CN112163299A - Excavator oil consumption prediction method and system and electronic equipment - Google Patents
Excavator oil consumption prediction method and system and electronic equipment Download PDFInfo
- Publication number
- CN112163299A CN112163299A CN202011068500.0A CN202011068500A CN112163299A CN 112163299 A CN112163299 A CN 112163299A CN 202011068500 A CN202011068500 A CN 202011068500A CN 112163299 A CN112163299 A CN 112163299A
- Authority
- CN
- China
- Prior art keywords
- excavator
- model
- injection system
- oil consumption
- oil
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F9/00—Measuring volume flow relative to another variable, e.g. of liquid fuel for an engine
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Fluid Mechanics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Operation Control Of Excavators (AREA)
Abstract
The invention provides a method and a system for predicting oil consumption of an excavator and electronic equipment, and relates to the technical field of oil consumption prediction of engineering equipment. The method comprises the steps of firstly, determining an electric injection type oil injection system excavator which is the same as a mechanical oil injection system excavator in model, and acquiring attribute data of the electric injection type oil injection system excavator; selecting a proper prediction model according to the attribute type; and inputting the attribute data into the initialized prediction model, and correcting the predicted oil consumption by using the real-time oil consumption according to the loss function set in the model. According to the method, the same type of electric injection type oil injection system excavator is used as an excavator of which training data is generalized to a mechanical oil injection system, model secondary correction is carried out according to the actual oil filling amount, and accurate acquisition of real-time oil consumption of the mechanical oil injection system excavator is achieved.
Description
Technical Field
The invention relates to the technical field of oil consumption prediction of engineering equipment, in particular to a method and a system for predicting oil consumption of an excavator and electronic equipment.
Background
The oil consumption control of the engineering equipment is important, but the existing engineering equipment still has a plurality of problems for the oil consumption control. Taking an excavator as an example, some excavators using a mechanical oil injection system cannot provide data related to oil consumption due to the limitation of the system. The oil consumption of the excavator equipment is high, the carried oil tank is large, the probability of oil stealing and oil leakage is also high, and once the situation occurs, a driver cannot directly judge the change of the oil quantity in the oil tank through oil consumption data, so that the maintainability of the excavator is poor.
Disclosure of Invention
In view of the above, the present invention provides a method, a system, and an electronic device for predicting oil consumption of an excavator, in which a related prediction model is used to predict oil consumption of a mechanical oil injection system excavator in real time, an electronic injection system excavator of the same model is generalized to an excavator of a mechanical oil injection system as training data, and model correction is performed by using an actual oil charge and real-time oil consumption uploaded by an electronic injection system as errors, so as to accurately obtain real-time oil consumption of the mechanical oil injection system excavator, fit oil consumption at different engine speeds with discrete changes, and increase a predictive maintenance scenario for an abnormal oil consumption scenario of the excavator.
In a first aspect, an embodiment of the present invention provides a method for predicting oil consumption of an excavator, where the method is applied to a mechanical oil injection system excavator, and the method includes:
determining an electronic injection type oil injection system excavator with the same model as the mechanical oil injection system excavator according to the model of the mechanical oil injection system excavator;
acquiring attribute data of an excavator of an electronic injection type oil injection system; the attribute data comprise real-time oil consumption of an excavator of the electronic injection type oil injection system;
inputting the attribute data into an initialization model in a model base to carry out model training, and taking the trained initialization model as a prediction model; the prediction model outputs the predicted oil consumption of the excavator of the electronic injection type oil injection system, and the predicted oil consumption is corrected by using the loss function and the real-time oil consumption;
and taking the predicted oil consumption of the corrected electric injection type oil injection system excavator as the real-time oil consumption of the mechanical oil injection system excavator.
In some embodiments, the training process of the initialization model includes:
obtaining model sample data; the model sample data is attribute data of an electric injection type oil injection system excavator of the same model as the mechanical oil injection system excavator;
inputting model sample data into an initialized random forest model for training to obtain a first training result;
respectively carrying out normalization calculation and zero value calculation on the first training result to obtain a second training result;
performing stacking regression calculation on the second training result by using a K-proximity algorithm to obtain temporary oil consumption prediction data; in the stacking regression calculation process, comparing the real-time oil consumption and temporary oil consumption prediction data of an excavator of the electronic injection type oil injection system to obtain a first comparison result, wherein the first comparison result is used as a correction parameter of an initialization model;
and calculating a loss value of the initialization model according to a preset loss function, and stopping training when the loss value meets a preset expected threshold value to obtain a prediction model.
In some embodiments, before inputting the model sample data into the initialized random forest model for training, the training process for initializing the model further includes:
performing correlation extraction on the model sample data by using a correlation coefficient matrix and a genetic algorithm to obtain a correlation result related to oil consumption change in the model sample data;
and combining the correlation result with the model sample data, and using the combined result as new model sample data for training the initialization model.
In some embodiments, after the step of obtaining model sample data, the training process for initializing the model further includes:
acquiring the oil consumption standard of the excavator of the electronic injection type oil injection system according to the gear data, the model data, the engine model and the emission standard data in the attribute data;
and taking the oil consumption reference of the excavator test data of the electronic injection type oil injection system as a filtering threshold reference, and filtering the oil consumption data of the model sample data to remove abnormal values.
In some embodiments, the modifying parameters further include:
acquiring the actual oil filling amount of a mechanical oil injection system excavator;
and comparing the actual fuel charge of the mechanical fuel injection system excavator with the temporary fuel consumption prediction data to obtain a second comparison result, wherein the second comparison result is used as a correction parameter of the initialization model.
In some embodiments, the attribute data of the electric injection type oil injection system excavator further includes: the method comprises the steps of main pump pressure, LS pressure, engine rotating speed, action codes and fuel temperature before and after an electronic injection type fuel injection system excavator.
In some embodiments, the initialization model and the trained prediction model are deployed in a cloud server.
In a second aspect, an embodiment of the present invention provides a system for predicting oil consumption of an excavator, where the system is applied to a mechanical oil injection system excavator, and the system includes:
the electronic injection type oil injection system excavator determining module is used for determining an electronic injection type oil injection system excavator which has the same model as the mechanical oil injection system excavator according to the model of the mechanical oil injection system excavator;
the electronic injection type oil injection system excavator attribute data acquisition module is used for acquiring attribute data of an electronic injection type oil injection system excavator; the attribute data comprise real-time oil consumption of an excavator of the electronic injection type oil injection system;
the oil consumption prediction module of the electric injection type oil injection system excavator is used for inputting the attribute data into an initialization model in a preset model base to carry out model training, and taking the trained initialization model as a prediction model; the prediction model outputs the predicted oil consumption of the excavator of the electronic injection type oil injection system, and the predicted oil consumption is corrected by utilizing a loss function and real-time oil consumption;
and the oil consumption determining module of the mechanical oil injection system excavator is used for taking the predicted oil consumption of the electric injection system excavator which is corrected as the real-time oil consumption of the mechanical oil injection system excavator.
In a third aspect, an embodiment of the present invention further provides an electronic device, including: a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the steps of the method for predicting excavator oil consumption as set forth in any of the possible embodiments of the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the steps of the method for predicting excavator oil consumption mentioned in any possible implementation manner of the first aspect.
The embodiment of the invention has the following beneficial effects:
the invention provides a method, a system and electronic equipment for predicting oil consumption of an excavator, which are applied to a mechanical oil injection system excavator, wherein the method comprises the steps of firstly determining an electric injection type oil injection system excavator with the same model as the mechanical oil injection system excavator according to the model of the mechanical oil injection system excavator, and acquiring attribute data of the electric injection type oil injection system excavator; the attribute data comprise real-time oil consumption of the electric injection type oil injection system excavator, and a proper prediction model is selected according to the attribute type. And inputting the attribute data into the trained prediction model, and correcting the predicted oil consumption by using the real-time oil consumption according to a loss function set in the model. The method utilizes a relevant prediction model to predict the oil consumption of the mechanical oil injection system excavator in real time, the electric injection system excavator with the same model is used as training data to be generalized to the mechanical oil injection system excavator, the actual oil adding amount and the real-time oil consumption uploaded by the electric injection system are used as errors to carry out model correction, the accurate acquisition of the real-time oil consumption of the mechanical oil injection system excavator is realized, the oil consumption under different engine rotating speeds with discrete changes can be fitted, and the predictive maintenance scene of the abnormal oil consumption scene of the excavator is increased.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention as set forth above.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for predicting excavator oil consumption according to an embodiment of the present disclosure;
FIG. 2 is a flowchart of a training process of a prediction model used in a prediction method for excavator oil consumption according to an embodiment of the present invention;
fig. 3 is a flowchart before model sample data is input into an initialized random forest model for training in a training process of a prediction model used in the prediction method for excavator oil consumption according to the embodiment of the present invention;
fig. 4 is a flowchart after a step of obtaining model sample data in a training process of a prediction model used in the prediction method for excavator oil consumption according to the embodiment of the present invention;
fig. 5 is a flowchart illustrating a procedure of obtaining a correction parameter in the method for predicting the oil consumption of the excavator according to the embodiment of the present invention;
FIG. 6 is a flow chart of another method for predicting oil consumption of an excavator according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a system for predicting oil consumption of an excavator according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Icon:
710-an electronic fuel injection system excavator determining module; 720-an electronic injection type oil injection system excavator attribute data acquisition module; 730-oil consumption prediction module of excavator of electric injection type oil injection system; 740-determining module for oil consumption of excavator of mechanical oil injection system; 101-a processor; 102-a memory; 103-a bus; 104-communication interface.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Because engineering equipment (excavator, road roller, bull-dozer etc.) is provided with the engine of great power, consequently engineering equipment's oil consumption is generally higher, and it is extremely important to engineering equipment's oil consumption management and control, nevertheless still has a great deal of problem to the oil consumption management and control in the existing engineering equipment. Taking an excavator as an example, some excavators using a mechanical oil injection system cannot provide data related to oil consumption and cannot obtain the cruising ability of the excavator due to the limitation of the system. The oil consumption of the excavator equipment is high, and the carried oil tank is large, so that the probability of oil stealing and leaking is high, once the situation occurs, a driver cannot directly judge the change of the oil quantity in the oil tank through oil consumption data, and cannot master the situation at the first time when abnormal situations such as oil stealing and leaking occur, so that the maintainability of the excavator is poor.
Therefore, in the prior art, an effective technical means is lacked for oil consumption prediction of a mechanical oil injection system excavator, and meanwhile, the excavator also has the problem of difficult maintenance.
Based on the method, the system and the electronic equipment for predicting the oil consumption of the excavator, provided by the embodiment of the invention, the oil consumption of the mechanical oil injection system excavator is predicted in real time by using the related prediction model, the electric injection system excavator with the same model is used as training data to be generalized to the mechanical oil injection system excavator, the actual oil filling amount and the real-time oil consumption uploaded by the electric injection system excavator are used as errors to carry out model correction, the accurate acquisition of the real-time oil consumption of the mechanical oil injection system excavator is realized, the oil consumption under different engine rotating speeds with discrete changes can be fitted, and the predictive maintenance scene of the abnormal oil consumption scene of the excavator is increased.
For the convenience of understanding the present embodiment, a method for predicting the oil consumption of the excavator disclosed in the embodiment of the present invention will be described in detail.
Referring to a flow chart of a method for predicting oil consumption of an excavator shown in fig. 1, the method is applied to a mechanical oil injection system excavator, and comprises the following specific steps:
and S101, determining an electronic injection type oil injection system excavator with the same model as the mechanical oil injection system excavator according to the model of the mechanical oil injection system excavator.
Since the excavator of the mechanical oil injection system does not have the oil consumption calculation capacity, the excavator which is provided with the electric oil injection system in the same model is used as a data source of the excavator of the mechanical oil injection system. Specifically, the data source is training data of a prediction model in the subsequent steps, and excavators with the same type and equipped with an electronic fuel injection system are generalized to excavators with a mechanical fuel injection system as training data, so that the oil consumption of the mechanical fuel injection system excavators is indirectly predicted.
Step S102, acquiring attribute data of an excavator of an electronic injection type oil injection system; the attribute data comprise real-time oil consumption of the excavator of the electronic injection type oil injection system.
For attribute data of an excavator of an electronic fuel injection system, the attribute data comprises static data, dynamic data and fuel consumption data of the excavator. The static data is related attribute data of the excavator in a static state, such as weight, volume, maximum power of an engine and the like; the dynamic data is dynamic data of relevant equipment when the excavator performs excavation operation, such as main pump pressure, LS pressure, action codes, engine rotating speed and the like; the oil consumption data is data related to oil consumption of the excavator, such as historical maximum oil consumption data, average oil consumption data, dynamic real-time oil consumption data and the like. Because various attribute data are involved, the oil consumption data under different engine rotating speeds with discrete changes can be represented through a subsequent prediction process.
The attribute data can be obtained through relevant sensors arranged in the excavator, and can also be obtained through a data reading interface directly reading the excavator control unit.
Step S103, inputting attribute data into an initialization model in a model base to carry out model training, and taking the trained initialization model as a prediction model; and the prediction model outputs the predicted oil consumption of the excavator of the electronic injection type oil injection system, and the predicted oil consumption is corrected by utilizing the loss function and the real-time oil consumption.
The model library includes various types of initialization models corresponding to different attribute types. The initialization model may be a model in the training process or a model which is not trained yet but is initialized, and the models are machine learning related models. The trained initialization model is used as a prediction model for subsequent oil consumption prediction, the attribute data of the excavator can be input through an input interface of the prediction model in the prediction process, and the prediction model outputs the predicted oil consumption of the excavator of the electronic injection type oil injection system after being processed.
After the predicted oil consumption is obtained, the predicted oil consumption is compared with the real-time oil consumption of the excavator of the electronic injection type oil injection system by the prediction model, and relevant parameters of the prediction model are adjusted by analyzing the difference between the predicted oil consumption and the real-time oil consumption, so that the correction of the prediction model is realized, and the prediction precision of the prediction model is further improved.
And step S104, taking the predicted oil consumption of the electric injection type oil injection system excavator which is corrected as the real-time oil consumption of the mechanical oil injection system excavator.
The real-time oil consumption is attribute data which can be directly acquired by the electric injection type oil injection system excavator, and the data is not possessed by the mechanical oil injection system excavator, so that the representation of the real-time oil consumption of the mechanical oil injection system excavator is realized in the step.
According to the prediction method for the oil consumption of the excavator, the oil consumption of the mechanical oil injection system excavator is predicted in real time by using the relevant prediction model, the electric injection system excavator with the same model is used as training data to be generalized to the excavator of the mechanical oil injection system, model correction is carried out by taking the actual oil filling amount and the real-time oil consumption uploaded by the electric injection system as errors, the accurate acquisition of the real-time oil consumption of the mechanical oil injection system excavator is realized, fitting can be carried out on the oil consumption under different engine rotating speeds with discrete changes, and the predictive maintenance scene of the abnormal oil consumption scene of the excavator is increased.
In some embodiments, the training process of the initialization model, as shown in fig. 2, includes:
step S201, obtaining model sample data; the model sample data is attribute data of an electric injection type oil injection system excavator of the same model as the mechanical oil injection system excavator.
The data of the model sample is not limited to the mechanical oil injection system excavator and the electric oil injection system excavator, and may include excavators different from the above two types. The diversification of model sample data is beneficial to improving the performance of the model, and during specific selection, an excavator which is different from a mechanical oil injection system excavator and an electronic injection type oil injection system excavator can be properly selected as negative sample data. In some embodiments, the attribute data of the electric injection type oil injection system excavator further includes: the method comprises the steps of main pump pressure, LS pressure, engine rotating speed, action codes and fuel temperature before and after an electronic injection type fuel injection system excavator.
Step S202, inputting model sample data into the initialized random forest model for training to obtain a first training result.
And the random forest model completes initialization operation, and when the first-layer regression training is carried out, the obtained related training result is used as a first training result for subsequent operation.
Step S203, the first training result is respectively subjected to normalization calculation and zero value calculation to obtain a second training result.
And normalizing the first training result obtained in the step, wherein the result after the normalization processing is a parameter matrix, and the parameter matrix comprises a correlation coefficient matrix capable of reflecting the change of the oil consumption. And after the parameter matrix is obtained, carrying out zero value calculation on the parameter matrix. Specifically, the zero value calculation is the number of zero values in the statistical parameter matrix, which is combined with the first training result as the second training result.
Step S204, carrying out stacking regression calculation on the second training result by using a K-proximity algorithm to obtain temporary oil consumption prediction data; in the stacking regression calculation process, the real-time oil consumption and the temporary oil consumption prediction data of the excavator of the electronic injection type oil injection system are compared to obtain a first comparison result, and the first comparison result is used as a correction parameter of the initialization model.
And performing stacking regression calculation on the second training result through a K-nearest neighbor algorithm, selecting multiple groups of data under approximate conditions to predict the oil consumption, and in the stacking regression calculation process, comparing the real-time oil consumption of the excavator of the electronic injection type oil injection system with the temporary data of the predicted oil consumption to obtain a first comparison result, wherein the first comparison result is used as a correction parameter of the initialization model. Specifically, the real-time oil consumption calculated by the excavator of the electronic injection type oil injection system is mainly compared with the predicted oil consumption, and the comparison result is used as error data for initializing the learning and correcting parameters of the model.
And S205, calculating a loss value of the initialization model according to a preset loss function, and stopping training when the loss value meets a preset expected threshold value to obtain a prediction model.
The loss function is used as a key index in the process of initializing the model training, and the function form of the loss function directly influences the training progress and efficiency of the model. In a specific implementation process, the preset Loss function is an OHEM (Online Hard instance Mining) function and/or a CEL (Cross Entropy Loss) function.
The preset expected threshold value can also be training time or iteration times, if the training time of the model reaches the predicted expected threshold value time, the model training time is long enough, and at the moment, the training can be stopped to obtain a prediction model; the iteration times in the model training process can be used as the preset expected threshold times, the times of model training are represented to be enough, and the training can be stopped at the moment, so that the prediction model is obtained.
In some embodiments, before inputting model sample data into the initialized random forest model for training, as shown in fig. 3, the training process for initializing the model further includes:
and S301, performing relevance extraction on the model sample data by using a correlation coefficient matrix and a genetic algorithm to obtain a relevance result related to oil consumption change in the model sample data.
The method comprises the following steps of simplifying model sample data, and selecting relevant model sample data which can reflect oil consumption change most. And performing correlation calculation on the model sample data through a correlation coefficient matrix and a genetic algorithm, wherein in the specific implementation process, correlation calculation results can be arranged, and a plurality of attribute data meeting a preset threshold value are selected as correlation results.
And S302, combining the correlation result with the model sample data, wherein the combined result is used as new model sample data for training the initialization model.
After a plurality of correlation results related to oil consumption change are obtained, the correlation results can be combined with model sample data, the obtained combination results are used as new model sample data for training of an initialization model, and the availability of the model sample data is further improved.
In some embodiments, after the step of obtaining model sample data, as shown in fig. 4, the training process of initializing the model further includes:
and S401, acquiring the oil consumption standard of the excavator of the electronic injection type oil injection system according to the gear data, the model data, the engine model and the emission standard data in the attribute data.
The step is used as a mode for simplifying data, and model sample data are simplified through an oil consumption standard. Specifically, the oil consumption standard of the excavator of the electronic injection type oil injection system is obtained according to the gear data, the model data, the engine model and the emission standard data, and the obtained oil consumption standard is used as a judgment basis to simplify the model sample data.
And S402, taking the oil consumption reference of the excavator test data of the electronic injection type oil injection system as a filtering threshold reference, and filtering the oil consumption data of the model sample data to remove abnormal values.
The step can be regarded as a step of data cleaning, particularly, the model sample data is cleaned through the oil consumption standard, relevant data irrelevant to oil consumption change are reduced, and the interference of abnormal values to a training model is eliminated, so that the overall performance of the model is improved.
In some embodiments, the obtaining process of the correction parameter, as shown in fig. 5, further includes:
and step S501, acquiring the actual oil filling amount of the mechanical oil injection system excavator.
The acquisition of the correction parameters can be determined by the actual oil filling amount of the mechanical oil injection system excavator. When the mechanical fuel injection system excavator refuels, the actual fuel charge can be obtained, the actual fuel charge is compared with the temporary fuel consumption prediction data stored, and the comparison result is used as a correction parameter for the correction operation of the model.
And step S502, comparing the actual fuel charge of the mechanical fuel injection system excavator with the temporary fuel consumption prediction data to obtain a second comparison result, wherein the second comparison result is used as a correction parameter of the initialization model.
Compared with the first comparison result, the second comparison result has certain time delay, so that the second comparison result is used as a secondary correction, the first comparison result is used as a primary correction, and the two corrections are combined to further improve the correction effect.
In some embodiments, the initialization model and the trained prediction model are deployed in a cloud server.
The cloud server is provided with related data warehouses which are specially used for storing mined attribute data. Taking a prediction model with a cloud server as an example, a flowchart of another method for predicting oil consumption of an excavator is shown in fig. 6.
In the specific implementation process, static data, dynamic data and oil consumption data of the excavator are uploaded to a cloud server in real time through a sensor installed on the excavator and stored in a data warehouse.
The existing data in the data warehouse are extracted, the excavator parameters of the cloud big data warehouse, including the front and rear main pump pressure, the LS pressure, the engine rotating speed, the real-time oil consumption, the action code, the fuel oil temperature and other parameters, are subjected to attribute reduction, a coefficient matrix which can reflect the oil consumption change most, and the correlation of each attribute is calculated. And arranging and extracting a plurality of highest parameters according to the sizes to be used as a coefficient matrix.
And cleaning and filtering data in the data warehouse according to oil consumption standards of different gears, different types of engines, different engine models and the like, and recombining the cleaned and filtered excavator parameters to serve as data of model training. And taking parameters and combined parameters in the dynamic data and the oil consumption data of the excavator as effective sample data, and inputting the effective sample data into a Random-Forest model for first training. And carrying out normalization processing on the output result, and counting the number of zero values in the parameter matrix as the input of the second layer model. And selecting multiple groups of data under approximate conditions for oil consumption prediction through KNN regression. And in the calculation process, the real-time oil consumption calculated by the electronic fuel injection system is mainly compared with the predicted oil consumption, and the model is learned and corrected according to errors. The model is corrected again by adding the fuel supply amount as a secondary correction. The training data is input into the model data learning process and is repeatedly carried out until the model training reaches a target or the training time or the iteration number reaches a preset value, and the model learning process is stopped.
The trained model is deployed into a model library of the cloud platform, and the model can be subsequently called through data uploaded by an excavator terminal to be calculated in real time, so that the method is applied to oil stealing and leaking of the excavator, oil consumption fitting of the mechanical oil injection system excavator, predictive maintenance of abnormal oil consumption and the like.
According to the prediction method for the oil consumption of the excavator, the oil consumption of the mechanical oil injection system excavator is predicted in real time by using the relevant prediction model, the electric injection system excavator with the same model is used as training data to be generalized to the excavator of the mechanical oil injection system, model correction is carried out by taking the actual oil filling amount and the real-time oil consumption uploaded by the electric injection system as errors, the accurate acquisition of the real-time oil consumption of the mechanical oil injection system excavator is realized, fitting can be carried out on the discretely-changed oil consumption of different engines at different rotating speeds, starting and adjusting points of the constant power pump at different gears can be automatically calculated and divided, and the predictive maintenance scene of the abnormal oil consumption scene of the excavator is increased. Because the prediction model is deployed to the cloud platform, the model can be self-learned periodically, and the prediction accuracy is improved.
Corresponding to the above method embodiment, an embodiment of the present invention further provides a system for predicting oil consumption of an excavator, where the system is applied to a mechanical oil injection system excavator, and a schematic structural diagram of the system is shown in fig. 7, where the system includes:
the electronic injection type oil injection system excavator determining module 710 is used for determining an electronic injection type oil injection system excavator which has the same model as the mechanical oil injection system excavator according to the model of the mechanical oil injection system excavator;
the attribute data acquisition module 720 of the excavator of the electronic injection type oil injection system is used for acquiring the attribute data of the excavator of the electronic injection type oil injection system; the attribute data comprise real-time oil consumption of an excavator of the electronic injection type oil injection system;
the oil consumption prediction module 730 of the excavator of the electronic fuel injection system is used for inputting the attribute data into an initialization model in a preset model base to carry out model training, and taking the trained initialization model as a prediction model; the prediction model outputs the predicted oil consumption of the excavator of the electronic injection type oil injection system, and the predicted oil consumption is corrected by utilizing a loss function and real-time oil consumption;
and the oil consumption determining module 740 of the mechanical oil injection system excavator is used for taking the predicted oil consumption of the electric injection system excavator which is corrected as the real-time oil consumption of the mechanical oil injection system excavator.
The system for predicting the oil consumption of the excavator provided by the embodiment of the invention has the same technical characteristics as the method for predicting the oil consumption of the excavator provided by the embodiment, so that the same technical problems can be solved, and the same technical effects are achieved. For the sake of brevity, where not mentioned in the examples section, reference may be made to the corresponding matter in the preceding method examples.
The embodiment also provides an electronic device, a schematic structural diagram of which is shown in fig. 8, and the electronic device includes a processor 101 and a memory 102; the memory 102 is used for storing one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the method for predicting the oil consumption of the excavator.
The electronic device shown in fig. 8 further comprises a bus 103 and a communication interface 104, and the processor 101, the communication interface 104 and the memory 102 are connected through the bus 103.
The Memory 102 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Bus 103 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 8, but that does not indicate only one bus or one type of bus.
The communication interface 104 is configured to connect with at least one user terminal and other network units through a network interface, and send the packaged IPv4 message or IPv4 message to the user terminal through the network interface.
The processor 101 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 101. The Processor 101 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic blocks disclosed in the embodiments of the present disclosure may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present disclosure may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 102, and the processor 101 reads the information in the memory 102 and completes the steps of the method of the foregoing embodiment in combination with the hardware thereof.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps of the method of the foregoing embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention or a part thereof, which essentially contributes to the prior art, can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for predicting oil consumption of an excavator, wherein the method is applied to a mechanical oil injection system excavator, and is characterized by comprising the following steps:
determining an electronic injection type oil injection system excavator with the same model as the mechanical oil injection system excavator according to the model of the mechanical oil injection system excavator;
acquiring attribute data of the excavator of the electronic injection type oil injection system; the attribute data comprise the real-time oil consumption of the electronic injection type oil injection system excavator;
inputting the attribute data into an initialization model in a preset model library to carry out model training, and taking the trained initialization model as a prediction model; the prediction model outputs the predicted oil consumption of the electric injection type oil injection system excavator, and the predicted oil consumption is corrected by using a loss function and the real-time oil consumption;
and taking the corrected predicted oil consumption of the electronic injection type oil injection system excavator as the real-time oil consumption of the mechanical oil injection system excavator.
2. The method for predicting oil consumption of an excavator according to claim 1, wherein the training process of the initialization model includes:
obtaining model sample data; the model sample data is attribute data of an electronic injection type oil injection system excavator of the same model as the mechanical oil injection system excavator;
inputting the model sample data into an initialized random forest model for training to obtain a first training result;
respectively carrying out normalization calculation and zero value calculation on the first training result to obtain a second training result;
performing stacking regression calculation on the second training result by using a K-proximity algorithm to obtain temporary oil consumption prediction data; in the stacking regression calculation process, comparing the real-time oil consumption of the electronic injection type oil injection system excavator with the oil consumption prediction temporary data to obtain a first comparison result, wherein the first comparison result is used as a correction parameter of the initialization model;
and calculating a loss value of the initialization model according to a preset loss function, and stopping training when the loss value meets a preset expected threshold value to obtain the prediction model.
3. The method for predicting excavator oil consumption according to claim 2, wherein before inputting the model sample data into the initialized random forest model for training, the training process of the initialized model further comprises:
performing relevance extraction on the model sample data by using a correlation coefficient matrix and a genetic algorithm to obtain a relevance result related to oil consumption change in the model sample data;
and combining the correlation result with the model sample data, and using the combined result as new model sample data for training the initialization model.
4. The method for predicting excavator oil consumption according to claim 2, wherein after the step of obtaining model sample data, the training process for initializing the model further comprises:
acquiring the oil consumption standard of the excavator of the electronic injection type oil injection system according to the gear data, the model data, the engine model and the emission standard data in the attribute data;
and taking the oil consumption reference of the excavator test data of the electronic injection type oil injection system as a filtering threshold reference, and filtering the oil consumption data of the model sample data to remove an abnormal value.
5. The method for predicting excavator oil consumption according to claim 2, wherein the correcting the parameters further comprises:
acquiring the actual oil filling amount of the mechanical oil injection system excavator;
and comparing the actual fuel charge of the mechanical fuel injection system excavator with the temporary fuel consumption prediction data to obtain a second comparison result, wherein the second comparison result is used as a correction parameter of the initialization model.
6. The method of predicting oil consumption of an excavator according to claim 1, wherein the attribute data of the electric injection type oil injection system excavator further comprises: the electric injection type oil injection system excavator comprises front and rear main pump pressures, LS pressures, engine rotating speed, action codes and fuel oil temperature.
7. The method of claim 1, wherein the initialization model and the trained predictive model are deployed in a cloud server.
8. The utility model provides a prediction system of excavator oil consumption, the system is applied to mechanical type oil injection system excavator, its characterized in that, the system includes:
the electronic injection type oil injection system excavator determining module is used for determining an electronic injection type oil injection system excavator which is the same as the mechanical oil injection system excavator in model according to the model of the mechanical oil injection system excavator;
the electronic injection type oil injection system excavator attribute data acquisition module is used for acquiring attribute data of the electronic injection type oil injection system excavator; the attribute data comprise the real-time oil consumption of the electronic injection type oil injection system excavator;
the oil consumption prediction module of the electric injection type oil injection system excavator is used for inputting the attribute data into an initialization model in a preset model base to perform model training, and taking the trained initialization model as a prediction model; the prediction model outputs the predicted oil consumption of the electric injection type oil injection system excavator, and the predicted oil consumption is corrected by using a loss function and the real-time oil consumption;
and the oil consumption determining module is used for taking the predicted oil consumption of the electric injection type oil injection system excavator which is corrected as the real-time oil consumption of the mechanical oil injection system excavator.
9. An electronic device, comprising: a processor and a storage device; the storage device has stored thereon a computer program which, when executed by the processor, performs the steps of the method of predicting excavator oil consumption of any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, where the computer program is executed by a processor to perform the steps of the method for predicting excavator oil consumption according to any one of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011068500.0A CN112163299B (en) | 2020-09-30 | 2020-09-30 | Method and system for predicting oil consumption of excavator and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011068500.0A CN112163299B (en) | 2020-09-30 | 2020-09-30 | Method and system for predicting oil consumption of excavator and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112163299A true CN112163299A (en) | 2021-01-01 |
| CN112163299B CN112163299B (en) | 2023-05-02 |
Family
ID=73861052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011068500.0A Active CN112163299B (en) | 2020-09-30 | 2020-09-30 | Method and system for predicting oil consumption of excavator and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163299B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113360270A (en) * | 2021-06-30 | 2021-09-07 | 杭州数梦工场科技有限公司 | Data cleaning task processing method and device |
| CN113673815A (en) * | 2021-07-08 | 2021-11-19 | 三一智矿科技有限公司 | Mine car scheduling method and device based on vehicle data processing |
| CN114626634A (en) * | 2022-04-01 | 2022-06-14 | 三一重工股份有限公司 | Method and device for mining oil consumption optimization strategy, electronic equipment, medium and chip |
| CN116644865A (en) * | 2023-07-27 | 2023-08-25 | 中汽信息科技(天津)有限公司 | Commercial vehicle fuel consumption prediction method, electronic equipment and storage medium |
| CN116882755A (en) * | 2023-07-28 | 2023-10-13 | 鱼快创领智能科技(南京)有限公司 | Method for predicting oil theft risk of trucking route based on vehicle-mounted Tbox data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106989788A (en) * | 2017-04-17 | 2017-07-28 | 徐州徐工挖掘机械有限公司 | A kind of BBG hydraulic crawler excavator fuel consumption test system and its method |
| CN109208687A (en) * | 2018-10-30 | 2019-01-15 | 柳州柳工挖掘机有限公司 | It is a kind of for obtaining the method and system of excavator fuel efficiency |
| CN109636951A (en) * | 2018-11-21 | 2019-04-16 | 中南大学 | A kind of excavator energy consumption analysis method based on working stage identification |
| CN111549849A (en) * | 2020-05-19 | 2020-08-18 | 三一重机有限公司 | Control method and device of excavator |
-
2020
- 2020-09-30 CN CN202011068500.0A patent/CN112163299B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106989788A (en) * | 2017-04-17 | 2017-07-28 | 徐州徐工挖掘机械有限公司 | A kind of BBG hydraulic crawler excavator fuel consumption test system and its method |
| CN109208687A (en) * | 2018-10-30 | 2019-01-15 | 柳州柳工挖掘机有限公司 | It is a kind of for obtaining the method and system of excavator fuel efficiency |
| CN109636951A (en) * | 2018-11-21 | 2019-04-16 | 中南大学 | A kind of excavator energy consumption analysis method based on working stage identification |
| CN111549849A (en) * | 2020-05-19 | 2020-08-18 | 三一重机有限公司 | Control method and device of excavator |
Non-Patent Citations (2)
| Title |
|---|
| YUPENG SHI 等: "Intelligent identification for working-cycle stages of excavator based on main pump pressure" * |
| 张庆洪 等: "基于改进RBF径向基神经网络的车载油耗软测量" * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113360270A (en) * | 2021-06-30 | 2021-09-07 | 杭州数梦工场科技有限公司 | Data cleaning task processing method and device |
| CN113360270B (en) * | 2021-06-30 | 2024-02-27 | 杭州数梦工场科技有限公司 | Data cleaning task processing method and device |
| CN113673815A (en) * | 2021-07-08 | 2021-11-19 | 三一智矿科技有限公司 | Mine car scheduling method and device based on vehicle data processing |
| CN114626634A (en) * | 2022-04-01 | 2022-06-14 | 三一重工股份有限公司 | Method and device for mining oil consumption optimization strategy, electronic equipment, medium and chip |
| CN116644865A (en) * | 2023-07-27 | 2023-08-25 | 中汽信息科技(天津)有限公司 | Commercial vehicle fuel consumption prediction method, electronic equipment and storage medium |
| CN116644865B (en) * | 2023-07-27 | 2023-10-20 | 中汽信息科技(天津)有限公司 | Commercial vehicle fuel consumption prediction method, electronic equipment and storage medium |
| CN116882755A (en) * | 2023-07-28 | 2023-10-13 | 鱼快创领智能科技(南京)有限公司 | Method for predicting oil theft risk of trucking route based on vehicle-mounted Tbox data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112163299B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112163299A (en) | Excavator oil consumption prediction method and system and electronic equipment | |
| CN109213476B (en) | Installation package generation method, computer readable storage medium and terminal equipment | |
| US20190220924A1 (en) | Method and device for determining key variable in model | |
| JP2016218961A (en) | Abnormality sign diagnosis device and abnormality sign diagnosis method | |
| Vasicek | Relaxed equivalence checking: a new challenge in logic synthesis | |
| CN115795928A (en) | Accelerated degradation test data processing method and device based on gamma process | |
| CN117667932A (en) | Method and system for customizing and converting storage format of vector database | |
| CN110866682B (en) | Underground cable early warning method and device based on historical data | |
| CN115129706B (en) | Soil moisture observation data quality evaluation method considering periodic characteristics | |
| CN112214854A (en) | Excavator oil consumption prediction method and system and electronic equipment | |
| CN111210105B (en) | Continuous operation performance verification, apparatus, computer device, and storage medium | |
| CN106777981B (en) | Behavior data verification method and device | |
| CN111159776A (en) | Self-adaptive neural network model verification method and system | |
| CN113872978B (en) | DNS hijacking monitoring method and device and electronic equipment | |
| CN111382185B (en) | Method for counting and applying mobile phone numbers by adopting partition positioning | |
| CN113194039B (en) | Method and device for segmenting system data flow, electronic equipment and storage medium | |
| CN113743532B (en) | Abnormality detection method, abnormality detection device, abnormality detection apparatus, and computer storage medium | |
| CN113704964B (en) | Route design method and device for whole vehicle reliability test and computer equipment | |
| CN116862135B (en) | Mechanical equipment maintenance analysis method and system and electronic equipment | |
| CN117971547B (en) | Memory fault prediction method, device, equipment, storage medium and program product | |
| CN117851397A (en) | Data quality detection method, device, equipment and storage medium | |
| CN115356949A (en) | System and method for maintaining consistency of digital twin model | |
| CN116824109A (en) | Grid deformation method, device, equipment and medium based on interpolation sequence reduction | |
| CN115330924A (en) | Rendering method and device of full liquid crystal instrument and computer equipment | |
| CN116992221A (en) | Fault detection method, device and equipment of operation and maintenance platform 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |