CN116522758A - Engineering machinery power consumption optimization method and device - Google Patents
Engineering machinery power consumption optimization method and device Download PDFInfo
- Publication number
- CN116522758A CN116522758A CN202310325271.3A CN202310325271A CN116522758A CN 116522758 A CN116522758 A CN 116522758A CN 202310325271 A CN202310325271 A CN 202310325271A CN 116522758 A CN116522758 A CN 116522758A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- information source
- source data
- data
- working
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000005070 sampling Methods 0.000 claims abstract description 32
- 238000012216 screening Methods 0.000 claims abstract description 30
- 230000005611 electricity Effects 0.000 claims description 30
- 238000000605 extraction Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 230000001502 supplementing effect Effects 0.000 claims description 7
- 230000000153 supplemental effect Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 24
- 230000008901 benefit Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Manufacturing & Machinery (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Geometry (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of engineering machinery energy consumption control, in particular to an engineering machinery power consumption optimization method and device, wherein the method comprises the following steps: acquiring a plurality of information source data of engineering machinery in operation, sampling parameters corresponding to each information source data and acquisition power consumption; determining a plurality of working phases of the engineering machine; classifying each information source data in a corresponding working stage; dividing a plurality of subdivision working conditions in each working stage; screening key features from a plurality of source types; obtaining an optimization strategy of key features from the information source data according to a preset optimization method; and optimizing the execution strategy of the key features in each subdivision working condition according to the optimization strategy. When the power consumption optimizing method is used, the power consumption optimizing effect of key features can be carried out on a large number of subdivision working conditions when the engineering machinery performs work, and the optimized working conditions can be covered more comprehensively.
Description
Technical Field
The application relates to the technical field of engineering machinery energy consumption control, in particular to an engineering machinery power consumption optimization method and device.
Background
The development of the engineering machinery industry plays a significant role in the domestic economic development, and in recent years, along with the strong promotion of the national energy conservation and emission reduction work, the engineering machinery industry also makes great progress, but how to better improve the use efficiency of the engineering machinery and reduce the energy consumption of the engineering machinery in operation is still a key problem to be solved in the development process of the industry.
In face of the current development status of the domestic engineering machinery industry and the urgent demands of users for energy conservation and emission reduction, domestic engineering machinery manufacturers and related research institutions are also continuously struggling to explore.
At present, few researches on engineering machinery are carried out by some domestic factories and institutions in the aspect of power consumption optimization, and the power consumption optimization is mainly focused on the field of automobiles. How to research a power consumption optimizing method aiming at engineering machinery, thereby reducing the power consumption of the engineering machinery under various working conditions is a technical problem to be solved in the field.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for optimizing power consumption of an engineering machine, which can optimize power consumption of the engineering machine and reduce power consumption of the engineering machine under various working conditions.
In a first aspect, the present application provides a power consumption optimization method for an engineering machine, including: acquiring a plurality of information source data of engineering machinery in operation, sampling parameters corresponding to the information source data and acquisition power consumption; determining a plurality of working stages of the engineering machinery according to the vehicle-to-machine data of the engineering machinery; classifying each information source data into the corresponding working phase according to the sampling parameters and the vehicle-to-machine data; dividing a plurality of subdivision working conditions in each working stage according to the information source data contained in each working stage; according to the information source data and the acquisition power consumption, key features are screened from a plurality of information source types based on a preset feature screening algorithm; obtaining an optimization strategy of the key features from the information source data according to a preset optimization method; and optimizing the execution strategy of the key features in each subdivision working condition according to the optimization strategy.
When the system is used, a plurality of working stages are subdivided according to the acquired information source data, sampling parameters and acquisition power consumption, so that a large number of fine working conditions are covered. And then screening out key features with high power consumption, and obtaining an optimization strategy corresponding to the key features from the information source data, and optimizing the power consumption of the key features according to the optimization strategy. According to the method, when the engineering machinery executes work, the power consumption of key features of a large number of subdivision working conditions can be optimized, the power consumption optimizing effect is remarkably improved, and the optimized working conditions can be covered more comprehensively.
With reference to the first aspect, in one possible implementation manner, the obtaining a plurality of source data of the engineering machine during operation, and obtaining sampling parameters and collecting power consumption corresponding to each of the source data include: acquiring sampling time data corresponding to the information source data; and performing time alignment on the plurality of sampling time data to obtain the sampling parameters corresponding to the information source data.
With reference to the first aspect, in a possible implementation manner, the dividing a plurality of subdivision operating conditions in each working phase according to the source data included in each working phase includes: invoking a preset corresponding relation between the information source data and the subdivision working condition; and in each working stage, based on the preset corresponding relation, obtaining the subdivision working conditions contained in the working stage according to the acquired information source data.
With reference to the first aspect, in one possible implementation manner, the selecting, according to the source data and the collected power consumption, key features from a plurality of source types based on a preset feature screening algorithm includes: obtaining electromechanical equipment parameters of the engineering machinery according to the vehicle-to-machine data; according to the information source data and the electromechanical equipment parameters, an initial electricity consumption prediction model of the engineering machinery is established, and the initial electricity consumption prediction model is trained to obtain the electricity consumption prediction model of the engineering machinery; and screening key features based on the electricity consumption prediction model.
With reference to the first aspect, in one possible implementation manner, the establishing an initial power consumption prediction model of the engineering machine according to the information source data and the electromechanical device parameters, and training the initial power consumption prediction model to obtain the power consumption prediction model of the engineering machine includes: extracting a part of the information source data, and combining the electromechanical equipment parameters to build and start training the initial power consumption prediction model; invoking a test set of the initial electricity consumption prediction model; inputting a part of the information source data into the test set to obtain predicted power consumption; and if the average absolute percentage error of the predicted power consumption and the collected power consumption accords with a preset error, finishing training and obtaining the power consumption prediction model.
With reference to the first aspect, in one possible implementation manner, the training to obtain the power consumption prediction model of the engineering machine according to the source data and the electromechanical device parameters further includes: and if the average absolute percentage error of the predicted power consumption and the acquired power consumption does not accord with a preset error, supplementing and extracting the information source data to continuously train the power consumption prediction model.
With reference to the first aspect, in a possible implementation manner, after the extracting the source data to continue training the electricity consumption prediction model, the method further includes: if the data quantity of the information source data subjected to supplementary extraction exceeds the preset extraction data quantity, stopping supplementary extraction; or stopping the supplementary extraction if the duration of the supplementary extraction exceeds the preset extraction duration.
With reference to the first aspect, in one possible implementation manner, the selecting, according to the source data and the collected power consumption, key features from a plurality of source types based on a preset feature screening algorithm includes: according to the information source data and the acquired power consumption, obtaining the power consumption correlation degree of each information source type based on a correlation degree algorithm; and if the power consumption correlation degree of the information source type accords with a preset correlation degree, taking the information source type as the key characteristic.
With reference to the first aspect, in one possible implementation manner, the deriving, according to a preset optimization method, the optimization policy of the key feature from the source data includes: in each subdivision working condition, if the acquired power consumption accords with a preset power consumption range corresponding to the corresponding information source type, taking the information source data corresponding to the acquired power consumption as optimization data; wherein, the executing strategy for optimizing the key features in each subdivision working condition according to the optimizing strategy comprises: and taking the optimized data as target execution data of the engineering machinery in the subdivision working condition when executing the work.
In a second aspect, the present application provides an apparatus for optimizing power consumption of a construction machine, including: the data acquisition module is configured to: acquiring a plurality of information source data of engineering machinery during working, and acquiring sampling parameters and acquisition power consumption corresponding to each information source data; the working condition dividing module is in communication connection with the data acquisition module and is configured to: obtaining a plurality of corresponding working stages according to the vehicle-machine data of the engineering machinery; classifying each information source data into the corresponding working phase according to the sampling parameters and the vehicle-to-machine data; dividing a plurality of subdivision working conditions in each working stage according to the information source data contained in each working stage; the key feature screening module is in communication connection with the data acquisition module and is configured to: according to the information source data and the acquisition power consumption, key features are screened from a plurality of information source types based on a preset feature screening algorithm; the strategy optimization module is respectively in communication connection with the working condition dividing module and the key feature screening module, and is configured to: obtaining an optimization strategy of the key features from the information source data according to a preset optimization method; and optimizing the execution strategy of the key features in each subdivision working condition according to the optimization strategy.
The second aspect is an apparatus corresponding to the first aspect, and technical effects of the second aspect are not described herein.
Drawings
Fig. 1 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to an embodiment of the present application.
Fig. 2 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
Fig. 3 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
Fig. 4 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
Fig. 5 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
Fig. 6 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
Fig. 7 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
Fig. 8 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
Fig. 9 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application.
FIG. 10 is a schematic flow chart of the present application using model predictive screening key features, for example, optimizing an accelerator pedal and optimizing a brake pedal.
Fig. 11 is a schematic diagram of a strategy optimization scheme using an accelerator pedal as an example.
FIG. 12 is a schematic flow chart of the present application using a correlation algorithm to screen key features, such as optimizing an accelerator pedal and optimizing a brake pedal.
Fig. 13 is a schematic structural diagram of an electricity consumption optimizing device for engineering machinery according to an embodiment of the present disclosure.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
An exemplary engineering machine power consumption optimization method is as follows:
fig. 1 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to an embodiment of the present application. The application provides a power consumption optimization method of engineering machinery, in an embodiment, as shown in fig. 1, the method includes:
step 110, acquiring a plurality of information source data of the engineering machinery during operation, and acquiring sampling parameters and acquisition power consumption corresponding to each information source data.
In the step, when the engineering machinery executes work, various work data of the engineering machinery are collected as information source data. Specifically, for example, when the engineering machinery is a pure electric front crane, the following information source types of the pure electric front crane are collected: and the signal data such as load, forward travel, speed, motor rotation speed, motor torque, accelerator pedal opening, brake pedal opening and the like. And, also gather the sampling parameter that each information source data corresponds, sampling parameter can include collection time, collection frequency etc.. The power consumption is the power consumption corresponding to each information source data, for example, the power consumption corresponding to the 2 ton load is collected as a collected power consumption value, and for example, the power consumption corresponding to the 30% accelerator pedal opening is collected as a collected power consumption value.
Step 120, determining a plurality of working stages of the engineering machine according to the vehicle-mounted data of the engineering machine.
In this step, the type of the construction machine can be known from the vehicle-mounted data of the construction machine, and the working stage of the construction machine can be known. For example, when the construction machine is a purely electric overhead crane, the plurality of working phases may include: a low-speed driving stage, a medium-speed driving stage, a high-speed driving stage, a lifting stage, a braking stage, a constant speed distance and a long time, a deceleration distance and the like; for example, when the work machine is an electric-only excavator, the plurality of work phases may include: a low-speed driving stage, a medium-speed driving stage, a high-speed driving stage, a braking stage, an excavating stage, a bucket lifting stage and the like; . Specifically, the corresponding relationship between the vehicle-mounted data and the working phases may be preset, and different vehicle-mounted data correspond to different working phases, i.e. different engineering machines correspond to different working phases.
And 130, classifying each information source data into corresponding working phases according to the sampling parameters and the vehicle-mounted data.
In the step, the sampling parameters and the vehicle-mounted data are mutually aligned in time, so that the working stage of each information source data can be known, and the information source data can be classified in the working stage.
And 140, dividing a plurality of subdivision working conditions in each working stage according to the information source data contained in each working stage.
In the step, the working phases are further classified and divided to obtain more finer subdivision working conditions, so that more working condition phases of the engineering machinery can be covered, and the power consumption can be optimized more finely during power optimization later. Specifically, the data range may be set in advance in each working phase to divide the subdivision working condition, for example, in the low-speed driving phase, the source data of 1km/h to 3km/h is divided into a subdivision working condition, and the subdivision working condition is divided into a fine working condition of 3km/h to 5km/h, which is the same.
And 150, screening key features from a plurality of information source types based on a preset feature screening algorithm according to the information source data and the acquired power consumption.
In this step, key features are obtained through screening by a preset algorithm, and the key features can be defined as the source type with high power consumption. The judging thresholds of the high power consumption of different source types can be different from each other.
Step 160, obtaining an optimization strategy of the key features from the information source data according to a preset optimization method.
In the step, by presetting an optimization screening method, the information source data with excellent power consumption corresponding to the key characteristics is screened from the information source data according to the key characteristics in each subdivision working condition, and the screened excellent information source data is used as the basis to obtain an optimization strategy.
Step 170, optimizing the execution strategy of the key features in each subdivision working condition according to the optimization strategy.
In the step, aiming at the information source type corresponding to the key characteristics in each subdivision working condition, an optimization strategy is adopted to optimize the information source type to obtain an execution strategy, and the engineering machinery can execute work based on the execution strategy, so that power consumption optimization is realized. If the key features to be optimized exist, after a plurality of execution strategies corresponding to the key features are obtained, the execution strategies are fused and applied for optimizing the power consumption of the engineering machinery.
When the embodiment is applied, a plurality of working stages are subdivided according to the acquired information source data, sampling parameters and acquisition power consumption, so that a large number of fine working conditions are covered. And then screening out key features with high power consumption, and obtaining an optimization strategy corresponding to the key features from the information source data, and optimizing the power consumption of the key features according to the optimization strategy. According to the power consumption optimization method and device, when engineering machinery executes work, power consumption optimization of key characteristics is carried out on a large number of subdivision working conditions, the power consumption optimization effect is remarkably improved, and the optimized working conditions can be covered more comprehensively.
Fig. 2 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in FIG. 2, step 110 includes:
and 111, acquiring sampling time data corresponding to the information source data.
And 112, performing time alignment on the plurality of sampling time data to obtain sampling parameters corresponding to each information source data.
According to the embodiment, after time alignment is carried out on the sampling time data of the information source data, time axes of all the information source data can be unified, and sampling parameters including time parameters are recorded after time alignment, so that the information source data can be accurately divided into corresponding working phases according to the sampling parameters.
Fig. 3 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in FIG. 3, step 140 includes:
step 141, calling a preset corresponding relation between the information source data and the subdivision working condition.
And 142, in each working stage, based on a preset corresponding relation, obtaining subdivision working conditions contained in the working stage according to the acquired information source data.
The embodiment is used for further working condition subdivision in the working phase, for example, in the low-speed driving phase, the information source data of 1 km/h-3 km/h are preset to be divided into a subdivision working condition, and the information source data of 3 km/h-5 km/h are preset to be divided into a fine working condition. After the preset corresponding relation is called, a plurality of subdivision working conditions can be divided for each information source type in each working stage.
Fig. 4 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in FIG. 4, step 150 comprises:
and 151, obtaining electromechanical equipment parameters of the engineering machinery according to the vehicle-to-machine data.
In this step, the electromechanical device parameters are mechanical parameters of each working mechanism of the engineering machinery during working, for example, when the pure electric front crane performs lifting work, the electromechanical device parameters include the length of the boom, the length of the cylinder, the strength of the cylinder, and the like.
And 152, establishing an initial power consumption prediction model of the engineering machinery according to the information source data and the electromechanical equipment parameters, and training the initial power consumption prediction model to obtain the power consumption prediction model of the engineering machinery.
In the step, the power consumption prediction model can be trained by adopting a model building method common in the field through information source data and electromechanical equipment parameters and building a simulation model of the pure electric front crane according to the electromechanical equipment parameters and then importing the information source data serving as input data of the simulation model into the simulation model, and the output of the power consumption prediction model is the predicted power consumption.
And step 153, screening key features based on the electricity consumption prediction model.
In this step, the key features are screened from the electricity consumption prediction model by using a common feature screening method, for example, a random forest classifier or GBDT (Gradient Boosting Decision Tree, gradient lifting tree) is used for feature screening.
Fig. 5 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in FIG. 5, step 152 includes:
step 1521, extracting a part of information source data, and combining with the electromechanical device parameters to build and start training an initial power consumption prediction model.
Step 1522, calling a test set of the initial electricity consumption prediction model.
Step 1523, inputting a part of information source data into the test set to obtain the predicted power consumption.
And judging whether the average absolute percentage error (MAPE, mean Absolute Percentage Error) of the predicted power consumption and the collected power consumption accords with a preset error, if so, executing step 1524, and finishing training to obtain a power consumption prediction model.
In this embodiment, a part of data is extracted from the source data and input into the electricity consumption prediction model for model training, and a part of input test set is also extracted from the source data for testing. In this embodiment, average absolute percentage errors of predicted power consumption and collected power consumption corresponding to each information source type are compared, and if the average absolute percentage error of all the information source types can be lower than a preset error, the power consumption prediction model training is successful.
Fig. 6 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in fig. 6, step 152 further includes:
and judging whether the average absolute percentage error of the predicted power consumption and the acquired power consumption accords with a preset error, if not, executing step 1525, and additionally extracting information source data to continue training the power consumption prediction model.
When the embodiment is used, if the average absolute percentage error corresponding to one or more information source types does not accord with the preset error, the fact that the electricity consumption prediction model is not sufficiently trained is indicated, and then supplementary extraction is carried out from information source data so as to further train the electricity consumption prediction model.
Fig. 7 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in fig. 7, after step 1525, the power consumption optimization method of the construction machine further includes:
and judging whether the data quantity of the source data of the supplementary extraction exceeds the preset extraction data quantity, and if so, executing step 1526 to stop the supplementary extraction.
After step 1525, or whether the duration of the supplementary extraction exceeds the preset extraction duration is determined, if so, step 1526 is executed to stop the supplementary extraction.
When the method is applied, the data amount of the information source data for training the electricity consumption prediction model is limited so as to avoid introducing excessive information source data, and the training effect of the electricity consumption prediction model is affected by the excessive information source data.
Fig. 8 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in FIG. 8, step 150 comprises:
and 154, obtaining the power consumption correlation degree of each information source type based on a correlation algorithm according to the information source data and the acquired power consumption.
And judging whether the power consumption relativity of the information source type accords with the preset relativity, if so, executing step 155, and taking the information source type as a key characteristic.
When the method is used, key features are screened in a mode of correlation algorithm instead of a mode of building a power consumption prediction model through training. Specifically, for each information source type, information source data corresponding to the information source type and acquisition power consumption are counted, and a change curve of the acquisition power consumption along with the change of the information source data is obtained. For example, as the value of the source data of a certain type increases, the collected electricity consumption variation exceeds a preset value, and the electricity consumption correlation of the source type is determined to accord with the preset correlation. Specifically, taking the source type of the accelerator pedal opening as an example, if the variation of the collected power consumption exceeds a preset value corresponding to the accelerator pedal opening along with the increase of the accelerator pedal opening, taking the accelerator pedal opening as a key feature; for example, taking the information source type of the opening degree of the brake pedal as an example, if the variation of the collected electricity consumption exceeds the preset value corresponding to the opening degree of the brake pedal along with the increase of the opening degree of the brake pedal, the opening degree of the brake pedal is also taken as a key feature.
Fig. 9 is a schematic diagram of method steps of a power consumption optimization method for an engineering machine according to another embodiment of the present application. In one embodiment, as shown in FIG. 9, step 160 includes:
and in each subdivision working condition, judging whether the acquired power consumption accords with a preset power consumption range corresponding to the corresponding information source type, if so, executing step 161, and taking the information source data corresponding to the acquired power consumption as optimization data.
Wherein step 170 comprises:
and 171, taking the optimized data as target execution data of the engineering machinery in the subdivision working condition when executing the work.
When the method is applied, the power consumption data which accords with the preset power consumption range are collected in the collected power consumption data corresponding to the key characteristics of the subdivision working conditions through quantitative analysis, and the fact that the power consumption accords with the preset power consumption range indicates that the power consumption of the collected power consumption is low is achieved, and the corresponding energy data can improve the endurance of the engineering machinery. And taking the acquired power consumption which accords with the preset power consumption range as the reference, selecting the information source data corresponding to the acquired power consumption as the optimization data, and executing the work by adopting the optimization data when the engineering machinery executes the work, so that the power consumption optimization can be realized for each subdivision working condition. For example, in the subdivision working conditions with the running speed of 1km/h to 3km/h, the collected electricity consumption corresponding to the accelerator pedal opening with the opening degree of 30% is screened to be in accordance with the preset electricity consumption range, and the engineering machinery is controlled to adjust the accelerator pedal opening degree in the subdivision working conditions of 1km/h to 3km/h to be 30% so as to work.
Referring to fig. 10, fig. 10 is a schematic flow chart of the present application using model predictive screening key features, for example, optimizing an accelerator pedal and optimizing a brake pedal. After the method starts to be executed, data acquisition is carried out, time alignment is carried out, working phase division and subdivision working condition division are then carried out, a plurality of information source data trained electricity consumption prediction models are extracted, training is finished and key characteristics are screened when the test set MAPE reaches the standard, and the extracted information source data are supplemented to train the models if the test set MAPE does not reach the standard. And when the source data is extracted in a supplementing mode, if the data quantity exceeds the standard or the supplementing time exceeds the standard, the supplementing extraction is not performed, and if the data quantity does not exceed the standard or the supplementing time does not exceed the standard, the supplementing extraction is continued. And then optimizing the accelerator pedal and the brake pedal respectively, and finally fusing and applying the optimization strategy of the accelerator pedal and the optimization strategy of the brake pedal.
Fig. 11 is a schematic diagram of a strategy optimization scheme using an accelerator pedal as an example. After the execution is started, dividing working stages and subdivision working conditions based on the load, the rising distance, the driving distance, the accelerating distance and time length, the uniform speed distance and time length and the decelerating distance and time length, quantitatively analyzing the relation between the accelerator pedal opening and the electricity consumption aiming at a certain subdivision working condition, taking the accelerator pedal opening data which accords with the preset electricity consumption range as the optimal accelerator pedal opening, and obtaining the optimization strategy of the accelerator pedal opening. In the process, the optimal accelerator pedal opening degree of a plurality of subdivision working conditions is calculated so as to cover all subdivision working conditions, and an optimization strategy of all subdivision working conditions is obtained. If all the subdivision working conditions are not covered, quantitative analysis is continuously carried out on a certain uncovered subdivision working condition, and if all the subdivision working conditions are covered, optimization strategy output, fusion and application corresponding to all the subdivision working conditions are output.
Referring to fig. 12, fig. 12 is a schematic flow chart of the present application for optimizing an accelerator pedal and optimizing a brake pedal using a correlation algorithm to screen key features. After the method is started to be executed, data acquisition is carried out, time alignment is carried out, working phase division and subdivision working condition division are carried out, key features are screened based on a correlation algorithm, the accelerator pedal and the brake pedal are optimized respectively, and finally an optimization strategy of the accelerator pedal and an optimization strategy of the brake pedal are fused and applied to each other.
An exemplary power consumption optimization device for a construction machine is as follows:
fig. 13 is a schematic structural diagram of an electricity consumption optimizing device for engineering machinery according to an embodiment of the present disclosure. The application also provides a power consumption optimizing device of engineering machinery, as shown in fig. 13, the device comprises: the system comprises a data acquisition module 101, a working condition division module 102, a key feature screening module 103 and a strategy optimization module 104. The data acquisition module 101 is configured to: and acquiring a plurality of information source data of the engineering machinery during working, and acquiring sampling parameters and acquisition power consumption corresponding to each information source data. The working condition dividing module 102 is in communication connection with the data acquisition module 101, and the working condition dividing module 102 is configured to: obtaining a plurality of corresponding working stages according to the vehicle-machine data of the engineering machinery; classifying each information source data into corresponding working stages according to the sampling parameters and the vehicle-mounted data; and dividing a plurality of subdivision working conditions in each working stage according to the information source data contained in each working stage. The key feature screening module 103 is communicatively connected to the data acquisition module 101, the key feature screening module 103 being configured to: and screening key features from the plurality of information source types based on a preset feature screening algorithm according to the information source data and the acquisition power consumption. The policy optimization module 104 is in communication connection with the working condition dividing module 102 and the key feature screening module 103, and the policy optimization module 104 is configured to: obtaining an optimization strategy of key features from the information source data according to a preset optimization method; and optimizing the execution strategy of the key features in each subdivision working condition according to the optimization strategy.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not intended to be limited to the details disclosed herein as such.
The block diagrams of the devices, apparatuses, devices, systems referred to in this application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent to the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. The power consumption optimizing method for engineering machinery is characterized by comprising the following steps:
acquiring a plurality of information source data of engineering machinery in operation, sampling parameters corresponding to the information source data and acquisition power consumption;
determining a plurality of working stages of the engineering machinery according to the vehicle-to-machine data of the engineering machinery;
classifying each information source data into the corresponding working phase according to the sampling parameters and the vehicle-to-machine data;
dividing a plurality of subdivision working conditions in each working stage according to the information source data contained in each working stage;
according to the information source data and the acquisition power consumption, key features are screened from a plurality of information source types based on a preset feature screening algorithm;
obtaining an optimization strategy of the key features from the information source data according to a preset optimization method; and
and optimizing the execution strategy of the key features in each subdivision working condition according to the optimization strategy.
2. The method for optimizing power consumption of a construction machine according to claim 1, wherein the steps of obtaining a plurality of source data of the construction machine during operation, and obtaining sampling parameters and collecting power consumption corresponding to each of the source data include:
acquiring sampling time data corresponding to the information source data; and
and performing time alignment on the plurality of sampling time data to obtain the sampling parameters corresponding to the information source data.
3. The power consumption optimization method of construction machine according to claim 1, wherein the dividing the plurality of subdivision conditions in each of the working phases according to the source data included in each of the working phases comprises:
invoking a preset corresponding relation between the information source data and the subdivision working condition; and
and in each working stage, based on the preset corresponding relation, obtaining the subdivision working conditions contained in the working stage according to the acquired information source data.
4. The method for optimizing power consumption of an engineering machine according to claim 1, wherein the selecting key features from a plurality of source types based on a preset feature selection algorithm according to the source data and the collected power consumption comprises:
obtaining electromechanical equipment parameters of the engineering machinery according to the vehicle-to-machine data;
according to the information source data and the electromechanical equipment parameters, an initial electricity consumption prediction model of the engineering machinery is established, and the initial electricity consumption prediction model is trained to obtain the electricity consumption prediction model of the engineering machinery; and
and screening key characteristics based on the electricity consumption prediction model.
5. The method for optimizing power consumption of a construction machine according to claim 4, wherein the establishing an initial power consumption prediction model of the construction machine according to the source data and the electromechanical device parameters, and training the initial power consumption prediction model to obtain the power consumption prediction model of the construction machine comprises:
extracting a part of the information source data, and combining the electromechanical equipment parameters to build and start training the initial power consumption prediction model;
invoking a test set of the initial electricity consumption prediction model;
inputting a part of the information source data into the test set to obtain predicted power consumption; and
and if the average absolute percentage error of the predicted power consumption and the collected power consumption accords with a preset error, finishing training and obtaining the power consumption prediction model.
6. The method for optimizing power consumption of a construction machine according to claim 5, wherein training the power consumption prediction model of the construction machine according to the information source data and the electromechanical device parameters further comprises:
and if the average absolute percentage error of the predicted power consumption and the acquired power consumption does not accord with a preset error, supplementing and extracting the information source data to continuously train the power consumption prediction model.
7. The method of optimizing power consumption of a work machine of claim 6, wherein after the supplemental extraction of the source data to continue training the power consumption prediction model, the method further comprises:
if the data quantity of the information source data subjected to supplementary extraction exceeds the preset extraction data quantity, stopping supplementary extraction; or alternatively
And stopping the supplementary extraction if the duration of the supplementary extraction exceeds the preset extraction duration.
8. The method for optimizing power consumption of an engineering machine according to claim 1, wherein the selecting key features from a plurality of source types based on a preset feature selection algorithm according to the source data and the collected power consumption comprises:
according to the information source data and the acquired power consumption, obtaining the power consumption correlation degree of each information source type based on a correlation degree algorithm; and
and if the power consumption correlation degree of the information source type accords with a preset correlation degree, taking the information source type as the key characteristic.
9. The power consumption optimization method of engineering machinery according to claim 1, wherein the deriving the optimization strategy of the key feature from the source data according to the preset optimization method comprises:
in each subdivision working condition, if the acquired power consumption accords with a preset power consumption range corresponding to the corresponding information source type, taking the information source data corresponding to the acquired power consumption as optimization data;
wherein, the executing strategy for optimizing the key features in each subdivision working condition according to the optimizing strategy comprises:
and taking the optimized data as target execution data of the engineering machinery in the subdivision working condition when executing the work.
10. An electricity consumption optimizing device for construction machinery, comprising:
the data acquisition module is configured to: acquiring a plurality of information source data of engineering machinery during working, and acquiring sampling parameters and acquisition power consumption corresponding to each information source data;
the working condition dividing module is in communication connection with the data acquisition module and is configured to: obtaining a plurality of corresponding working stages according to the vehicle-machine data of the engineering machinery; classifying each information source data into the corresponding working phase according to the sampling parameters and the vehicle-to-machine data; dividing a plurality of subdivision working conditions in each working stage according to the information source data contained in each working stage;
the key feature screening module is in communication connection with the data acquisition module and is configured to: according to the information source data and the acquisition power consumption, key features are screened from a plurality of information source types based on a preset feature screening algorithm; and
the strategy optimization module is respectively in communication connection with the working condition dividing module and the key feature screening module, and is configured to: obtaining an optimization strategy of the key features from the information source data according to a preset optimization method; and optimizing the execution strategy of the key features in each subdivision working condition according to the optimization strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310325271.3A CN116522758A (en) | 2023-03-29 | 2023-03-29 | Engineering machinery power consumption optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310325271.3A CN116522758A (en) | 2023-03-29 | 2023-03-29 | Engineering machinery power consumption optimization method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116522758A true CN116522758A (en) | 2023-08-01 |
Family
ID=87393042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310325271.3A Pending CN116522758A (en) | 2023-03-29 | 2023-03-29 | Engineering machinery power consumption optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116522758A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109594606A (en) * | 2018-12-05 | 2019-04-09 | 徐州徐工挖掘机械有限公司 | A kind of broken operating condition recognition methods suitable for excavator |
| CN109636951A (en) * | 2018-11-21 | 2019-04-16 | 中南大学 | Excavator energy consumption analysis method based on working phase recognition |
| CN110414720A (en) * | 2019-07-08 | 2019-11-05 | 中国铁道科学研究院集团有限公司 | Energy consumption optimization method, device and the intelligent management system of EMU electrical equipment |
| CN111775925A (en) * | 2020-06-09 | 2020-10-16 | 同济大学 | Working mode decision method and device for power split hybrid electric vehicle |
| CN113216311A (en) * | 2021-05-19 | 2021-08-06 | 三一重机有限公司 | Excavator self-adaptive control method and device and excavator |
| CN114120192A (en) * | 2021-11-19 | 2022-03-01 | 浙江蓝卓工业互联网信息技术有限公司 | Multi-working-condition model automatic selection method and device based on video signal |
| 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 |
-
2023
- 2023-03-29 CN CN202310325271.3A patent/CN116522758A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636951A (en) * | 2018-11-21 | 2019-04-16 | 中南大学 | Excavator energy consumption analysis method based on working phase recognition |
| CN109594606A (en) * | 2018-12-05 | 2019-04-09 | 徐州徐工挖掘机械有限公司 | A kind of broken operating condition recognition methods suitable for excavator |
| CN110414720A (en) * | 2019-07-08 | 2019-11-05 | 中国铁道科学研究院集团有限公司 | Energy consumption optimization method, device and the intelligent management system of EMU electrical equipment |
| CN111775925A (en) * | 2020-06-09 | 2020-10-16 | 同济大学 | Working mode decision method and device for power split hybrid electric vehicle |
| CN113216311A (en) * | 2021-05-19 | 2021-08-06 | 三一重机有限公司 | Excavator self-adaptive control method and device and excavator |
| CN114120192A (en) * | 2021-11-19 | 2022-03-01 | 浙江蓝卓工业互联网信息技术有限公司 | Multi-working-condition model automatic selection method and device based on video signal |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 罗鑫等: ""空气源热泵宽工况能效特性分析与优化控制策略"", 《南通职业大学学报》, vol. 37, no. 1, 25 March 2023 (2023-03-25) * |
| 韩爱国等: ""插电轴混合动力乘用车能量管理策略优化研究‘", 《武汉理工大学学报》, vol. 43, no. 12, 31 December 2021 (2021-12-31) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110775065B (en) | Hybrid electric vehicle battery life prediction method based on working condition recognition | |
| CN110610260B (en) | Driving energy consumption prediction system, method, storage medium and equipment | |
| CN105005222B (en) | New-energy electric vehicle vehicle performance lifting system and method based on big data | |
| CN105774564B (en) | A kind of hybrid electric vehicle energy feedback method and system | |
| CN113358369B (en) | Load spectrum analysis method and system for electric drive system of mining dump truck | |
| CN108790835B (en) | Single-pedal sliding control method for pure electric logistics vehicle | |
| CN115665936B (en) | Tunnel lighting energy-saving control strategy generation method, system, terminal and medium | |
| CN109968989A (en) | A kind of control method for vehicle and device | |
| CN116215495A (en) | Hybrid vehicle energy management optimization method, device and system | |
| CN107817888A (en) | For the method and apparatus for the FPGA boards for operating automatic driving vehicle | |
| CN116522758A (en) | Engineering machinery power consumption optimization method and device | |
| CN112606875B (en) | Control method and system for stable running of heavy-load freight train | |
| CN113378286B (en) | Fatigue life prediction method, storage medium and terminal | |
| CN116823298A (en) | Excavator operation condition identification and timing method | |
| CN115520205B (en) | Method, system and device for adjusting voice interaction based on driving state | |
| CN107356871B (en) | motor monitoring method and device | |
| CN112078559A (en) | Braking control method for electromechanical flywheel hybrid power system | |
| CN111984707A (en) | Multi-mode cross-boundary large data multilevel depth fusion mining method for commercial vehicle | |
| CN118038702B (en) | Method and system for calculating and analyzing upper and lower limits of traffic capacity of lanes in mixed traffic scene | |
| CN117382641B (en) | Method, device and medium for optimizing energy consumption performance of vehicle | |
| CN111912632A (en) | Steering system endurance test control method, device, storage medium and system | |
| CN115585071A (en) | Multistage idle speed control system and method based on engine regeneration conditions | |
| CN117850224A (en) | Energy optimization control method and device for dynamic compactor hybrid power system | |
| CN104635667B (en) | Electric vehicle regenerative braking and ESP coordinated control quick development platform | |
| CN118549162A (en) | Rail transit vehicle traction system energy efficiency test method and system |
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 |