,1] by adopting a minimum and maximum standardization technology.
5. The method according to claim 1, wherein in step S5, the training set and the validation set are input into an initial neural network, and the error is calculated using a loss function:
wherein, FlossIs a loss function; n is the number of samples in the training set; y isiThe actual value of the travel time is taken as the actual value; y isi' is a travel time prediction output value;
the specific training process is as follows:
setting the global learning rate as eta; the decay rates of the first order moment estimate and the second order moment estimate are respectively beta1And beta2(ii) a Initializing weight matrix W0(ii) a Initializing a first moment of momentum m0And second moment of momentum v0Are all 0; initializing the time step t to be 0, and then circularly executing the following steps until the stop requirement is met;
s51: calculating the gradient:
wherein, gtIs the gradient value of the t time step, J is the cost function, Wt-1A weight matrix representing the t-1 time step;
s52: updating the time step t;
s53: updating the first order biased estimate and the second order biased estimate:
mt＝β1mt-1+(1-β1)gt
vt＝β2vt-1+(1-β2)gt
wherein m istAnd vtRespectively a first moment and a second moment of momentum at the t-th time step;
s54: and (3) correcting the deviation of the first-order moment and the second-order moment:
wherein m ist' represents the first moment of momentum after correction; v. oft' represents the second moment of momentum after correction;
and
respectively representing the decay rates of the first moment estimate and the second moment estimate at the tth time step;
s55: calculating parameter update amount
Wherein, Δ w represents a weight increment, which is a deviation term constant;
s56: updating parameters:
Wt＝Wt-1+Δw。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010934034.3A CN112149888A (en) | 2020-09-08 | 2020-09-08 | Real-time travel time prediction method for unmanned mine card for strip mine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010934034.3A CN112149888A (en) | 2020-09-08 | 2020-09-08 | Real-time travel time prediction method for unmanned mine card for strip mine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112149888A true CN112149888A (en) | 2020-12-29 |
Family
ID=73889417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010934034.3A Pending CN112149888A (en) | 2020-09-08 | 2020-09-08 | Real-time travel time prediction method for unmanned mine card for strip mine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149888A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734111A (en) * | 2021-01-11 | 2021-04-30 | 上海振华重工(集团)股份有限公司 | AGV dynamic time estimation method for horizontal transportation task |
| CN113959453A (en) * | 2021-09-28 | 2022-01-21 | 青岛慧拓智能机器有限公司 | Mining area road network map generation method, device, equipment and storage medium |
| WO2023155012A1 (en) * | 2022-02-17 | 2023-08-24 | Teck Resources Limited | Truck allocation system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170243121A1 (en) * | 2016-02-22 | 2017-08-24 | Institute For Information Industry | Traffic forecasting system, traffic forecasting method and traffic model establishing method |
| CN110309957A (en) * | 2019-06-17 | 2019-10-08 | 北京航空航天大学 | It is a kind of towards in the car-haul time pre-judging method with the unmanned transportation system of mine car |
| CN110486017A (en) * | 2019-08-30 | 2019-11-22 | 西安建筑科技大学 | A kind of automatic driving vehicle energy consumption power-economizing method based on Open pit Area path |
| CN111601277A (en) * | 2020-04-26 | 2020-08-28 | 北京踏歌智行科技有限公司 | On-line simulation system for unmanned mining operation |
-
2020
- 2020-09-08 CN CN202010934034.3A patent/CN112149888A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170243121A1 (en) * | 2016-02-22 | 2017-08-24 | Institute For Information Industry | Traffic forecasting system, traffic forecasting method and traffic model establishing method |
| CN110309957A (en) * | 2019-06-17 | 2019-10-08 | 北京航空航天大学 | It is a kind of towards in the car-haul time pre-judging method with the unmanned transportation system of mine car |
| CN110486017A (en) * | 2019-08-30 | 2019-11-22 | 西安建筑科技大学 | A kind of automatic driving vehicle energy consumption power-economizing method based on Open pit Area path |
| CN111601277A (en) * | 2020-04-26 | 2020-08-28 | 北京踏歌智行科技有限公司 | On-line simulation system for unmanned mining operation |
Non-Patent Citations (1)
| Title |
|---|
| 李敏 等: "差分隐私保护下的Adam优化算法研究", 计算机应用与软件, vol. 37, no. 6, pages 255 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734111A (en) * | 2021-01-11 | 2021-04-30 | 上海振华重工(集团)股份有限公司 | AGV dynamic time estimation method for horizontal transportation task |
| CN112734111B (en) * | 2021-01-11 | 2023-12-22 | 上海振华重工(集团)股份有限公司 | Horizontal transport task AGV dynamic time prediction method |
| CN113959453A (en) * | 2021-09-28 | 2022-01-21 | 青岛慧拓智能机器有限公司 | Mining area road network map generation method, device, equipment and storage medium |
| WO2023155012A1 (en) * | 2022-02-17 | 2023-08-24 | Teck Resources Limited | Truck allocation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112149888A (en) | Real-time travel time prediction method for unmanned mine card for strip mine | |
| US10936940B2 (en) | Arrangement and method for predicting road friction within a road network | |
| Jin et al. | A group-based traffic signal control with adaptive learning ability | |
| CN103177570B (en) | Method for predicting traffic jam indexes for rush hours in morning and evening | |
| CN101909965B (en) | System and method for optimizing power system performance in presence of changing optimization parameters | |
| CN109887284B (en) | Smart city traffic signal control recommendation method, system and device | |
| CN106022549A (en) | Short term load predication method based on neural network and thinking evolutionary search | |
| CN111860989B (en) | LSTM neural network short-time traffic flow prediction method based on ant colony optimization | |
| CN105761488A (en) | Real-time limit learning machine short-time traffic flow prediction method based on fusion | |
| CN114287022A (en) | Multi-step traffic prediction | |
| CN113704956A (en) | Urban road online microscopic simulation method and system based on digital twin technology | |
| CN113219933B (en) | Strip mine unmanned truck dispatching system and method based on digital twin prediction | |
| KR102254765B1 (en) | Device and method of prediction traffic data using deep learning model | |
| US20200379417A1 (en) | Techniques for using machine learning for control and predictive maintenance of buildings | |
| CN114360266B (en) | Intersection reinforcement learning signal control method for sensing detection state of internet connected vehicle | |
| Tettamanti et al. | Model predictive control in urban traffic network management | |
| CN113744527A (en) | Intelligent targeting dredging method for highway confluence area | |
| CN113781811B (en) | Mining area intersection vehicle passing decision making system and method | |
| CN109858681B (en) | Traffic short-time passenger flow prediction method and related device based on IC card | |
| Aslani et al. | Continuous residual reinforcement learning for traffic signal control optimization | |
| CN110490365B (en) | Method for predicting network car booking order quantity based on multi-source data fusion | |
| Li et al. | A deep adaptive traffic signal controller with long-term planning horizon and spatial-temporal state definition under dynamic traffic fluctuations | |
| CN111507499B (en) | Method, device and system for constructing model for prediction and testing method | |
| CN113628455B (en) | Intersection signal optimization control method considering number of people in vehicle under Internet of vehicles environment | |
| CN112734111A (en) | AGV dynamic time estimation method for horizontal transportation task |
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 |