CN115293055A - Method and device for training oil consumption prediction model of mining area vehicle and electronic equipment - Google Patents
Method and device for training oil consumption prediction model of mining area vehicle and electronic equipment Download PDFInfo
- Publication number
- CN115293055A CN115293055A CN202211220194.7A CN202211220194A CN115293055A CN 115293055 A CN115293055 A CN 115293055A CN 202211220194 A CN202211220194 A CN 202211220194A CN 115293055 A CN115293055 A CN 115293055A
- Authority
- CN
- China
- Prior art keywords
- oil consumption
- time period
- historical
- data
- target time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000005065 mining Methods 0.000 title claims abstract description 45
- 239000000446 fuel Substances 0.000 claims abstract description 96
- 230000006870 function Effects 0.000 claims description 33
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 230000000873 masking effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002354 daily effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The disclosure relates to a method and a device for training a fuel consumption prediction model of a mining vehicle and electronic equipment, and relates to the technical field of engineering machinery. The training method of the oil consumption prediction model of the mining area vehicle comprises the following steps: acquiring historical time sequence data, task data of a target time period, a true value of oil consumption of the historical time sequence and a true value of the oil consumption of the target time period; generating a predicted value of the oil consumption of the historical time sequence by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data; generating a predicted value of the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period; and jointly training the oil consumption prediction model according to the actual value of the historical time sequence oil consumption, the predicted value of the historical time sequence oil consumption, the actual value of the oil consumption in the target period and the predicted value of the oil consumption in the target period. According to the method and the device, the accuracy of the oil consumption prediction of the vehicles in the mining area is improved.
Description
Technical Field
The disclosure relates to the technical field of engineering machinery, in particular to a method and a device for training a fuel consumption prediction model of a mine vehicle.
Background
In mining operations, oil consumption is closely related to the cost and profitability of the mine. The large amount of work in the mine leads to large load and oil consumption of the vehicle, and the large oil consumption. If the oil reserves are not replenished in time, the vehicle transport task may be affected, affecting the production in the mine.
Operating data of mine vehicles, such as distance, actual load of the vehicle, may affect fuel consumption. In the related art, the fuel consumption of a vehicle is predicted by manually marking the operation data of the vehicle in a mining area to generate a label.
Disclosure of Invention
According to a first aspect of the present disclosure, a method for training a fuel consumption prediction model of a mine vehicle is provided, including: acquiring historical time sequence data, task data of a target time period, a real value of historical time sequence oil consumption and a real value of oil consumption of the target time period, wherein the historical time sequence data comprises a sequence of historical data of a plurality of continuous time periods before the target time period, and the real value of the historical time sequence oil consumption comprises a sequence of real values of oil consumption of a vehicle in the plurality of continuous time periods before the target time period; generating a predicted value of the oil consumption of the historical time sequence by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data; generating a predicted value of the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period; and jointly training the oil consumption prediction model according to the actual value of the oil consumption of the historical time sequence, the predicted value of the oil consumption of the historical time sequence, the actual value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period.
In some embodiments, the jointly training oil consumption prediction model according to the actual value of the historical time sequence oil consumption, the predicted value of the historical time sequence oil consumption, the actual value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period includes: calculating a first loss function according to the actual value of the historical time sequence oil consumption and the predicted value of the historical time sequence oil consumption; calculating a second loss function according to the real value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period; and jointly training the oil consumption prediction model according to the first loss function and the second loss function.
In some embodiments, the jointly training the fuel consumption prediction model according to the first loss function and the second loss function includes: and jointly training the oil consumption prediction model according to the weighted results of the first loss function and the second loss function.
In some embodiments, the generating a predicted value of the historical time-series oil consumption by using a prediction model of the oil consumption of the mining area vehicle according to the historical time-series data includes: generating a time sequence characteristic by utilizing a multi-head self-attention network of a fuel consumption prediction model of the mining area vehicle according to historical time sequence data; and generating a predicted value of the historical time-sequence oil consumption according to the time-sequence characteristics.
In some embodiments, the generating the time series feature using a multi-head self-attention network of a fuel consumption prediction model of the mine vehicle according to the historical time series data includes: masking missing values in the historical time sequence data; generating a position code for the history time sequence data after mask processing; and generating a time sequence characteristic by utilizing a multi-head self-attention network, a feedforward neural network and a residual error network of the oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the position code.
In some embodiments, the mission data of the target time period includes a planned load and a mileage of the vehicle in the target time period, and the generating the predicted value of the fuel consumption of the target time period by using the fuel consumption prediction model of the mine vehicle according to the historical time series data and the mission data of the target time period includes: generating task characteristics according to the planned load and the driving mileage of the vehicle in the target time period; and generating a predicted value of the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the time sequence characteristics and the task characteristics.
In some embodiments, the generating the mission profile based on the planned load and the mileage of the vehicle over the target period of time includes: acquiring the no-load and the full-load of the vehicle; a plurality of load ranges are generated from the empty load and the full load of the vehicle: and generating task characteristics corresponding to the load ranges according to the driving mileage of the vehicle with the planned load in each load range.
In some embodiments, the generating a plurality of load ranges from the empty load and the full load of the vehicle comprises: the plurality of load ranges are nonlinearly divided according to an average value of empty loads of the plurality of vehicles at a specified time and a maximum value among full loads of the plurality of vehicles.
In some embodiments, the generating the mission characteristics corresponding to the load ranges according to the mileage of the vehicle planned to be loaded in each load range comprises: for each load range, a mission characteristic corresponding to the load range is generated based on the sum of the traveling mileage of all the vehicles in the load range, the average value of the planned load of all the vehicles in the load range, and the average value of the empty load of the plurality of vehicles at a predetermined time.
In some embodiments, the generating a predicted value of fuel consumption in a target time period according to the timing characteristics and the task characteristics includes: processing task characteristics by using a residual error network of a fuel consumption prediction model of the mining area vehicle; and generating a predicted value of the oil consumption in the target time period according to the sum of the task characteristics and the time sequence characteristics after the residual error network processing.
In some embodiments, the actual values of historical time-series fuel consumption comprise a sequence of actual values of total fuel consumption for a plurality of vehicles over a plurality of consecutive periods prior to a target period; the actual value of fuel consumption for the target time period includes an actual value of total fuel consumption for the plurality of vehicles over the target time period.
In some embodiments, the historical data includes at least one of historical weather data for the mine area, historical unloaded mileage of the vehicle, and historical loaded mileage.
In some embodiments, the obtaining task data for a target period includes: acquiring planned yields of different types of ores in a target time period; and determining the planned load of the vehicle in the target time period according to the planned yield of different types of ores in the target time period.
According to a second aspect of the present disclosure, there is provided a method for predicting oil consumption of mine vehicles, comprising obtaining historical time series data and task data of a target time period, wherein the historical time series data comprises a sequence of historical data of a plurality of consecutive time periods before the target time period; and predicting the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period.
In some embodiments, the oil consumption prediction model of the mining vehicle is obtained by training according to a training method of the oil consumption prediction model of any one embodiment of the present disclosure.
According to a third aspect of the present disclosure, a training device for a fuel consumption prediction model of a mine vehicle comprises: the acquisition module is configured to acquire historical time sequence data, task data of a target time period, a real value of historical time sequence oil consumption and a real value of oil consumption of the target time period, wherein the historical time sequence data comprise a sequence of historical data of a plurality of continuous time periods before the target time period, the real value of the historical time sequence oil consumption comprises a sequence of real values of oil consumption of a vehicle in the plurality of continuous time periods before the target time period, and the task data of the target time period comprise planned load and driving mileage of the vehicle in the target time period; the historical oil consumption generation module is configured to generate a predicted value of the historical time sequence oil consumption by utilizing an oil consumption prediction model of the mining area vehicle according to the historical time sequence data; the target oil consumption generation module is configured to generate a predicted value of oil consumption in a target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period; and the joint training module is configured to joint train the oil consumption prediction model according to the actual value of the oil consumption of the historical time sequence, the predicted value of the oil consumption of the historical time sequence, the actual value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period.
According to a fourth aspect of the disclosure, a prediction device of oil consumption of a mine vehicle comprises an acquisition module configured to acquire historical time sequence data and task data of a target time period, wherein the historical time sequence data comprises a sequence of historical data of a plurality of continuous time periods before the target time period, and the task data of the target time period comprises planned load and driving mileage of the vehicle in the target time period; and the prediction module is configured to predict the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period.
According to a fifth aspect of the present disclosure, an electronic device comprises:
a memory; and a processor coupled to the memory, the processor configured to execute the method for training the oil consumption prediction model of the mine vehicle according to any embodiment of the disclosure or the method for predicting the oil consumption of the mine vehicle according to any embodiment of the disclosure based on the instructions stored in the memory.
According to a sixth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method for training a prediction model of fuel consumption of a mine vehicle according to any one of the embodiments of the present disclosure, or the method for predicting fuel consumption of a mine vehicle according to any one of the embodiments of the present disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be understood more clearly from the following detailed description, taken with reference to the accompanying drawings, in which.
Fig. 1 illustrates a flow chart of a method of training a fuel consumption prediction model for mine vehicles, according to some embodiments of the present disclosure.
Fig. 2 illustrates a schematic diagram of planned production and haul, according to some embodiments of the present disclosure.
FIG. 3 illustrates a schematic diagram of a fuel consumption prediction model for a mine vehicle, according to some embodiments of the present disclosure.
FIG. 4 illustrates a flow chart of a method of predicting oil consumption of a mine vehicle, according to some embodiments of the present disclosure.
FIG. 5 illustrates a block diagram of a training apparatus for a fuel consumption prediction model for mine vehicles, according to some embodiments of the present disclosure.
FIG. 6 illustrates a block diagram of an apparatus for predicting oil consumption of a mine vehicle, according to some embodiments of the present disclosure.
FIG. 7 shows a block diagram of an electronic device, in accordance with further embodiments of the present disclosure.
FIG. 8 illustrates a block diagram of a computer system for implementing some embodiments of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of parts and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as exemplary only and not as limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
In the related art, only the influence of the task plan on the oil consumption on the day is considered, and the influence of time series data of continuous days in the past on the oil consumption is neglected, so that the prediction accuracy is not high. In addition, in the related art, labels of training data need to be labeled manually, which results in high training cost.
The invention provides a method and a device for training a fuel consumption prediction model of a mining vehicle and electronic equipment, which improve the efficiency and accuracy of fuel consumption prediction of the mining vehicle and reduce the cost.
Fig. 1 illustrates a flow chart of a method of training a fuel consumption prediction model for a mine vehicle, according to some embodiments of the present disclosure.
As shown in fig. 1, the method for training the fuel consumption prediction model of the mine vehicle includes steps S11 to S14.
In step S11, historical time series data, task data of a target time period, a true value of the historical time series oil consumption, and a true value of the oil consumption of the target time period are obtained, where the historical time series data includes a sequence of historical data of a plurality of consecutive time periods before the target time period, and the true value of the historical time series oil consumption includes a sequence of true values of the oil consumption of the vehicle in the plurality of consecutive time periods before the target time period.
For example, in days, the target period is 4 months and 1 day, and the consecutive periods before the target period may be 3 months and 1 day to 3 months and 31 days. The sequence of the history data of a plurality of consecutive periods before the target period is as follows.
Historical data of 3 month and 1 day, historical data of 3 month and 2 days, \8230 \ 8230 \ 31 day.
Similarly, the true values of fuel consumption for a number of consecutive periods preceding the target period are as follows.
Oil consumption in 3 months and 1 day, oil consumption in 3 months and 2 days, \ 8230 \ 8230 `, and oil consumption in 3 months and 31 days.
In some embodiments, the actual values of historical time-series fuel consumption comprise a sequence of actual values of total fuel consumption for a plurality of vehicles over a plurality of consecutive periods prior to the target period; the actual value of fuel consumption for the target time period includes an actual value of total fuel consumption for the plurality of vehicles during the target time period.
For example, the total oil consumption of all vehicles in the mining area is considered integrally, so that the integral oil consumption prediction of all vehicles in the mining area is realized, guidance can be provided for integral oil quantity storage supplement and mining task optimization in the mining area, the efficiency is improved, and the cost is saved.
In some embodiments, the historical data includes at least one of historical weather data for the mine area, historical empty mileage of the vehicle, and historical full mileage.
For example, weather data, an empty mileage and a full mileage of a vehicle are time-series data, that is, weather data of today and today, an empty mileage or a full mileage of a vehicle, and accordingly, weather data of tomorrow, an empty mileage and a full mileage of a vehicle are affected.
The oil consumption can be further influenced under different extreme climates and construction conditions. The influence of weather time sequence data is considered, and therefore oil consumption prediction of the strip mine in the complex climate environment is achieved.
In some embodiments, the mission data for the target time period includes a planned load and a mileage of the vehicle during the target time period, and the obtaining the mission data for the target time period includes: acquiring planned yields of different types of ores in a target time period; and determining the planned load of the vehicle in the target time period according to the planned yield of different types of ores in the target time period.
For example, the full-load driving mileage and the no-load driving mileage are uploaded by the unmanned vehicle in real time, and the daily full-load driving mileage and no-load driving mileage are regularly counted by the background big data management center.
The ore types are different, the total weight of the vehicles is different when the vehicles are fully loaded, the vehicle loads under different ore types are actual loads in the one-time transportation process of the vehicles, the vehicles have the conditions of no load, partial load, full load and the like, and the loads when the vehicles are fully loaded have certain difference. Therefore, planned yields of different types of ores can be formulated first, and planned loads of the vehicles in the target time period can be generated according to the planned yields of the different types of ores.
In some embodiments, the planned recovery is calculated from a mine allocation plan for the mine area, wherein the mine allocation plan is obtained from a data source.
For example, a mine allocation plan is obtained from a dispatch center module.
Fig. 2 illustrates a schematic diagram of projected production and haul, according to some embodiments of the present disclosure.
As shown in fig. 2, the production of the crushing stations 1 and 2, respectively, is related to the production of the quarries 1, 2 and the haul distance from the quarry 1 to the crushing station 1 needs to be calculated. Similarly, the output of the dump is related to the output of the stopes 1, 2.
In step S12, a predicted value of the historical time-series fuel economy is generated from the historical time-series data by using the vehicle fuel economy prediction model.
For example, the vehicle fuel consumption prediction model includes a neural network, and a time series of the historical fuel consumption corresponding to the neural network can be predicted according to the time series of the historical data by using the neural network.
In some embodiments, generating the predicted value of the historical time-series fuel consumption according to the historical time-series data by using a fuel consumption prediction model of the vehicle comprises: generating a time sequence characteristic by utilizing a multi-head self-attention network of a vehicle oil consumption prediction model according to historical time sequence data; and generating a predicted value of the historical time-sequence oil consumption according to the time-sequence characteristics.
For example, the characteristics of the sequences of the weather data of the past thirty days, the empty mileage and the full mileage of the vehicle are extracted by using the multi-head self-attention network, and the sequence of the fuel consumption of the past thirty days is calculated according to the extracted sequence characteristics.
The method and the device have the advantages that the feature extraction is carried out on the multi-source time sequence data such as the vehicle condition and the weather through the self-attention mechanism, and the capture capability of the long sequence features is enhanced.
In some embodiments, generating the timing feature from the historical timing data using a multi-headed self-attention network of a vehicle fuel consumption prediction model comprises: masking missing values in the historical time sequence data; generating a position code for the historical time sequence data after mask processing; and generating a time sequence characteristic by utilizing a multi-head self-attention network, a feedforward neural network and a residual error network of the vehicle oil consumption prediction model according to the historical time sequence data and the position code.
For example, the acquired data is time-series cut (weather is divided into daily weather) according to time continuity, and then feature completion is performed. Specifically, time series data is extracted in steps. Because the mining work is stopped for several days in severe weather such as part of holidays, rainstorm, snowstorm and the like, missing values in continuous time sequence characteristics are supplemented first, and characteristic data of date interruption is set to be zero. Then, a time sequence characteristic mask is generated according to the time sequence data interrupt condition.
The multi-head self-attention module and the feedforward neural network are used, residual connection is combined, and time sequence characteristics are generated. Wherein, the query vector q, the key vector k and the value vector v, and the attention vector is attention.
The transformation process for a multi-headed self-attention binding residual is as follows, wherein,
representing model parameters, LN representing layer normalization, concat representing stitching, input x in The output is x multi 。
The transformation process of the feedforward neural network combined with the residual error module is as follows, wherein W 1 ，W 2 B1, b2, are model parameters, relu represents an activation function, and the corresponding output is x out 。
In step S13, a predicted value of fuel consumption in the target period is generated using the vehicle fuel consumption prediction model based on the historical time series data and the task data in the target period.
In some embodiments, generating a predicted value of fuel consumption for the target time period using a vehicle fuel consumption prediction model based on the historical timing data and the mission data for the target time period comprises: generating task characteristics according to the planned load and the driving mileage of the vehicle in the target time period; and generating a predicted value of the oil consumption in the target time period according to the time sequence characteristics and the task characteristics.
For example, task features are extracted from task data, and the task features and the time sequence features are considered to jointly predict the oil consumption in the tomorrow.
In some embodiments, the planned load and range of the vehicle over the target period of time, generating mission features, comprises: acquiring the no-load and the full-load of the vehicle; a plurality of load ranges are generated from the empty load and the full load of the vehicle: a mission characteristic corresponding to the load range is generated based on the driving range of the vehicle for which the load is planned within each load range.
For example, the load section is a weight section from the empty weight of the vehicle to the maximum load weight of the vehicle obtained from the history data. Different quarry ore types account for than different, acquire the average load of the vehicle of corresponding ore type, acquire the vehicle load under the different ore types, wherein, same kind of ore, soil and ore proportion are different, lead to the vehicle under the condition of the ore of the different grade type of carrying same volume, the load is also different. The load can influence the fuel consumption, so the load conditions of different vehicles can be evaluated by dividing the load section, and the task characteristics are generated and used for predicting the fuel consumption.
In some embodiments, a plurality of load ranges are generated from the empty load and the full load of the vehicle, including: the plurality of load ranges are nonlinearly divided according to an average value of empty loads of the plurality of vehicles at a specified time and a maximum value among full loads of the plurality of vehicles.
For example, the average load of empty loads of all vehicles over a specified time (e.g., the past year) empty Maximum load of a single vehicle among all vehicles by a specified time (e.g., last year) max The load-carrying section is nonlinearly divided into n small sections, and the width wi of the ith section is as follows.
Where pi is an intermediate variable.
For example, the fuel consumption is counted in one day, the vehicle is mainly in two states of no load and loading in one day, and the fuel consumption is larger when the loading amount is larger. According to the method, the load carrying interval is divided in a nonlinear mode, and therefore large load can be divided more finely. The load is divided into n small intervals with different widths, the larger the load is, the smaller the intervals are, the more fine the division is, the discretization of data is realized, the difference characteristics among different loading capacities under the loading condition can be more accurately obtained, and therefore the accuracy of prediction is improved.
In some embodiments, generating mission characteristics corresponding to a load range based on miles driven by a vehicle projected to be loaded within the load range comprises: for each load range, a mission characteristic corresponding to the load range is generated based on the sum of the traveling ranges of all the vehicles whose planned loads are within the load range, the average value of the planned loads of all the vehicles whose planned loads are within the load range, and the average value of the empty loads of the plurality of vehicles at a predetermined time.
For example, for each load section wi, the planned load in the load section within the target time period is selectedwiAll vehicles in the house. The average of the planned loads of all vehicles within the load section wi is found: the average load loadi. And calculates in the load sectionw i Sum of the mileage of all vehicles within: driving distance dis i A load sectionw i And mileage dis i Forming feature pairs, and constructing combined features f according to the feature pairs i Obtaining n task characteristics f corresponding to the n load sections i As follows.
And the alpha i and the beta i are parameters of the vehicle oil consumption prediction model and are updated in the model training process.
According to the method, the load is divided into n cells with different widths, the larger the load is, the smaller the cells are, the more fine the division is, and the discretization of data is realized, so that n statistical characteristics are obtained and the method is used for inputting data of a vehicle fuel consumption prediction model.
In some embodiments, generating a predicted value of fuel consumption for the target time period based on the timing characteristics and the task characteristics comprises: processing task characteristics by using a residual error network of a vehicle oil consumption prediction model; and generating a predicted value of the oil consumption in the target time period according to the sum of the task characteristics and the time sequence characteristics after the residual error network processing.
For example, a residual error network is used for further extracting the characteristics of the task, then the result of the characteristic extraction is added with the time sequence characteristics, and the added result passes through at least one full connection layer, so that the predicted value of the oil consumption is obtained.
In step S14, a vehicle oil consumption prediction model is jointly trained according to the actual value of the historical time sequence oil consumption, the predicted value of the historical time sequence oil consumption, the actual value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period.
For example, the model is jointly trained by using the prediction results generated by the task data and the time sequence data of different data sources respectively.
In some embodiments, the method for jointly training the vehicle oil consumption prediction model according to the actual value of the historical time-series oil consumption, the predicted value of the historical time-series oil consumption, the actual value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period comprises the following steps: calculating a first loss function according to the actual value of the historical time sequence oil consumption and the predicted value of the historical time sequence oil consumption; calculating a second loss function according to the real value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period; and jointly training a vehicle oil consumption prediction model according to the first loss function and the second loss function.
For example, according to a historical oil consumption sequence predicted by historical time series data and oil consumption in a target time period predicted by task data in the target time period, a first loss function and a second loss function are respectively calculated, and then a vehicle oil consumption prediction model is jointly trained according to the first loss function and the second loss function, namely parameters of the model are updated. In the model parameter updating process, each time the parameters are updated, the parameters are simultaneously influenced by the first loss function and the second loss function.
That is, in each round (epoch) of training, the two types of labels, i.e., the true value of the historical oil consumption sequence and the true value of the oil consumption in the target period, can be used at the same time to correct the parameters of the model, instead of using only one label, i.e., the true value of the oil consumption in the target period. Although the predicted value of the target time interval is the final required result, the predicted value and the true value of the historical oil consumption sequence are additionally introduced, more references can be provided for model parameter updating, and therefore training efficiency is improved, and model prediction accuracy is improved.
In some embodiments, training the vehicle fuel consumption prediction model according to the first loss function and the second loss function comprises: and training a vehicle oil consumption prediction model according to the weighted result of the first loss function and the second loss function.
For example, a respective weight is set for each loss function, and the parameters of the model are updated based on the weighted sum of the loss functions.
According to the method, different types of data are processed respectively, the time sequence of the historical oil consumption is predicted according to the sequence of the historical data, and the oil consumption in the target time period is predicted according to comprehensive consideration of the historical time sequence data and the task data. And then, jointly training the model according to the predicted historical oil consumption and the predicted oil consumption in the target time period. According to the method and the device, when the oil consumption in the target time period is predicted, the influence of time sequence data on the oil consumption is additionally considered, the capturing capability of time sequence characteristics is enhanced, and the prediction accuracy is improved. In addition, when the model is trained, the actual value of the historical time sequence oil consumption and the predicted value of the historical time sequence oil consumption are additionally used for updating the parameters of the model, and the training efficiency of the model and the prediction accuracy of the model are improved.
In addition, labels (the true value of the oil consumption in the historical time sequence and the true value of the oil consumption in the target time period) of the training data used in the training model are the true oil consumption values, manual marking is not needed, and the cost is reduced.
FIG. 3 illustrates a schematic diagram of a fuel consumption prediction model for mine vehicles, according to some embodiments of the present disclosure.
As shown in fig. 3, position coding is performed on multi-dimensional time sequence characteristics formed by weather, full load, no-load mileage and the like, then the multi-head self-attention module, the residual module and the feedforward neural network are used for generating time sequence characteristics, and the time sequence characteristics are input into the full connection layer, so that a sequence of the historical oil consumption 1 is obtained.
For task data, extracting task features, then constructing a deep network through multilayer residual connection, obtaining deep task features, and further extracting the task features. And splicing (e.g., adding) the extracted result and the time sequence characteristics, and then inputting the spliced result into another full-connection layer to generate the oil consumption 2 of the time period needing to be predicted.
According to the oil consumption 1 and 2, parameters of the model (including parameters alpha i and beta i of the task data characteristics) are updated. And circularly acquiring time sequence data and task data uploaded every day, predicting oil consumption and updating parameters according to a prediction result. Through model cycle training, the model can be continuously optimized.
FIG. 4 illustrates a flow chart of a method of predicting oil consumption of a mine vehicle, according to some embodiments of the present disclosure.
As shown in fig. 4, the method for predicting the fuel consumption of a mine vehicle includes steps S21 to S22.
In step S21, acquiring history time series data and task data of a target period, wherein the history time series data includes a sequence of history data of a plurality of consecutive periods before the target period;
in step S22, the oil consumption in the target time period is predicted by using the oil consumption prediction model of the mine vehicle based on the historical time series data and the task data in the target time period.
For example, when fuel consumption in the next day needs to be predicted, historical data of weather and the like in the days and before the days and task data of a plan in the next day are acquired, and prediction is performed by using a trained fuel consumption prediction model according to the acquired data. And taking the oil consumption of the target time period generated by the model as a prediction result.
In some embodiments, the fuel consumption prediction model of the mine vehicle is trained according to the method of any embodiment of the present disclosure.
In some embodiments, the mission data of the target time period includes a planned load and a driving mileage of the vehicle in the target time period, and the predicted value of the fuel consumption of the vehicle in the target time period is generated by using a fuel consumption prediction model of the mine vehicle according to the historical time sequence data and the mission data of the target time period, and the method includes the following steps:
generating a time sequence characteristic by utilizing a multi-head self-attention network of a fuel consumption prediction model of the mining area vehicle according to historical time sequence data;
generating task characteristics according to the planned load and the driving mileage of the vehicle in the target time period;
and generating a predicted value of the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the time sequence characteristics and the task characteristics.
For example, when the model is used for prediction, the time series characteristic and the task characteristic are respectively generated according to the time series data and the task data, and the predicted value of the fuel consumption in the target time period is generated according to the time series characteristic and the task characteristic. Different from the training method, the prediction value of the historical time sequence oil consumption can not be generated any more during prediction, so that the prediction efficiency of the model is improved.
FIG. 5 illustrates a block diagram of a training apparatus for a fuel consumption prediction model for a mine vehicle, according to some embodiments of the present disclosure.
As shown in fig. 5, the training device 5 of the fuel consumption prediction model of the mine vehicle includes an obtaining module 51, a historical fuel consumption generating module 52, a target fuel consumption generating module 53, and a joint training module 54.
The obtaining module 51 is configured to obtain historical time series data, task data of a target time period, a true value of the historical time series fuel consumption, and a true value of the fuel consumption of the target time period, wherein the historical time series data includes a sequence of historical data of a plurality of continuous time periods before the target time period, the true value of the historical time series fuel consumption includes a sequence of true values of the fuel consumption of the vehicle in a plurality of continuous time periods before the target time period, and the task data of the target time period includes a planned load and a driving mileage of the vehicle in the target time period, for example, S11 shown in fig. 1 is executed.
And the historical oil consumption generation module 52 is configured to generate a predicted value of the historical time-series oil consumption by using an oil consumption prediction model of the mining area vehicle according to the historical time-series data, for example, executing S12 shown in FIG. 1.
And the target oil consumption generating module 53 is configured to generate a predicted value of the oil consumption in the target time period by using the oil consumption prediction model of the mining area vehicle according to the historical time series data and the task data in the target time period, for example, S13 shown in fig. 1 is executed.
And the joint training module 54 is configured to jointly train the oil consumption prediction model according to the actual value of the historical time-series oil consumption, the predicted value of the historical time-series oil consumption, the actual value of the oil consumption in the target period and the predicted value of the oil consumption in the target period, for example, executing S14 shown in fig. 1.
FIG. 6 illustrates a block diagram of an apparatus for predicting oil consumption of a mine vehicle, according to some embodiments of the present disclosure.
As shown in fig. 6, the prediction device 6 of the oil consumption of the mine vehicle comprises an acquisition module 61 and a prediction module 62.
The acquiring module 61 is configured to acquire historical time series data and task data of a target period, wherein the historical time series data includes a sequence of historical data of a plurality of continuous periods before the target period, and the task data of the target period includes a planned load and a driving mileage of the vehicle within the target period, for example, step S21 shown in fig. 2 is executed.
And the prediction module 62 is configured to predict the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data of the target time period, for example, step S22 shown in fig. 2 is executed.
FIG. 7 shows a block diagram of an electronic device, in accordance with further embodiments of the present disclosure.
As shown in fig. 7, the electronic device 7 includes a memory 71; and a processor 72 coupled to the memory 71, the memory 71 being configured to store instructions for executing a method for training a fuel consumption prediction model of a mine vehicle according to any of the embodiments of the present disclosure, or for executing a method for predicting fuel consumption of a mine vehicle according to any of the embodiments of the present disclosure. The processor 72 is configured to execute a method of training a fuel consumption prediction model of a mine vehicle or a method of predicting fuel consumption of a mine vehicle of any of the embodiments of the present disclosure, based on instructions stored in the memory 71.
FIG. 8 illustrates a block diagram of a computer system for implementing some embodiments of the present disclosure.
As shown in FIG. 8, computer system 80 may take the form of a general purpose computing device. Computer system 80 includes a memory 810, a processor 820, and a bus 800 that connects the various system components.
The memory 810 may include, for example, system memory, non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), and other programs. The system memory may include volatile storage media such as Random Access Memory (RAM) and/or cache memory. The non-volatile storage medium stores, for example, instructions to perform a method of training a fuel consumption prediction model for a mine vehicle or a method of predicting fuel consumption for a mine vehicle in any of the embodiments of the present disclosure. Non-volatile storage media include, but are not limited to, magnetic disk storage, optical storage, flash memory, and the like.
The processor 820 may be implemented as discrete hardware components, such as a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gates or transistors, or the like. Accordingly, each of the modules, such as the judging module and the determining module, may be implemented by a Central Processing Unit (CPU) executing instructions in a memory for performing the corresponding step, or may be implemented by a dedicated circuit for performing the corresponding step.
Claims (19)
1. A method for training a fuel consumption prediction model of mine vehicles comprises the following steps:
acquiring historical time sequence data, task data of a target time period, a real value of historical time sequence oil consumption and a real value of oil consumption of the target time period, wherein the historical time sequence data comprises a sequence of historical data of a plurality of continuous time periods before the target time period, and the real value of the historical time sequence oil consumption comprises a sequence of real values of oil consumption of a vehicle in the plurality of continuous time periods before the target time period;
generating a predicted value of the historical time sequence oil consumption by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data;
generating a predicted value of the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period;
and jointly training the oil consumption prediction model according to the actual value of the historical time sequence oil consumption, the predicted value of the historical time sequence oil consumption, the actual value of the oil consumption in the target period and the predicted value of the oil consumption in the target period.
2. The training method of claim 1, wherein jointly training the fuel consumption prediction model according to the actual value of the fuel consumption in the historical time sequence, the predicted value of the fuel consumption in the historical time sequence, the actual value of the fuel consumption in the target time period, and the predicted value of the fuel consumption in the target time period comprises:
calculating a first loss function according to the actual value of the historical time sequence oil consumption and the predicted value of the historical time sequence oil consumption;
calculating a second loss function according to the real value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period;
and jointly training the oil consumption prediction model according to the first loss function and the second loss function.
3. The training method of claim 2, wherein jointly training the fuel consumption prediction model according to the first loss function and the second loss function comprises:
and jointly training the oil consumption prediction model according to the weighted results of the first loss function and the second loss function.
4. The training method of claim 1, wherein generating a predicted value of historical time-series oil consumption using a model for predicting oil consumption of mine vehicles based on historical time-series data comprises:
generating a time sequence characteristic by utilizing a multi-head self-attention network of a fuel consumption prediction model of the mining area vehicles according to historical time sequence data;
and generating a predicted value of the historical time-sequence oil consumption according to the time-sequence characteristics.
5. The training method of claim 4, wherein generating a timing feature using a multi-headed self-attention network of a fuel consumption prediction model of mine vehicles from historical timing data comprises:
masking missing values in historical time sequence data;
generating a position code for the historical time sequence data after mask processing;
and generating a time sequence characteristic by utilizing a multi-head self-attention network, a feedforward neural network and a residual error network of a fuel consumption prediction model of the mining area vehicle according to the historical time sequence data and the position code.
6. The training method of claim 4, wherein the mission data of the target time period comprises the planned load and the mileage of the vehicle in the target time period, and the generating of the predicted value of the fuel consumption of the target time period by using the fuel consumption prediction model of the mine vehicle according to the historical time sequence data and the mission data of the target time period comprises:
generating task characteristics according to the planned load and the driving mileage of the vehicle in the target time period;
and generating a predicted value of the oil consumption in the target time period by using an oil consumption prediction model of the mining area vehicle according to the time sequence characteristics and the task characteristics.
7. The training method of claim 6, wherein generating mission features from a projected load and range of the vehicle over a target period comprises:
acquiring the no-load and the full-load of the vehicle;
a plurality of load ranges are generated from the empty load and the full load of the vehicle:
and generating task characteristics corresponding to the load ranges according to the driving mileage of the vehicle with the planned load in each load range.
8. The training method of claim 7, wherein generating a plurality of load ranges from an empty load and a full load of the vehicle comprises:
the plurality of load ranges are nonlinearly divided according to an average value of empty loads of the plurality of vehicles at a specified time and a maximum value among full loads of the plurality of vehicles.
9. The training method of claim 7, wherein generating the mission features corresponding to the load ranges from the range of travel of the vehicle for which the load is planned within each load range comprises:
for each load range, a mission characteristic corresponding to the load range is generated based on the sum of the traveling mileage of all the vehicles in the load range, the average value of the planned load of all the vehicles in the load range, and the average value of the empty load of the plurality of vehicles at a predetermined time.
10. The training method of claim 6, wherein generating a predicted value of fuel consumption for a target time period based on the timing characteristics and the mission characteristics comprises:
processing task characteristics by using a residual error network of a fuel consumption prediction model of the mining area vehicle;
and generating a predicted value of the oil consumption in the target time period according to the sum of the task characteristics and the time sequence characteristics after the residual error network processing.
11. The training method of claim 1, wherein:
the actual values of the historical time-series fuel consumption comprise a sequence of actual values of total fuel consumption of a plurality of vehicles in a plurality of consecutive time periods prior to a target time period;
the actual value of fuel consumption for the target time period includes an actual value of total fuel consumption for the plurality of vehicles over the target time period.
12. The training method of claim 1, wherein the historical data comprises at least one of historical weather data for the mine, historical empty mileage of the vehicle, and historical full mileage.
13. The training method of claim 1, wherein obtaining task data for a target period comprises:
acquiring planned yields of different types of ores in a target time period;
and determining the planned load of the vehicle in the target time period according to the planned yield of different types of ores in the target time period.
14. A method for predicting oil consumption of mining vehicles comprises
Acquiring historical time sequence data and task data of a target time period, wherein the historical time sequence data comprises a sequence of historical data of a plurality of continuous time periods before the target time period;
and predicting the oil consumption in the target time period by using the oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period.
15. The prediction method according to claim 14, wherein the prediction model for oil consumption of the mine vehicles is trained according to the method of any one of claims 1-13.
16. A training device for a fuel consumption prediction model of mine vehicles comprises:
the acquisition module is configured to acquire historical time sequence data, task data of a target time period, a real value of historical time sequence oil consumption and a real value of oil consumption of the target time period, wherein the historical time sequence data comprise a sequence of historical data of a plurality of continuous time periods before the target time period, the real value of the historical time sequence oil consumption comprises a sequence of real values of oil consumption of a vehicle in the plurality of continuous time periods before the target time period, and the task data of the target time period comprise planned load and driving mileage of the vehicle in the target time period;
the historical oil consumption generation module is configured to generate a predicted value of the historical time sequence oil consumption by utilizing an oil consumption prediction model of the mining area vehicle according to the historical time sequence data;
the target oil consumption generation module is configured to generate a predicted value of oil consumption in a target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data in the target time period;
and the joint training module is configured to joint train the oil consumption prediction model according to the actual value of the oil consumption of the historical time sequence, the predicted value of the oil consumption of the historical time sequence, the actual value of the oil consumption in the target time period and the predicted value of the oil consumption in the target time period.
17. A device for predicting oil consumption of mining vehicles comprises
The system comprises an acquisition module, a display module and a display module, wherein the acquisition module is configured to acquire historical time sequence data and task data of a target time period, the historical time sequence data comprises a sequence of historical data of a plurality of continuous time periods before the target time period, and the task data of the target time period comprises the planned load and the driving mileage of a vehicle in the target time period;
and the prediction module is configured to predict the oil consumption of the target time period by using an oil consumption prediction model of the mining area vehicle according to the historical time sequence data and the task data of the target time period.
18. An electronic device, comprising:
a memory; and
a processor coupled to the memory, the processor being configured to perform a method of training a prediction model of fuel consumption of a mine vehicle according to any one of claims 1 to 13, or to perform a method of predicting fuel consumption of a mine vehicle according to claim 14 or 15, based on instructions stored in the memory.
19. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method of training a fuel consumption prediction model for a mine vehicle according to any one of claims 1 to 13, or a method of predicting fuel consumption of a mine vehicle according to claim 14 or 15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211220194.7A CN115293055B (en) | 2022-10-08 | 2022-10-08 | Training method and device for oil consumption prediction model of mining vehicle and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211220194.7A CN115293055B (en) | 2022-10-08 | 2022-10-08 | Training method and device for oil consumption prediction model of mining vehicle and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115293055A true CN115293055A (en) | 2022-11-04 |
| CN115293055B CN115293055B (en) | 2023-05-09 |
Family
ID=83834636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211220194.7A Active CN115293055B (en) | 2022-10-08 | 2022-10-08 | Training method and device for oil consumption prediction model of mining vehicle and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115293055B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1786413A (en) * | 2005-11-17 | 2006-06-14 | 孟江 | Method for porecasting water upwelling amount of mine well based on nerve network model |
| CN110562096A (en) * | 2019-08-22 | 2019-12-13 | 东软睿驰汽车技术（沈阳）有限公司 | Remaining mileage prediction method and device |
| CN111310995A (en) * | 2020-02-12 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Service prediction method and device based on convolutional neural network |
| CN113776610A (en) * | 2021-08-04 | 2021-12-10 | 中寰卫星导航通信有限公司 | Method and device for determining vehicle oil consumption |
| CN114202123A (en) * | 2021-12-14 | 2022-03-18 | 深圳壹账通智能科技有限公司 | Service data prediction method and device, electronic equipment and storage medium |
| CN114274780A (en) * | 2022-01-10 | 2022-04-05 | 中国第一汽车股份有限公司 | Vehicle driving mileage prediction method, device, equipment and storage medium |
| CN114435138A (en) * | 2022-01-25 | 2022-05-06 | 中国第一汽车股份有限公司 | Vehicle energy consumption prediction method and device, vehicle and storage medium |
| CN114781698A (en) * | 2022-03-31 | 2022-07-22 | 山东大学 | Vehicle oil consumption prediction method and system based on spatio-temporal attention mechanism chart convolution network |
-
2022
- 2022-10-08 CN CN202211220194.7A patent/CN115293055B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1786413A (en) * | 2005-11-17 | 2006-06-14 | 孟江 | Method for porecasting water upwelling amount of mine well based on nerve network model |
| CN110562096A (en) * | 2019-08-22 | 2019-12-13 | 东软睿驰汽车技术（沈阳）有限公司 | Remaining mileage prediction method and device |
| CN111310995A (en) * | 2020-02-12 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Service prediction method and device based on convolutional neural network |
| CN113776610A (en) * | 2021-08-04 | 2021-12-10 | 中寰卫星导航通信有限公司 | Method and device for determining vehicle oil consumption |
| CN114202123A (en) * | 2021-12-14 | 2022-03-18 | 深圳壹账通智能科技有限公司 | Service data prediction method and device, electronic equipment and storage medium |
| CN114274780A (en) * | 2022-01-10 | 2022-04-05 | 中国第一汽车股份有限公司 | Vehicle driving mileage prediction method, device, equipment and storage medium |
| CN114435138A (en) * | 2022-01-25 | 2022-05-06 | 中国第一汽车股份有限公司 | Vehicle energy consumption prediction method and device, vehicle and storage medium |
| CN114781698A (en) * | 2022-03-31 | 2022-07-22 | 山东大学 | Vehicle oil consumption prediction method and system based on spatio-temporal attention mechanism chart convolution network |
Non-Patent Citations (2)
| Title |
|---|
| 冀盛全等: "神经网络测控露天煤矿220 t级卡车油耗研究", 《露天采矿技术》 * |
| 温廷新等: "矿用卡车单位油耗的神经网络预测", 《有色金属(矿山部分)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115293055B (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101350138B (en) | Method for estimating seaport planning year traffic generative amount based on inverse calculation of goods series | |
| CN113077103B (en) | Transportation network planning method and device | |
| Song et al. | A match‐then‐predict method for daily traffic flow forecasting based on group method of data handling | |
| US10643159B2 (en) | System and method for mining site production planning | |
| CN112862184A (en) | Transportation information prediction method and device, electronic equipment and readable storage medium | |
| CN111311050A (en) | Method for managing operations of a work site | |
| Wang et al. | Optimizing the maintenance schedule for a vehicle fleet: a simulation-based case study | |
| Safiullin et al. | The software adaptive system for managing the heavy cargo transportation process based on the automated vehicle weight and size control system | |
| CN115293055B (en) | Training method and device for oil consumption prediction model of mining vehicle and electronic equipment | |
| CN117436678B (en) | Method, device, equipment and storage medium for generating entry point of strip mine loading area | |
| Ruta et al. | Diversified gradient boosting ensembles for prediction of the cost of forwarding contracts | |
| CN117808384A (en) | Cargo matching method, device, equipment and medium for cargo transport vehicle | |
| JP4285232B2 (en) | Logistics cost forecasting device, forecasting method and program therefor | |
| CN116187887A (en) | Method for constructing and tracking traffic subsection door goods communication data | |
| US20230135656A1 (en) | Systems and methods for undercarriage wear prediction | |
| CN113706874B (en) | Method and device for predicting arrival time of logistics vehicles in factory in real time and electronic equipment | |
| Guseva et al. | Simulation modeling of transport flows of copper deposit | |
| Eskandari et al. | Simulation and optimization of haulage system of an open-pit mine. | |
| Kumar et al. | A digital solution framework for enabling electric vehicle battery circularity based on an ecosystem value optimization approach | |
| CN111815250B (en) | Cargo state identification method and device for logistics and classification modeling method | |
| EP3876045A1 (en) | A method of evaluating operation of at least one vehicle | |
| Kotenko et al. | Supervised Machine Learning Models for Forecasting Fuel Consumption by Vehicles During the Grain Crops Delivery | |
| Efimov et al. | Digital Transformation of Open-Pit Coal Mining in Russia | |
| Danilov et al. | Energy consumption forecasting as a service | |
| Martins et al. | An integrated simulation and optimization tool for short-term mining planning problems with different prioritization among competing plant targets |
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 |