CN116542389A - Truck fuel consumption prediction method, system, equipment and storage medium - Google Patents

Truck fuel consumption prediction method, system, equipment and storage medium Download PDF

Info

Publication number
CN116542389A
CN116542389A CN202310572243.1A CN202310572243A CN116542389A CN 116542389 A CN116542389 A CN 116542389A CN 202310572243 A CN202310572243 A CN 202310572243A CN 116542389 A CN116542389 A CN 116542389A
Authority
CN
China
Prior art keywords
truck
oil consumption
fuel consumption
time
time sequence
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
Application number
CN202310572243.1A
Other languages
Chinese (zh)
Inventor
王朋
王笑颜
徐豪
张树峰
纪凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinan Engineering Vocational Technical College
Original Assignee
Jinan Engineering Vocational Technical College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jinan Engineering Vocational Technical College filed Critical Jinan Engineering Vocational Technical College
Priority to CN202310572243.1A priority Critical patent/CN116542389A/en
Publication of CN116542389A publication Critical patent/CN116542389A/en
Pending legal-status Critical Current

Links

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • 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
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0838—Historical data
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0808—Diagnosing performance data
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Human Resources & Organizations (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a truck oil consumption prediction method, a system, equipment and a storage medium, comprising the following steps: collecting oil consumption time sequence data of a truck; preprocessing the oil consumption time series data, inputting the processed oil consumption time series data into a pre-trained time series oil consumption prediction model, and outputting an oil consumption prediction value of a truck; the time sequence fuel consumption prediction model is optimized by adopting an Adam loss function, and overfitting is reduced by a regularization method. The dependency relationship and the attention mechanism of the long-term memory neural network capturing time sequence are utilized to mine key information in the time sequence, so that the oil consumption of the truck is predicted more accurately. And the fusion of various characteristics is carried out, so that the prediction accuracy of the model is further improved, the model can be converged more quickly and is prevented from sinking into a local optimal solution, regularization and other technologies are adopted, the risk of overfitting of the model is reduced, the generalization performance of the model can be improved, and the prediction result is more accurate and reliable.

Description

Truck fuel consumption prediction method, system, equipment and storage medium
Technical Field
The present disclosure relates to the field of data mining technologies, and in particular, to a method, a system, an apparatus, and a storage medium for predicting truck fuel consumption.
Background
With the rising of the oil price, the truck oil consumption problem not only brings economic pressure to the logistics transportation industry, but also aggravates the environmental pollution problem. Therefore, the fuel consumption of the truck is studied with important significance and application prospect.
At present, the fuel consumption of a truck is generally researched by utilizing a neural network technology, the fuel consumption of the truck is predicted based on statistics and a machine learning method based on a fuel consumption prediction model of a traditional machine learning algorithm, the constraint of complex road spectrum road conditions and driving situations in the actual running of the truck is neglected, and complex practical problems are difficult to deal with only from the aspects of data and algorithm. Most algorithms require manual selection of features and parameters and cannot capture complex nonlinear relationships. The traditional time sequence-based model cannot deal with long-term dependence, and under the condition of a long sequence, the problems of gradient disappearance or gradient explosion can occur, the requirement on data is high, the characteristics are required to be manually extracted, and the influence of external factors cannot be well considered.
Disclosure of Invention
The embodiment of the application provides a truck oil consumption prediction method, a truck oil consumption prediction system, truck oil consumption prediction equipment and a storage medium, which are used for solving the problems.
Firstly, an embodiment of the present application provides a method for predicting truck fuel consumption, where the method includes: collecting oil consumption time series data of the truck; preprocessing the oil consumption time series data, inputting the processed oil consumption time series data into a pre-trained time series oil consumption prediction model, and outputting an oil consumption prediction value of the truck; the time sequence fuel consumption prediction model is optimized by adopting an Adam loss function, and the overfitting is reduced by a regularization method.
In one implementation manner of the present application, the training process of the time-series fuel consumption prediction model specifically includes: dividing the preprocessed oil consumption time series data into a training set and a testing set; constructing a time sequence oil consumption prediction model, and inputting the training set into a long-short-period memory network module in the time sequence oil consumption prediction model to obtain time sequence dependency characteristics of each moment; based on the time sequence dependent characteristics, cycle characteristics are obtained, and weight coefficients corresponding to the time sequence dependent characteristics are obtained; and based on the weight coefficient, carrying out weighted fusion on the periodic characteristics and the final output information of the long-short-period memory module to obtain the predicted value of the fuel consumption.
In one implementation manner of the present application, after the collecting the fuel consumption time series data of the truck, the method further includes: combining and encoding the acquired oil consumption time series data to obtain multi-effect variable characteristics; and normalizing the multi-influence variable characteristic based on a Z-score normalization mode so as to enable the multi-influence variable characteristic to accord with standard normal distribution.
In one implementation manner of the present application, the process of obtaining the periodic feature based on the time sequence dependent feature specifically includes: inputting the time sequence dependent characteristics of each moment in the long-short-term memory network module into an attention module to obtain attention scores; multiplying the attention score by a time series dependent characteristic of each instant of time to obtain the periodic characteristic.
In one implementation of the present application, after performing the weighted fusion, the method further includes: inputting the time sequence dependent characteristics of each moment in the long-short-term memory network module into an attention module, and calculating the attention score of each moment; the attention score is multiplied by the time series dependent features and summed to obtain a periodic variation law of the time series dependent features.
In one implementation manner of the present application, the fuel consumption time series data includes any one to more than one of the following: time, frame number, longitude and latitude coordinates, accumulated driving mileage, vehicle speed, engine rotation speed, accumulated operation fuel consumption, accumulated operation time, engine internal torque, vehicle external environment pressure, vehicle external environment temperature, engine oil pressure, circulating fuel injection quantity, internal torque percentage, accelerator pedal opening, engine coolant temperature, engine hour fuel consumption, engine fault code, brake switch state and clutch state.
In one implementation manner of the present application, the preprocessing is performed on the fuel consumption time series data, specifically: removing the rows with null values in the modulus variable after linear interpolation, and removing redundant rows in the repetition time; filtering data which does not meet a preset value based on a preset rotating speed value and a preset torque value; based on the preset time threshold, filtering out data with data fragments less than the preset time threshold.
Secondly, the embodiment of the application also provides a truck oil consumption prediction system, which comprises: the data acquisition module is used for acquiring the oil consumption time series data of the truck; the data preprocessing module is used for preprocessing the oil consumption time series data; the prediction module is used for inputting the processed oil consumption time sequence data into a pre-trained time sequence oil consumption prediction model and outputting an oil consumption prediction value of the truck; the time sequence fuel consumption prediction model is optimized by adopting an Adam loss function, and the overfitting is reduced by a regularization method.
Still further, the embodiment of the application also provides a truck oil consumption prediction device, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the truck fuel consumption prediction method as described above.
Finally, the embodiment of the application also provides a non-volatile computer storage medium for predicting truck oil consumption, which stores computer executable instructions for executing the truck oil consumption prediction method.
The embodiment of the application provides a truck oil consumption prediction method, a system, equipment and a storage medium, which utilize a long-short-term memory neural network to capture the dependency relationship of a time sequence and key information in an attention mechanism mining time sequence, so that the truck oil consumption is predicted more accurately. And fusion of various features is performed, so that the prediction accuracy of the model is further improved. The loss function based on the Adam optimization algorithm is used, so that the local optimal solution can be converged more quickly and prevented from being trapped, regularization and other technologies are adopted, the risk of model overfitting is reduced, the generalization performance of the model can be improved, and the prediction result is more accurate and reliable.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
fig. 1 is a flowchart of a method for predicting truck fuel consumption according to an embodiment of the present application;
FIG. 2 is a training flow chart of a model of an embodiment of the present application;
FIG. 3 is a diagram illustrating a truck fuel consumption prediction system according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a truck fuel consumption prediction apparatus provided in an embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The embodiment of the application provides a method, a system, equipment and a storage medium for predicting truck oil consumption, and the technical scheme provided by the embodiment of the application is described in detail through the attached drawings.
Fig. 1 is a flowchart of a truck fuel consumption prediction method provided in an embodiment of the present application. As shown in fig. 1, the method mainly comprises the following steps:
step S1: and collecting the oil consumption time series data of the truck.
In the embodiment of the application, the time series data is obtained by collecting original information through the vehicle machines of the related freight train, and the collection parameters include, but are not limited to, collection time, frame number, longitude and latitude coordinates, accumulated driving mileage, vehicle speed, engine rotating speed, accumulated operation fuel consumption, accumulated operation time, engine internal torque, vehicle external environment pressure, vehicle external environment temperature, engine oil pressure, circulating fuel injection quantity, internal torque percentage, accelerator pedal opening, engine coolant temperature, engine hour fuel consumption, engine fault code, brake switch state, clutch state and other characteristics related to road spectrum road conditions.
Further, the acquired oil consumption time series data are combined and encoded to obtain multi-effect variable characteristics; and normalizing the multi-influence variable characteristic based on a Z-score normalization mode so as to enable the multi-influence variable characteristic to accord with standard normal distribution.
It should be noted that, the Z-score normalization is to normalize data according to the standard deviation so as to conform to a standard normal distribution, and the formula is as follows:where x is the original data, μ is the mean of the original data, σ is the standard deviation of the original data, and z is the normalized data. The Z-score normalization can maintain the distribution form of the original data, and can convert the data into standard normal distribution, thereby facilitating comparison and analysis between different variables. At the same time, since Z-score normalization is not limited by data range, it can be better adapted toTime series data of the same data range.
Step S2: preprocessing the oil consumption time series data, inputting the processed oil consumption time series data into a pre-trained time series oil consumption prediction model, and outputting the oil consumption predicted value of the truck.
In the embodiment of the present application, the training process of the time-series fuel consumption prediction model, as shown in fig. 2, specifically includes the following steps:
step S21: and dividing the preprocessed oil consumption time series data into a training set and a testing set.
In this embodiment of the present application, the preprocessing of the fuel consumption time-series data specifically includes: removing the rows with the modulus variable containing null values after linear interpolation; removing redundant rows in the repetition time; only data satisfying both the engine speed >700 and the engine internal torque >100 are retained; searching continuous data fragments, wherein the conditions are met, at least more than 60S is provided, the difference between the maximum value and the minimum value of the cooling liquid temperature in the fragments is not more than 5%, and the same fragment is marked and numbered. Based on the acquired longitude and latitude coordinates and actual feedback, distinguishing data of different road spectrums and marking.
Step S22: and constructing a time sequence oil consumption prediction model, and inputting the training set into a long-short-period memory network module in the time sequence oil consumption prediction model to obtain time sequence dependency characteristics of each moment.
In the embodiment of the application, the time sequence dependence characteristic can capture time sequence correlation and nonlinear relation in data.
Step S23: and obtaining periodic characteristics based on the time sequence dependent characteristics, and obtaining weight coefficients corresponding to the time sequence dependent characteristics.
In the embodiment of the present application, in order to check the relationship between the time sequence dependency characteristic at each moment and the last output of the long-term and short-term memory network module, a corresponding weight coefficient needs to be obtained. The weight coefficients are obtained using an attention mechanism. Specifically, the time sequence dependent characteristic of each moment of the long-period memory network module is input into the attention module to obtain attention score, and the attention score is multiplied by the time sequence dependent characteristic of each moment to finally obtain the periodic characteristic.
Step S24: and based on the weight coefficient, carrying out weighted fusion on the periodic characteristics and the final output information of the long-short-period memory module to obtain the predicted value of the fuel consumption.
Further, the period characteristics obtained by the attention module are fused with the final output information of the long-period and short-period memory network module. Specifically, the two features are spliced, and then weighted fusion is carried out through a full-connection layer, so that a final output result is obtained.
Furthermore, the fused data is input into a full connection layer to obtain a predicted value, and an Adam algorithm (Adaptive Moment Estimation) is adopted to optimize until convergence. Adam is a commonly used optimization algorithm, commonly used to train deep learning models. Adam's algorithm combines the advantages of adaptive learning rate and momentum, while utilizing first and second moment estimates of gradients to adjust learning rate. The Adam algorithm has the main advantages that the learning rate can be adaptively adjusted, the process of manually adjusting parameters is avoided, and the Adam algorithm has better performance.
Furthermore, the time sequence dependent characteristics of each moment of the long-period memory network module are input into the attention module, and the periodic variation rules of all the time sequence dependent characteristics are obtained through an attention mechanism. Specifically, the attention mechanism can calculate the attention score of each moment according to the time sequence dependency characteristic and a learnable parameter vector of each moment of the long-term memory network module, so as to obtain a corresponding periodic variation rule. This periodic variation law can be obtained by multiplying the attention score with the time-series dependent features and summing. The calculation formula of the attention mechanism can be expressed as:
wherein a is t Attention score at time t, t representing long-short term memory network modelOutput of block at time t, gamma t-1 Representing the periodic characteristics, ω, of the last moment a A learnable parameter vector, ω, representing the attentional mechanisms a1 And omega a2 Weight matrix representing the attentional mechanisms, b a Representing the bias vector.
By calculating the attention score, we can get the periodic characteristics at each moment, and the calculation formula can be expressed as:wherein, gamma t The periodic characteristic at the T-th time is represented by T, the length of time series data is represented by a i Represents the attention score, h, at time i i And the output of the long-period memory network module at the ith moment is represented.
The foregoing is a method for predicting truck oil consumption provided by the embodiments of the present application, and based on the same inventive concept, the embodiments of the present application further provide a system for predicting truck oil consumption, and fig. 3 is a composition diagram of the truck oil consumption prediction system provided by the embodiments of the present application, as shown in fig. 3, where the system mainly includes: the data acquisition module 301 is configured to acquire fuel consumption time series data of the truck; the data preprocessing module 302 is configured to preprocess the fuel consumption time series data; the prediction module 303 is configured to input the processed fuel consumption time sequence data into a pre-trained time sequence fuel consumption prediction model, and output a fuel consumption predicted value of the truck; the time sequence fuel consumption prediction model is optimized by adopting an Adam loss function, and the overfitting is reduced by a regularization method.
The embodiment of the application provides a truck oil consumption prediction scheme, which utilizes a long-short-term memory neural network to capture the dependency relationship of a time sequence and key information in an attention mechanism mining time sequence, so that the truck oil consumption is predicted more accurately. And fusion of various features is performed, so that the prediction accuracy of the model is further improved. The loss function based on the Adam optimization algorithm is used, so that the local optimal solution can be converged more quickly and prevented from being trapped, regularization and other technologies are adopted, the risk of model overfitting is reduced, the generalization performance of the model can be improved, and the prediction result is more accurate and reliable.
The foregoing is a fuel consumption prediction system for a truck provided in the embodiments of the present application, and based on the same inventive concept, the embodiments of the present application further provide a fuel consumption prediction device for a truck, and fig. 4 is a schematic diagram of a fuel consumption prediction device for a truck provided in the embodiments of the present application, as shown in fig. 4, where the device mainly includes: at least one processor 401; and a memory 402 communicatively coupled to the at least one processor; the memory 402 stores instructions executable by the at least one processor 401, and the instructions are executed by the at least one processor 401, so that the at least one processor 401 can implement the truck fuel consumption prediction method.
In addition, the embodiment of the application also provides a non-volatile computer storage medium for predicting truck oil consumption, which stores computer executable instructions, and the computer can execute the truck oil consumption prediction method.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
All embodiments in the application are described in a progressive manner, and identical and similar parts of all embodiments are mutually referred, so that each embodiment mainly describes differences from other embodiments. In particular, for the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims (10)

1. The method for predicting the truck oil consumption is characterized by comprising the following steps of:
collecting oil consumption time series data of the truck;
preprocessing the oil consumption time series data, inputting the processed oil consumption time series data into a pre-trained time series oil consumption prediction model, and outputting an oil consumption prediction value of the truck; the time sequence fuel consumption prediction model is optimized by adopting an Adam loss function, and the overfitting is reduced by a regularization method.
2. The truck fuel consumption prediction method according to claim 1, wherein the training process of the time-series fuel consumption prediction model specifically includes:
dividing the preprocessed oil consumption time series data into a training set and a testing set;
constructing a time sequence oil consumption prediction model, and inputting the training set into a long-short-period memory network module in the time sequence oil consumption prediction model to obtain time sequence dependency characteristics of each moment;
based on the time sequence dependent characteristics, cycle characteristics are obtained, and weight coefficients corresponding to the time sequence dependent characteristics are obtained;
and based on the weight coefficient, carrying out weighted fusion on the periodic characteristics and the final output information of the long-short-period memory module to obtain the predicted value of the fuel consumption.
3. The method for predicting fuel consumption of a truck according to claim 1, wherein after the collecting the fuel consumption time series data of the truck, the method further comprises:
combining and encoding the acquired oil consumption time series data to obtain multi-effect variable characteristics;
and normalizing the multi-influence variable characteristic based on a Z-score normalization mode so as to enable the multi-influence variable characteristic to accord with standard normal distribution.
4. The method for predicting truck fuel consumption according to claim 2, wherein the process of obtaining the periodic characteristic based on the time-series dependent characteristic is specifically:
inputting the time sequence dependent characteristics of each moment in the long-short-term memory network module into an attention module to obtain attention scores;
multiplying the attention score by a time series dependent characteristic of each instant of time to obtain the periodic characteristic.
5. The truck fuel consumption prediction method according to claim 2, characterized in that after the weighted fusion, the method further comprises:
inputting the time sequence dependent characteristics of each moment in the long-short-term memory network module into an attention module, and calculating the attention score of each moment;
the attention score is multiplied by the time series dependent features and summed to obtain a periodic variation law of the time series dependent features.
6. The truck fuel consumption prediction method according to claim 1, characterized in that the fuel consumption time-series data includes any one to more of: time, frame number, longitude and latitude coordinates, accumulated driving mileage, vehicle speed, engine rotation speed, accumulated operation fuel consumption, accumulated operation time, engine internal torque, vehicle external environment pressure, vehicle external environment temperature, engine oil pressure, circulating fuel injection quantity, internal torque percentage, accelerator pedal opening, engine coolant temperature, engine hour fuel consumption, engine fault code, brake switch state and clutch state.
7. The truck fuel consumption prediction method according to claim 1, wherein the fuel consumption time series data is preprocessed, specifically:
removing the rows with null values in the modulus variable after linear interpolation, and removing redundant rows in the repetition time;
filtering data which does not meet a preset value based on a preset rotating speed value and a preset torque value;
based on the preset time threshold, filtering out data with data fragments less than the preset time threshold.
8. A fuel consumption prediction system for a truck, the system comprising:
the data acquisition module is used for acquiring the oil consumption time series data of the truck;
the data preprocessing module is used for preprocessing the oil consumption time series data;
the prediction module is used for inputting the processed oil consumption time sequence data into a pre-trained time sequence oil consumption prediction model and outputting an oil consumption prediction value of the truck; the time sequence fuel consumption prediction model is optimized by adopting an Adam loss function, and the overfitting is reduced by a regularization method.
9. A truck fuel consumption prediction apparatus, characterized in that the apparatus comprises:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A non-transitory computer storage medium storing computer executable instructions for predicting truck fuel consumption, wherein the computer executable instructions are configured to perform the method of any one of claims 1-7.
CN202310572243.1A 2023-05-18 2023-05-18 Truck fuel consumption prediction method, system, equipment and storage medium Pending CN116542389A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310572243.1A CN116542389A (en) 2023-05-18 2023-05-18 Truck fuel consumption prediction method, system, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310572243.1A CN116542389A (en) 2023-05-18 2023-05-18 Truck fuel consumption prediction method, system, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116542389A true CN116542389A (en) 2023-08-04

Family

ID=87454039

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310572243.1A Pending CN116542389A (en) 2023-05-18 2023-05-18 Truck fuel consumption prediction method, system, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116542389A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117168558A (en) * 2023-11-03 2023-12-05 山东奥斯登房车有限公司 High-end intelligent real-time monitoring method for fuel consumption of caravan
CN117763976A (en) * 2024-02-22 2024-03-26 华南师范大学 method and device for predicting lubricating oil quantity of aero-engine and computer equipment

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117168558A (en) * 2023-11-03 2023-12-05 山东奥斯登房车有限公司 High-end intelligent real-time monitoring method for fuel consumption of caravan
CN117168558B (en) * 2023-11-03 2024-01-16 山东奥斯登房车有限公司 High-end intelligent real-time monitoring method for fuel consumption of caravan
CN117763976A (en) * 2024-02-22 2024-03-26 华南师范大学 method and device for predicting lubricating oil quantity of aero-engine and computer equipment
CN117763976B (en) * 2024-02-22 2024-05-14 华南师范大学 Method and device for predicting lubricating oil quantity of aero-engine and computer equipment

Similar Documents

Publication Publication Date Title
CN116542389A (en) Truck fuel consumption prediction method, system, equipment and storage medium
CN111160311A (en) Yellow river ice semantic segmentation method based on multi-attention machine system double-flow fusion network
CN112069892B (en) Image recognition method, device, equipment and storage medium
CN111612274A (en) Tidal water level forecasting method based on space-time correlation
CN115496384A (en) Monitoring management method and device for industrial equipment and computer equipment
CN117406100A (en) Lithium ion battery remaining life prediction method and system
CN114297795B (en) PR-Trans-based mechanical equipment residual life prediction method
CN117057779A (en) Digital twin reduced order model construction method based on lumped probability reconstruction
CN116599683A (en) Malicious traffic detection method, system, device and storage medium
CN118332511A (en) Underwater laser welding quality stability prediction method based on LSTM-HHO-SVR
CN116628395B (en) Urban terrain feature-based road vehicle carbon emission measuring and calculating method and system
CN116628444A (en) Water quality early warning method based on improved meta-learning
CN114550460B (en) Rail transit anomaly detection method and device and storage medium
CN116386005A (en) Door and window opening prompting method and system after vehicle collision
Shah et al. A Comparative Study of Machine Learning and Deep Learning Techniques for Prediction of CO 2 Emission in Cars
CN116184470A (en) Patrol car fusion positioning method and device based on data driving and relevant medium thereof
US20230297823A1 (en) Method and system for training a neural network for improving adversarial robustness
CN116151449A (en) Short-term prediction method and device for power load
CN114722704A (en) Wheel wear prediction network model training method and device
Yu et al. CNN-LSTM-based model for predicting the remaining useful life of rolling bearings
CN114168320B (en) End-to-end edge intelligent model searching method and system based on implicit spatial mapping
Su et al. Intelligent Prediction of Bearing Remaining Useful Life Based on Data Enhancement and Adaptive Temporal Convolutional Networks
CN115481702B (en) Predictive comparison characterization method for multi-element time series data processing
CN117698749A (en) Vehicle control method and device based on state sequence prediction and electronic equipment
CN117334058B (en) Truck traffic flow prediction method, device, equipment and storage medium

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