CN114610200A - Intelligent control method and device for engineering mechanical equipment and engineering mechanical equipment - Google Patents
Intelligent control method and device for engineering mechanical equipment and engineering mechanical equipment Download PDFInfo
- Publication number
- CN114610200A CN114610200A CN202210294948.7A CN202210294948A CN114610200A CN 114610200 A CN114610200 A CN 114610200A CN 202210294948 A CN202210294948 A CN 202210294948A CN 114610200 A CN114610200 A CN 114610200A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- target
- framework
- data structure
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000005259 measurement Methods 0.000 claims abstract description 63
- 230000006870 function Effects 0.000 claims description 71
- 238000004364 calculation method Methods 0.000 claims description 40
- 230000015654 memory Effects 0.000 claims description 36
- 238000013507 mapping Methods 0.000 claims description 33
- 238000010276 construction Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 description 15
- 238000004891 communication Methods 0.000 description 14
- 230000008447 perception Effects 0.000 description 10
- 230000004927 fusion Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003213 activating effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/04817—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04845—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44521—Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
- G06F9/44526—Plug-ins; Add-ons
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Stored Programmes (AREA)
Abstract
The invention relates to the technical field of engineering mechanical equipment, in particular to an intelligent control method and device of the engineering mechanical equipment and the engineering mechanical equipment, wherein the method comprises the steps of responding to the selection and connection operation of a plurality of algorithm frame nodes to determine a target algorithm frame corresponding to a target function and a one-way graph data structure corresponding to the target algorithm frame, wherein the algorithm frame nodes are used for realizing the corresponding function; initializing a target algorithm framework based on a data structure of a one-way graph; acquiring measurement data of measurement equipment of engineering mechanical equipment; and triggering the operation of the initialized target algorithm framework according to the measurement data, and controlling the engineering mechanical equipment corresponding to the target function. The data structure of the one-way graph is used for representing the connection relation among all algorithm frame nodes, and the connection relation is utilized to initialize a target algorithm frame, so that the accuracy of initialization can be adjusted, and the intelligent control of engineering machinery equipment is realized.
Description
Technical Field
The invention relates to the technical field of engineering mechanical equipment, in particular to an intelligent control method and device for the engineering mechanical equipment and the engineering mechanical equipment.
Background
Engineering machinery equipment is comprehensively transformed to intellectualization and networking, the demand of a vehicle-mounted computing platform on computing power is gradually increased, and the vehicle-mounted computing platform with a central integrated architecture becomes a development trend. As subjects and fields related to intelligent driving and unmanned operation of engineering machinery vehicles are numerous and industrial chains are incomplete, the industry and ecology are continuously developed, and more engineering machinery host machines and factories hope to integrate system software from shallow to deep and from easy to difficult.
The existing engineering machinery equipment is generally integrated with the realization of corresponding functions, and a user can start the corresponding functions by one key. However, these functions are fixed in the construction machinery equipment, and when special conditions are met, users are required to participate in the control process of the construction machinery equipment, so that the intelligence degree of the construction machinery equipment is reduced.
Disclosure of Invention
In view of this, embodiments of the present invention provide an intelligent control method and apparatus for engineering machinery equipment, and the engineering machinery equipment, so as to solve the problem of low intelligent degree of the engineering machinery equipment.
According to a first aspect, an embodiment of the present invention provides an intelligent control method for construction machinery equipment, including:
responding to selection and connection operations of a plurality of algorithm frame nodes to determine a target algorithm frame corresponding to a target function and a one-way graph data structure corresponding to the target algorithm frame, wherein the algorithm frame nodes are used for realizing the corresponding functions;
initializing the target algorithm framework based on the single-direction graph data structure;
acquiring measurement data of measurement equipment of the engineering mechanical equipment;
and triggering the operation of the initialized target algorithm framework according to the measurement data, and controlling the engineering mechanical equipment corresponding to the target function.
According to the intelligent control method for the engineering mechanical equipment, the target algorithm frame is achieved through combination of all algorithm frame nodes to achieve the corresponding target function, the unidirectional graph data structure is correspondingly obtained after the target algorithm frame is determined, the unidirectional graph data structure is used for representing the connection relation among all algorithm frame nodes, the target algorithm frame is initialized through the connection relation, the accuracy of initialization can be adjusted, and triggering of the target algorithm frame is triggered by the measurement data of the measurement equipment, so that the intelligent control of the engineering mechanical equipment is achieved.
With reference to the first aspect, in a first implementation manner of the first aspect, the determining, in response to the selection and connection operations of the plurality of algorithm framework nodes, a target algorithm framework corresponding to a target function and a unidirectional graph data structure corresponding to the target algorithm framework includes:
in response to a selection operation on the plurality of algorithm frame nodes, determining a target algorithm frame node;
responding to the selection operation of the algorithm plug-ins in each target algorithm frame node, and determining the target algorithm plug-ins corresponding to the target algorithm frame nodes, wherein the target algorithm plug-ins are used for realizing corresponding functions;
and responding to the connection operation between the target algorithm frame nodes, and determining a target algorithm frame corresponding to the target function and the data structure of the unidirectional graph.
According to the intelligent control method for the engineering mechanical equipment, provided by the embodiment of the invention, after the target algorithm frame node is selected and determined, the algorithm plug-in the target algorithm frame node is selected to realize the corresponding function, and then the target algorithm frame node is connected, so that the configuration of the target function required by a user is completed, and the intelligent control on the engineering mechanical equipment can be realized only by once configuration in the process of realizing the target function.
With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the initializing the target algorithm framework based on the unidirectional graph data structure includes;
resetting the number of input/output ports of each target algorithm frame node by using the data structure of the unidirectional graph and the number of input/output ports of the target algorithm plug-in;
and establishing an initial mapping relation between the target algorithm plug-in and an algorithm calculation library through a heterogeneous calculation framework by using the single-direction graph data structure, wherein the algorithm calculation library is used for operating a corresponding algorithm.
According to the intelligent control method for the engineering mechanical equipment, the number of the input/output ports of the target algorithm frame node is reset by using the actual number of the input/output ports of the target algorithm plug-in unit during initialization, so that the reliability of the target algorithm frame node after initialization is ensured; and an initial mapping relation between the target algorithm plug-in and the algorithm calculation library is established during initialization, the initial mapping relation is realized through a heterogeneous calculation framework, and the heterogeneous calculation framework is a bridge for connecting the target algorithm plug-in and the algorithm calculation library, so that logical hierarchical decoupling control is realized, and the reliability of the intelligent control method is ensured.
With reference to the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the establishing, by using the undirected graph data structure, an initial mapping relationship between the target algorithm plug-in and the algorithm computation library through a heterogeneous computation framework includes:
establishing an initial mapping relation between the target algorithm plug-in and a corresponding application interface in the heterogeneous computing framework by using the unidirectional graph data structure;
and establishing an initial mapping relation between the target algorithm plug-in and the corresponding algorithm calculation library based on the initial mapping relation between the target algorithm plug-in and the corresponding application interface in the heterogeneous calculation framework.
According to the intelligent control method for the engineering machinery equipment, provided by the embodiment of the invention, the corresponding application interface in the heterogeneous computing framework is the integrated API interface, and the integrated API interface can be downwards decomposed into each algorithm computing library according to the implementation of the algorithm, namely, the upper layer is only connected with the API interface of the heterogeneous computing framework, and the specific algorithm computing library is not sensed, so that decoupling control is realized.
With reference to the second implementation manner of the first aspect, in a fourth implementation manner of the first aspect, the triggering, according to measurement data of a measurement device of the construction machinery equipment, operation of an initialized target algorithm framework to control the construction machinery equipment according to the target function includes:
acquiring real-time load of each algorithm calculation library;
adjusting the initial mapping relation based on the real-time load, and determining a target mapping relation;
and processing the measurement data based on the target mapping relation and the target algorithm framework so as to control the engineering mechanical equipment corresponding to the target function.
According to the intelligent control method for the engineering mechanical equipment, provided by the embodiment of the invention, the initial mapping relation is adjusted in real time based on the real-time load of each algorithm calculation library in the intelligent control process, so that load balance is realized.
With reference to the first aspect, in a fifth implementation manner of the first aspect, the target algorithm framework inputs an algorithm framework node and a plurality of functional algorithm framework nodes, and the triggering, according to the measurement data, the operation of the initialized target algorithm framework to control the engineering machinery equipment according to the target function further includes:
acquiring the measurement data by using the input algorithm frame node and preprocessing the measurement data;
inputting the preprocessed measurement data into a corresponding functional algorithm frame node for corresponding functional processing, and determining control information of the target function;
and controlling the engineering mechanical equipment based on the control information.
According to the intelligent control method for the engineering machinery equipment, provided by the embodiment of the invention, the measured data is introduced by utilizing a special input algorithm frame node, and then the measured data is sent to the subsequent functional algorithm frame node for processing after being correspondingly preprocessed, so that the connection between the target algorithm frame and the measured result of the measuring equipment is realized.
According to a second aspect, an embodiment of the present invention further provides an intelligent control device for construction machinery equipment, including:
the response module is used for responding to the selection and connection operation of a plurality of algorithm frame nodes to determine a target algorithm frame corresponding to a target function and a unidirectional graph data structure corresponding to the target algorithm frame, wherein the algorithm frame nodes are used for realizing the corresponding functions;
the initialization module is used for initializing the target algorithm framework based on the data structure of the unidirectional graph;
the acquisition module is used for acquiring the measurement data of the measurement equipment of the engineering mechanical equipment;
and the control module is used for triggering the operation of the initialized target algorithm framework according to the measurement data and controlling the engineering mechanical equipment corresponding to the target function.
According to a third aspect, an embodiment of the present invention provides an electronic device applied to a computing platform or a cloud server, where the electronic device includes: the intelligent control method for the construction machinery equipment comprises a memory and a processor, wherein the memory and the processor are in communication connection with each other, computer instructions are stored in the memory, and the processor executes the computer instructions so as to execute the intelligent control method for the construction machinery equipment in the first aspect or any one of the implementation modes of the first aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the method for intelligently controlling construction machinery equipment according to the first aspect or any one of the embodiments of the first aspect.
According to a fifth aspect, an embodiment of the present invention provides a construction machine, including:
equipping a body;
the display part is used for providing a function editing interface which is used for displaying each algorithm frame node;
the electronic device according to the third aspect of the present invention, which is provided in the equipment body.
It should be noted that, for corresponding beneficial effects of the intelligent control device for engineering mechanical equipment, the electronic device and the computer-readable storage medium provided in the embodiment of the present invention, please refer to description of corresponding beneficial effects of the intelligent control method for engineering mechanical equipment, which is not described herein again.
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 flowchart of an intelligent control method of construction machinery equipment according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a goal algorithm framework according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method of intelligent control of work machine equipment according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a selection of algorithm plug-ins according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an algorithm framework node according to an embodiment of the invention;
FIG. 6 is a diagram illustrating a mapping relationship according to an embodiment of the invention;
FIG. 7 is a schematic diagram of the internal components of a heterogeneous computing framework, according to an embodiment of the invention;
FIG. 8 is a flowchart of a method of intelligent control of work machine equipment according to an embodiment of the present disclosure;
fig. 9 is a block diagram of a construction machine equipped intelligent control apparatus according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
According to the intelligent control method of the engineering machinery equipment, provided by the embodiment of the invention, part or even all of upper-layer functional application software is generated in a visual and dragging mode by depending on an engineering machinery vehicle-mounted computing platform and platform software matched with the engineering machinery vehicle-mounted computing platform, so that the development period is shortened, and the online rhythm of intelligent engineering machinery products is accelerated. The method comprises the steps of conducting modularized segmentation on functional application software of intelligent driving and unmanned operation, abstracting algorithm frame nodes, wherein each algorithm frame node supports a heterogeneous computing algorithm plug-in of one category, and corresponds to a node icon in a visual interface. For a user, the user only needs to understand the modularized functional principle and is completely insensitive to the specific implementation of heterogeneous computation on the vehicle-mounted computing platform, the development difficulty is reduced, the development experience of the user is improved, the probability of errors in manually writing codes is greatly reduced, the stability and reliability of a software system are improved, and meanwhile, the maintenance cost of later-period software is greatly reduced.
Specifically, according to the functional characteristics of intelligent driving and unmanned operation of the engineering machinery, functional application software is abstracted into a network formed by a plurality of algorithm frame nodes, a user drags and connects node icons in a visual mode to generate a one-way Graph data structure, for example, a directed acyclic Graph DAG or a directed local cyclic Graph is adopted, and the data structure is stored in a vehicle-mounted computing platform.
The method comprises the following steps that a single-direction Graph data structure is loaded and analyzed by a vehicle-mounted computing platform CPU program of the engineering machinery, then algorithm frame nodes involved in the single-direction Graph are initialized, and finally a decentralized network is formed and strictly follows the direction described in the single-direction Graph: the former algorithm frame node triggers the latter algorithm frame node to execute, and the initial algorithm frame node is triggered by the real-time measurement data of the measurement equipment at a fixed frequency, so that the execution of all algorithm frame nodes can be ensured to have certainty, the observability of the algorithm frame nodes is enhanced, and the robustness of the whole software system is improved.
All algorithm framework nodes involved in the Graph of the unidirectional Graph support a category of heterogeneous computing algorithm plug-ins, such as: the method comprises a camera-perceived heterogeneous computing algorithm plug-in, a laser radar-perceived heterogeneous computing algorithm plug-in, a camera and laser radar front-fusion heterogeneous computing algorithm plug-in, a planning decision heterogeneous computing algorithm plug-in and the like. The user uses the algorithm plug-ins for heterogeneous calculation as required without paying attention to a specific heterogeneous calculation implementation scheme at the bottom layer, so that the development threshold is reduced, and the efficient utilization of resources of a multi-core heterogeneous SOC chip on an engineering machinery vehicle-mounted computing platform is ensured.
The embodiment of the invention also provides engineering mechanical equipment, including but not limited to a dump truck, a mine truck, a forklift and an excavator, and the specific type of the engineering mechanical equipment is not limited at all. The engineering mechanical equipment comprises an equipment body, a display piece and electronic equipment, wherein the equipment body is related to the specific type of the engineering mechanical equipment; the display part is used for providing a function editing interface, and the function editing interface is used for displaying each algorithm frame node, wherein, as for the display mode of the algorithm frame nodes, the display mode can be in a form of a list, or in a form of an icon, and the like, without any limitation here. The electronic equipment is connected with the display part and used for executing the intelligent control method of the engineering mechanical equipment in the embodiment of the invention.
Specific details regarding the intelligent control method of the construction machine equipment will be described in detail below.
As a specific application scenario of the embodiment of the present invention, taking engineering machinery equipment as a forklift as an example, each algorithm frame node is provided on a display of the forklift, and a user performs processing such as selection and connection of the corresponding algorithm frame node on the display based on a control requirement of the current forklift, so as to obtain a target algorithm frame corresponding to a target function. In the operation process of the forklift, the measuring equipment on the forklift acquires corresponding measuring data in real time, and the measuring data is processed by using a target algorithm frame to correspondingly control the forklift.
As another specific application scenario of the embodiment of the present invention, taking engineering machinery equipment as a forklift as an example, the forklift is connected to a terminal, each algorithm frame node is provided on a display of the terminal, and a user performs processing such as selection and connection of the corresponding algorithm frame node on the display based on a control requirement of the current forklift, so as to obtain a target algorithm frame corresponding to a target function. During the operation process of the forklift, the measuring equipment on the forklift collects corresponding measuring data in real time, sends the measuring data to the terminal, processes the measuring data by using the target algorithm frame to obtain a control instruction, and sends the control instruction to the forklift, so that the forklift is correspondingly controlled.
In accordance with an embodiment of the present invention, there is provided an intelligent control method for construction machinery equipment, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that described herein.
In this embodiment, an intelligent control method for an engineering mechanical equipment is provided, which may be used in an engineering mechanical equipment, such as a vehicle controller, and fig. 1 is a flowchart of the intelligent control method for an engineering mechanical equipment according to an embodiment of the present invention, and as shown in fig. 1, the flowchart includes the following steps:
and S11, responding to the selection and connection operation of the plurality of algorithm frame nodes to determine a target algorithm frame corresponding to the target function and a one-way graph data structure corresponding to the target algorithm frame.
Wherein the algorithm framework nodes are used for realizing corresponding functions.
As described above, the algorithm frame nodes and the setting interface of the algorithm frame are displayed on the interface of the construction machinery equipment. In the process of setting a target algorithm frame with a target function, a user selects a corresponding algorithm frame node, places the corresponding algorithm frame node on a setting interface of the algorithm frame, and correspondingly connects the algorithm frame nodes to obtain the target algorithm frame.
Fig. 2 shows a specific application example of a target algorithm framework, where the target algorithm framework includes high-precision positioning algorithm framework nodes, lidar sensing algorithm framework nodes, camera sensing algorithm framework nodes, fusion positioning algorithm framework nodes, post-fusion algorithm framework nodes, planning decision algorithm framework nodes, and control algorithm framework nodes, and a user connects the algorithm framework nodes according to actual needs to obtain the target algorithm framework.
Because the target algorithm framework is obtained by connecting the nodes of each algorithm framework, the data structure of the one-way graph corresponding to the target algorithm framework can be obtained after the target algorithm framework is determined. The data result of the unidirectional graph is used for representing the connection relation among all algorithm frame nodes, namely, the unidirectional graph data structure describes the connection relation of all the involved algorithm frame nodes, and for the specific algorithm frame node, before a vehicle-mounted computing platform CPU program loads and analyzes the unidirectional graph data structure, the unidirectional graph data structure does not know which algorithm frame nodes the input of the front end of the unidirectional graph data structure is and which algorithm frame nodes the output of the rear end of the unidirectional graph data structure is required to be. Based on this, the target algorithm framework needs to be initialized.
S12, initializing the target algorithm framework based on the data structure of the one-way graph.
As described above, the unidirectional graph data structure is used to represent the connection relationships of the various algorithm frame nodes in the target algorithm frame. For the electronic equipment, the target algorithm framework is not perceived, and the connection relation of each algorithm framework node is known through the data structure of the unidirectional graph. And after the data structure of the unidirectional Graph is successfully loaded and analyzed, triggering each algorithm framework node to execute respective initialization process. When the algorithm framework nodes are initialized, the default input and output software interfaces are automatically reloaded, because for a certain class of algorithm framework nodes, the default input software interfaces at the front end are X, and the default output software interfaces at the back end are Y. After initialization, the number of input/output ports is adjusted according to the actual configuration of the algorithm framework nodes.
And S13, acquiring the measurement data of the measurement equipment of the engineering machinery equipment.
As mentioned above, the operation of the target algorithm framework is triggered by the measuring devices of the construction machinery equipment, which can perform the acquisition of the measurement data at a fixed period, and accordingly, the target algorithm framework processes the measurement data at a corresponding period. For the acquisition of the measurement data, the measurement equipment sends the acquired measurement data to the electronic equipment, and the electronic equipment takes the acquired measurement data as the input of the target algorithm framework.
Wherein, the setting of the measuring equipment is set according to actual requirements. For example, it may be for image acquisition, or for positioning, or for distance acquisition, etc.
And S14, triggering the operation of the initialized target algorithm framework according to the measurement data, and controlling the engineering mechanical equipment according to the target function.
After the electronic equipment acquires the measurement data, triggering the operation of the target algorithm framework, taking the measurement data as the input of the target algorithm framework, and obtaining an output result through the automatic operation of the target algorithm framework, wherein the output result is the control information of the target function. Correspondingly, the electronic equipment controls the engineering mechanical equipment by reusing the control information, so that the intelligent control of the engineering mechanical equipment is realized.
For example, in the case of an on-board computing platform of a construction machine, a camera, a laser radar, a millimeter wave radar, and other measuring devices are usually connected, and these measuring devices transmit data to the outside according to a fixed period/frequency. For example, the camera transmits 30 frames of image data outwards every second, which triggers the camera-aware algorithm framework nodes to execute 30 times per second.
According to the intelligent control method for the engineering mechanical equipment, the target algorithm frame is realized by utilizing the combination of all algorithm frame nodes to realize the corresponding target function, a unidirectional graph data structure is correspondingly obtained after the target algorithm frame is determined, the unidirectional graph data structure is used for representing the connection relation among all the algorithm frame nodes, the target algorithm frame is initialized by utilizing the connection relation, the initialization accuracy can be adjusted, and the triggering of the target algorithm frame is triggered by the measurement data of the measurement equipment, so that the intelligent control on the engineering mechanical equipment is realized.
In this embodiment, an intelligent control method for an engineering mechanical equipment is provided, which may be used in an engineering mechanical equipment, such as a vehicle controller, and fig. 3 is a flowchart of the intelligent control method for an engineering mechanical equipment according to an embodiment of the present invention, and as shown in fig. 3, the flowchart includes the following steps:
and S21, responding to the selection and connection operation of the plurality of algorithm frame nodes to determine a target algorithm frame corresponding to the target function and a one-way graph data structure corresponding to the target algorithm frame.
Wherein the algorithm framework nodes are used for realizing corresponding functions.
Specifically, the above S21 may include:
(1) in response to a selection operation of the plurality of algorithm frame nodes, a target algorithm frame node is determined.
(2) And responding to the selection operation of the algorithm plug-ins in each target algorithm frame node, and determining the target algorithm plug-ins corresponding to the target algorithm frame nodes. Wherein the target algorithm plug-in is used for realizing corresponding functions.
(3) And responding to the connection operation among the nodes of the target algorithm framework, and determining the target algorithm framework corresponding to the target function and the data structure of the unidirectional graph.
For each algorithm framework node, an algorithm plug-in with default support is provided, and when a plurality of algorithm plug-ins are supported, a user can bind/unbind the algorithm plug-ins through a visual interface. As shown in fig. 4, each algorithm framework node is adapted to a class of algorithms, which are mainly embodied on the communication architecture, the underlying data structure and the algorithm plug-ins. In particular, there is a distinction between the input and output software interfaces of the communication architecture, the type of data structure corresponding to the software interfaces, and the algorithm plug-ins of the heterogeneous computations that the algorithm framework nodes can choose from, for different classes of algorithm framework nodes. And the binding API interfaces of the algorithm plug-ins in each algorithm frame node are consistent, and a uniform API interface is adopted, but the parameters transmitted to the API interface in the process of binding the specific algorithm plug-ins by the algorithm frame node are different.
The algorithm plug-in is responsible for specific algorithm processing, the algorithm plug-in is designed to be plug-and-play, and the input and output software interfaces of the whole algorithm frame node correspond to the one-way Graph described in the following steps: the front end of the system is connected with the outputs of which algorithm frame nodes, and the back end of the system needs to transmit data to the inputs of which algorithm frame nodes.
As a specific embodiment, the input software interface of the algorithm framework node adopts a subscriber, and the output software interface adopts a publisher. After the subscriber is initialized, the algorithm framework node can receive the output of other algorithm framework nodes connected with the front end of the algorithm framework node and described in the data structure of the unidirectional graph; after the publisher is initialized, the algorithm framework node can transmit data to other algorithm framework nodes connected to it at its back end as described in the data structure of the unidirectional graph.
As shown in fig. 5, the algorithm framework node is mainly composed of 4 parts: an algorithm plug-in set, an algorithm plug-in binding API interface, a communication architecture and an underlying data structure.
The design of the algorithm plug-in adopts a plug-and-play scheme, namely the algorithm frame nodes and the algorithm plug-in are not in one-to-one correspondence but in one-to-many relationship, so that the algorithm plug-in has the advantages that: algorithm plugins can be replaced but the "base" portion of the algorithm framework nodes is not modified at all.
The algorithm plug-in binding API interface is mainly responsible for binding the algorithm plug-in with the algorithm frame node in the initialization stage, so that the algorithm frame node and the algorithm plug-in form a one-to-one relationship in the running state: only the algorithm plug-ins that are bound during the initialization phase will execute.
The communication architecture mainly comprises management functions of input and output software interfaces of the algorithm frame nodes, the number of default input software interfaces at the front end of a certain algorithm frame node is X, the number of default output software ports at the rear end of the certain algorithm frame node is Y, and after the initialization process is completed: the number of the input software interfaces in the running state of the algorithm frame node is J, and the number of the output software interfaces is K, so that the communication architecture of the algorithm frame node manages the J input software interfaces and the K output software interfaces in the running state.
The basic data structure defines the data structure commonly used by the algorithm framework node for algorithm processing, for example, the basic data structure of the algorithm framework node suitable for camera sensor access and preprocessing defines the image data structure output by the camera sensor.
After a user drags 2 or more algorithm frame nodes in a setting interface of an algorithm frame, the output of one algorithm frame node can be led to the input end of another algorithm frame node in a connection mode, the software interfaces of the input and the output of the algorithm frame nodes can be expanded in a self-adaptive mode, the input interfaces of each algorithm frame node can support X at most, and the output interfaces can support Y at most (for example, X is less than or equal to 32, and Y is less than or equal to 32). As a specific example, as shown in fig. 2, a final decentralized target algorithm framework is formed by dragging, wherein:
1) the input end of the high-precision positioning algorithm frame node can be connected with the output of an RTK differential positioning sensor access and preprocessing algorithm frame node (not shown in figure 2) and the output of an IMU inertial navigation sensor access and preprocessing algorithm frame node (not shown in figure 2); the output end of the high-precision positioning algorithm frame node can output RTK + IMU combined positioning information, and generally can reach centimeter-level positioning precision;
2) the input end of the laser radar perception algorithm frame node can be connected with the laser radar sensor access and the point cloud data output of the preprocessing algorithm frame node (not shown in figure 2); one output interface of the frame node of the laser radar perception algorithm can be the output of a laser SLAM positioning result, and the output interface of the frame node of the laser radar perception algorithm and the output interface of the frame node of the high-precision positioning algorithm are connected to the input end of the frame node of the fusion positioning algorithm; the other output interface of the laser radar perception algorithm frame node can be used for outputting the result of obstacle target detection based on the laser point cloud and connecting the result to one input interface of the post-fusion algorithm frame node.
3) The input end of the fusion positioning algorithm frame node is connected with the output of the high-precision positioning algorithm frame node and the output of the laser radar perception algorithm frame node, and meanwhile, the fusion positioning algorithm frame node is loaded with high-precision map data at the input end; after algorithm processing, the fusion positioning algorithm frame node outputs fusion positioning information in the scene where the fusion positioning algorithm frame node is actually located, and provides the fusion positioning information to a planning decision algorithm frame node at the rear end.
4) The input end of the camera perception algorithm frame node can be the original video image output from a monocular camera, a binocular camera or even a multi-view camera accessing algorithm frame node (not shown in figure 2), the output of the camera perception algorithm frame node is the detection and identification result of the obstacle target, and the output information and the obstacle target detection result of the output end of the laser radar perception algorithm frame node are output to the input end of the post-fusion algorithm frame node.
5) The input end of the post-fusion algorithm frame node is connected with the output of the laser radar perception algorithm frame node and the output of the camera perception algorithm frame node, and after the post-fusion algorithm processing, the post-fusion algorithm frame node outputs accurate obstacle target detection and identification result information to the planning decision algorithm frame node.
6) The input end of the planning decision algorithm frame node is connected with the outputs of the fusion positioning algorithm frame node and the post-fusion algorithm frame node, and the local path planning information is output to the control algorithm frame node at the rear end after the processing of the planning decision algorithm.
7) The input end of the control algorithm frame node is connected with the output of the planning decision algorithm frame node, and the local path planning information is converted into control instructions of the engineering machinery vehicle such as transverse direction, longitudinal direction, even lifting and side tilting after being processed by the control algorithm.
After the target algorithm frame node is selected and determined, the algorithm plug-in the target algorithm frame node is selected to realize the corresponding function, and then the target algorithm frame node is connected, so that the configuration of the target function required by a user is completed, and in the process of realizing the target function, the intelligent control of the engineering machinery equipment can be realized only by once configuration.
S22, initializing the target algorithm framework based on the data structure of the one-way graph.
Specifically, S22 includes:
s221, the number of the input/output ports of each target algorithm frame node is reset by using the data structure of the unidirectional graph and the number of the input/output ports of the target algorithm plug-in.
When a user connects J lines to the input end and connects K lines to the output end of the algorithm frame node through the setting interface, J input software interfaces and K output software interfaces are recorded in the data structure of the unidirectional graph at this time. When the algorithm frame nodes are initialized, the input software interfaces of the algorithm frame nodes are automatically reloaded into J and the output software interfaces are automatically reconstructed into K according to the data structure of the unidirectional graph.
It should be noted that the J input software interfaces and the K software interfaces are all in a run state, which is the case only when the algorithm framework nodes are running, and remain in a default state if not initialized.
S222, establishing an initial mapping relation between the target algorithm plug-in and the algorithm calculation library through a heterogeneous calculation framework by using a unidirectional graph data structure.
Wherein the algorithm computation library is used for operating a corresponding algorithm.
On the software hierarchical design, a heterogeneous computing framework belongs to a layer below an algorithm framework node. The heterogeneous computing framework is a set of API interfaces with a large granularity provided in a software system of a vehicle-mounted computing platform, and the code implementation inside the API interfaces generally relates to programming of 2 or more processors on a multi-core heterogeneous SOC chip, for example, the code implementation inside the API interfaces corresponding to function a of the heterogeneous computing framework includes a part of code running on a CPU, a part of code running on a GPU, and a part of code running on a DSP.
The algorithm calculation library is a set of API interfaces with smaller granularity provided in the software system, and the code implementation inside the API interfaces usually only relates to programming of 1 processor on a multi-core heterogeneous SOC chip and is provided in the form of library functions, including a CPU high-performance calculation library, a GPU high-performance calculation library, an NPU high-performance calculation library, a DSP high-performance calculation library and the like.
As shown in FIG. 6, the software layer of the heterogeneous computing framework generates a default mapping relationship between the upper API interface and the underlying high-performance library API interface during the process of initializing automatic deployment. That is to say, the heterogeneous computing framework provides an API interface with a larger granularity for the computing algorithm plug-in of the upper-layer algorithm framework node, but the implementation inside the API interface calls the API interface with a smaller granularity provided by the high-performance computing library, and the processor cores such as the CPU, the DSP, and the GPU provide the API interfaces of the high-performance computing library with the same function, and the heterogeneous computing framework maintains a mapping relationship between the upper-layer API interface and the bottom-layer API interface by default according to the condition of the selected computing algorithm plug-in.
In some optional embodiments, the S222 includes:
(1) and establishing an initial mapping relation between the target algorithm plug-in and a corresponding application interface in the heterogeneous computing framework by using the data structure of the unidirectional graph.
(2) And establishing an initial mapping relation between the target algorithm plug-in and a corresponding algorithm calculation library based on the initial mapping relation between the target algorithm plug-in and a corresponding application interface in the heterogeneous calculation framework.
As described above, the heterogeneous computing framework provides an application interface for the upper layer, and connects each algorithm computing library to the lower layer, and each application interface corresponds to a default algorithm computing library. The heterogeneous computing framework is not embodied in the setting interface, and the existing meaning of the heterogeneous computing framework is as follows: and providing an API interface with larger granularity for calling an algorithm plug-in an algorithm framework node, and shielding the implementation details of the bottom layer. For example, the algorithm plug-in calls the heterogeneous computing API interface func _ a to implement a certain function, but the implementation inside func _ a is divided into 3 steps, where the first step is executed on the CPU of the SOC chip, the second step is executed on the DSP of the SOC chip, and the 3 rd step is executed on the GPU of the SOC chip.
As shown in fig. 7, algorithm plug-ins for heterogeneous computation in each algorithm framework node in the unidirectional graph data structure string may call heterogeneous computation API interfaces provided by the heterogeneous computation framework; the specific implementation inside the heterogeneous computing API interface is that an algorithm computing library arranged on each processor core on the multi-core heterogeneous SOC chip is activated, for example, a heterogeneous computing framework achieves the effects of activating a certain high-performance computing library arranged on a CPU and obtaining a corresponding computing result by calling the API interface calculated by the CPU; the effect of activating a certain high-performance computing library deployed on the DSP and obtaining a corresponding computing result is achieved by calling the API interface of the DSP computing. Each processor core on the multi-core heterogeneous SOC chip has the access right of the SOC chip shared memory, the calculation input of a certain processor core can be acquired from the shared memory area, and then the calculation result can also be output to the shared memory area; in this way, the other processor core can obtain the output result of the previous step from the shared memory area and perform the calculation and processing of the next step. And finally, all algorithm frame nodes and algorithm plug-ins thereof which are strung together with the directed single-direction graph data structure are implemented on various high-performance computing libraries on the multi-core heterogeneous SOC chip, and are called by the heterogeneous computing frame, and real-time and efficient data interaction is carried out through the memory space shared by the SOC chip, so that the whole process is insensitive to users.
And S23, acquiring the measurement data of the measurement equipment of the engineering machinery equipment.
Please refer to S13 in fig. 1, which is not described herein again.
And S24, triggering the operation of the initialized target algorithm framework according to the measurement data, and controlling the engineering mechanical equipment according to the target function.
Specifically, S24 includes:
and S241, acquiring real-time loads of the algorithm calculation libraries.
And S242, adjusting the initial mapping relation based on the real-time load, and determining a target mapping relation.
And S243, processing the measurement data based on the target mapping relation and the target algorithm framework so as to control the engineering mechanical equipment according to the target function.
The heterogeneous computing framework also comprises an algorithm analysis module which is responsible for analyzing the load condition of each processor core on the SOC chip, and because the functions of the high-performance computing libraries deployed on each processor core on the SOC chip are overlapped, namely a certain function can be completed by the high-performance computing library of the CPU or the high-performance computing library of the DSP, the heterogeneous computing framework can dynamically adjust the calling of the high-performance computing libraries according to the load condition of each processor core, thereby realizing the integral load balancing effect and enabling the engineering machinery vehicle-mounted computing platform to efficiently and stably run.
Once an algorithm analysis module in a heterogeneous computing framework finds that the resource occupancy rate of a certain processor core is too high, the mapping relationship between an API interface on the heterogeneous computing framework pair and an API of a bottom-layer high-performance computing library is adjusted at the moment. For example, the current DSP resource occupancy is too high, and the "monocular camera preprocessing" API interface provided upwards by the running heterogeneous computing framework uses the "image YUV-to-RGB color space conversion" API interface provided by the high-performance computing library on the DSP, so that the "image YUV-to-RGB color space conversion" API interface provided by the high-performance computing library on the GPU or other processor core needs to be adopted at this time, thereby ensuring the overall load balance.
According to the intelligent control method for the engineering mechanical equipment, the number of the input/output ports of the target algorithm frame node is reset by using the actual number of the input/output ports of the target algorithm plug-in during initialization, so that the reliability of the target algorithm frame node after initialization is ensured; and an initial mapping relation between the target algorithm plug-in and the algorithm calculation library is established during initialization, the initial mapping relation is realized through a heterogeneous calculation framework, and the heterogeneous calculation framework is a bridge for connecting the target algorithm plug-in and the algorithm calculation library, so that logical hierarchical decoupling control is realized, and the reliability of the intelligent control method is ensured. In the intelligent control process, the initial mapping relation is adjusted in real time based on the real-time load of each algorithm calculation library, so that load balance is realized.
In this embodiment, an intelligent control method for a construction machinery equipment is provided, which may be used in a construction machinery equipment, such as a vehicle control unit, and fig. 8 is a flowchart of the intelligent control method for a construction machinery equipment according to an embodiment of the present invention, and as shown in fig. 8, the flowchart includes the following steps:
and S31, responding to the selection and connection operation of the plurality of algorithm frame nodes to determine a target algorithm frame corresponding to the target function and a one-way graph data structure corresponding to the target algorithm frame.
Wherein the algorithm framework nodes are used for realizing corresponding functions.
The target algorithm frame inputs algorithm frame nodes and a plurality of functional algorithm frame nodes, and the input algorithm frame nodes only support the connection of output ends and do not support the connection of input ends. That is, the input of the input algorithm framework node is not connected to the output of other algorithm framework nodes, which is typically used for access and data pre-processing by measurement devices. The input of the algorithm is the data output of a specific sensor, for example, an image of 30 frames per second of a camera, then certain data preprocessing such as image cutting, filtering and the like is carried out, and the output software interface of the algorithm is connected with other algorithm framework nodes in a wired mode.
For the rest, please refer to S21 in the embodiment shown in fig. 3, which is not described herein again.
S32, initializing the target algorithm framework based on the data structure of the one-way graph.
Please refer to S22 in fig. 3 for details, which are not described herein.
And S33, acquiring the measurement data of the measurement equipment of the engineering machinery equipment.
Please refer to S13 in fig. 1, which is not described herein again.
And S34, triggering the operation of the initialized target algorithm framework according to the measurement data, and controlling the engineering mechanical equipment according to the target function.
Specifically, S34 includes:
and S341, acquiring the measurement data by using the input algorithm frame node and preprocessing the measurement data.
As described above, the input algorithm framework node is used for interfacing with the measurement device, the input of the input algorithm framework node is measurement data, and after the measurement data is acquired by the input algorithm framework node, the measurement data is subjected to preset preprocessing. The specific pretreatment mode is set according to actual requirements, and is not limited herein.
And S342, inputting the preprocessed measurement data into a corresponding functional algorithm frame node for corresponding functional processing, and determining control information of a target function.
The output of the input algorithm frame nodes is connected with the corresponding functional algorithm frame nodes, certainly, the functional algorithm frame nodes are connected according to actual requirements, correspondingly, the output data of the input algorithm frame nodes are subjected to corresponding functional processing, and control information of the target function is obtained.
And S343, controlling the engineering machinery equipment based on the control information.
The electronic equipment controls the engineering mechanical equipment by using the control information obtained by calculation, so that the intelligent control of the engineering mechanical equipment is realized.
According to the intelligent control method for the engineering machinery equipment, the measured data is introduced by using a special input algorithm frame node, the measured data is correspondingly preprocessed and then sent to the subsequent functional algorithm frame node for processing, and therefore the connection between the target algorithm frame and the measured result of the measuring equipment is achieved.
In this embodiment, an intelligent control device for engineering machinery equipment is further provided, and the device is used to implement the foregoing embodiments and preferred embodiments, and the description of the device is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
The present embodiment provides an intelligent control device for construction machinery equipment, as shown in fig. 9, including:
a response module 41, configured to respond to selection and connection operations on a plurality of algorithm frame nodes, so as to determine a target algorithm frame corresponding to a target function and a unidirectional graph data structure corresponding to the target algorithm frame, where the algorithm frame nodes are used to implement the corresponding functions;
an initialization module 42 for initializing the target algorithm framework based on the unidirectional graph data structure;
an obtaining module 43, configured to obtain measurement data of a measurement device of the engineering mechanical equipment;
and the control module 44 is configured to trigger the initialized operation of the target algorithm framework according to the measurement data, and perform control on the engineering mechanical equipment corresponding to the target function.
The intelligent control device of the construction machinery equipment in the embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and a memory executing one or more software or fixed programs, and/or other devices that can provide the above functions.
Further functional descriptions of the modules are the same as those of the corresponding embodiments, and are not repeated herein.
An embodiment of the present invention further provides an electronic device, which includes the intelligent control device of the engineering mechanical equipment shown in fig. 9. The electronic equipment is applied to a computing platform of engineering machinery assembly configuration, or a cloud server, and the like, and the application scene of the electronic equipment is not limited at all and can be set according to actual requirements.
Referring to fig. 10, fig. 10 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, as shown in fig. 10, the electronic device may include: at least one processor 51, such as a CPU (Central Processing Unit), at least one communication interface 53, memory 54, at least one communication bus 52. Wherein a communication bus 52 is used to enable the connection communication between these components. The communication interface 53 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 53 may also include a standard wired interface and a standard wireless interface. The Memory 54 may be a high-speed RAM Memory (volatile Random Access Memory) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 54 may alternatively be at least one memory device located remotely from the processor 51. Wherein the processor 51 may be in connection with the apparatus described in fig. 9, the memory 54 stores an application program, and the processor 51 calls the program code stored in the memory 54 for performing any of the above-mentioned method steps.
The communication bus 52 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 52 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 10, but this is not intended to represent only one bus or type of bus.
The memory 54 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviated: HDD) or a solid-state drive (english: SSD); the memory 54 may also comprise a combination of the above types of memories.
The processor 51 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of a CPU and an NP.
The processor 51 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 54 is also used to store program instructions. The processor 51 may call program instructions to implement the intelligent control method of the construction machine equipment as shown in any of the embodiments of the present application.
The embodiment of the invention also provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions which can execute the intelligent control method of the engineering mechanical equipment in any method embodiment. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. An intelligent control method for engineering machinery equipment is characterized by comprising the following steps:
responding to selection and connection operations of a plurality of algorithm frame nodes to determine a target algorithm frame corresponding to a target function and a one-way graph data structure corresponding to the target algorithm frame, wherein the algorithm frame nodes are used for realizing the corresponding functions;
initializing the target algorithm framework based on the single-direction graph data structure;
acquiring measurement data of measurement equipment of the engineering mechanical equipment;
and triggering the operation of the initialized target algorithm framework according to the measurement data, and controlling the engineering mechanical equipment corresponding to the target function.
2. The method of claim 1, wherein determining a target algorithm framework corresponding to a target function and a one-way graph data structure corresponding to the target algorithm framework in response to selecting and connecting operations on a plurality of algorithm framework nodes comprises:
in response to a selection operation on the plurality of algorithm frame nodes, determining a target algorithm frame node;
responding to the selection operation of the algorithm plug-ins in each target algorithm frame node, and determining the target algorithm plug-ins corresponding to the target algorithm frame nodes, wherein the target algorithm plug-ins are used for realizing corresponding functions;
and responding to the connection operation between the target algorithm frame nodes, and determining a target algorithm frame corresponding to the target function and the data structure of the unidirectional graph.
3. The method of claim 2, wherein initializing the target algorithm framework based on the directed graph data structure comprises;
resetting the number of input/output ports of each target algorithm frame node by using the data structure of the unidirectional graph and the number of input/output ports of the target algorithm plug-in;
and establishing an initial mapping relation between the target algorithm plug-in and an algorithm calculation library through a heterogeneous calculation framework by using the single-direction graph data structure, wherein the algorithm calculation library is used for operating a corresponding algorithm.
4. The method according to claim 3, wherein the establishing an initial mapping relationship between the target algorithm plug-in and the algorithm calculation library through a heterogeneous calculation framework by using the single direction graph data structure comprises:
establishing an initial mapping relation between the target algorithm plug-in and a corresponding application interface in the heterogeneous computing framework by using the unidirectional graph data structure;
and establishing an initial mapping relation between the target algorithm plug-in and the corresponding algorithm calculation library based on the initial mapping relation between the target algorithm plug-in and the corresponding application interface in the heterogeneous calculation framework.
5. The method of claim 3, wherein triggering the operation of the initialized target algorithm framework based on the measurement data of the measuring device of the work machine equipment, controlling the work machine equipment corresponding to the target function comprises:
acquiring real-time load of each algorithm calculation library;
adjusting the initial mapping relation based on the real-time load, and determining a target mapping relation;
and processing the measurement data based on the target mapping relation and the target algorithm framework so as to control the engineering mechanical equipment corresponding to the target function.
6. The method of claim 1, wherein the target algorithm framework inputs an algorithm framework node and a plurality of functional algorithm framework nodes, the triggering of the initialized operation of the target algorithm framework based on the measurement data, the controlling of the work machine equipment corresponding to the target function, further comprising:
acquiring the measurement data by using the input algorithm frame node and preprocessing the measurement data;
inputting the preprocessed measurement data into a corresponding functional algorithm frame node for corresponding functional processing, and determining control information of the target function;
and controlling the engineering mechanical equipment based on the control information.
7. An intelligent control device of engineering machinery equipment is characterized by comprising:
the response module is used for responding to the selection and connection operation of a plurality of algorithm frame nodes to determine a target algorithm frame corresponding to a target function and a unidirectional graph data structure corresponding to the target algorithm frame, wherein the algorithm frame nodes are used for realizing the corresponding functions;
the initialization module is used for initializing the target algorithm framework based on the data structure of the unidirectional graph;
the acquisition module is used for acquiring the measurement data of the measurement equipment of the engineering mechanical equipment;
and the control module is used for triggering the operation of the initialized target algorithm framework according to the measurement data and controlling the engineering mechanical equipment corresponding to the target function.
8. An electronic device applied to a computing platform or a cloud server, the electronic device comprising:
a memory and a processor, wherein the display, the memory and the processor are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the intelligent control method of the construction machinery equipment according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing a computer to execute the intelligent control method of construction machinery equipment according to any one of claims 1 to 6.
10. A work machine, comprising:
equipping a body;
the display part is used for providing a function editing interface which is used for displaying each algorithm frame node;
the electronic device of claim 8, disposed within the equipment body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210294948.7A CN114610200A (en) | 2022-03-23 | 2022-03-23 | Intelligent control method and device for engineering mechanical equipment and engineering mechanical equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210294948.7A CN114610200A (en) | 2022-03-23 | 2022-03-23 | Intelligent control method and device for engineering mechanical equipment and engineering mechanical equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114610200A true CN114610200A (en) | 2022-06-10 |
Family
ID=81864428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210294948.7A Pending CN114610200A (en) | 2022-03-23 | 2022-03-23 | Intelligent control method and device for engineering mechanical equipment and engineering mechanical equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114610200A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130331963A1 (en) * | 2012-06-06 | 2013-12-12 | Rockwell Automation Technologies, Inc. | Systems, methods, and software to identify and present reliability information for industrial automation devices |
| CN109783141A (en) * | 2017-11-10 | 2019-05-21 | 华为技术有限公司 | Isomery dispatching method |
| CN111258744A (en) * | 2018-11-30 | 2020-06-09 | 中兴通讯股份有限公司 | Task processing method based on heterogeneous computation and software and hardware framework system |
| CN112346618A (en) * | 2020-11-11 | 2021-02-09 | 广州小鹏汽车科技有限公司 | Vehicle service processing method and device |
| CN112652012A (en) * | 2020-12-31 | 2021-04-13 | 北京百度网讯科技有限公司 | Intelligent control method, device and equipment for excavator, storage medium and excavator |
| CN112685154A (en) * | 2020-12-25 | 2021-04-20 | 北京有竹居网络技术有限公司 | Data processing method of task flow engine, device and medium |
| US20210149889A1 (en) * | 2019-11-18 | 2021-05-20 | Rockwell Automation Technologies, Inc. | Interactive industrial automation remote assistance system for components |
| CN112836404A (en) * | 2021-01-07 | 2021-05-25 | 大连理工大学 | Method for constructing digital twin body of structural performance of intelligent excavator |
| WO2021217659A1 (en) * | 2020-04-30 | 2021-11-04 | 深圳中砼物联网科技有限公司 | Multi-source heterogeneous data processing method, computer device, and storage medium |
-
2022
- 2022-03-23 CN CN202210294948.7A patent/CN114610200A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130331963A1 (en) * | 2012-06-06 | 2013-12-12 | Rockwell Automation Technologies, Inc. | Systems, methods, and software to identify and present reliability information for industrial automation devices |
| CN109783141A (en) * | 2017-11-10 | 2019-05-21 | 华为技术有限公司 | Isomery dispatching method |
| CN111258744A (en) * | 2018-11-30 | 2020-06-09 | 中兴通讯股份有限公司 | Task processing method based on heterogeneous computation and software and hardware framework system |
| US20210149889A1 (en) * | 2019-11-18 | 2021-05-20 | Rockwell Automation Technologies, Inc. | Interactive industrial automation remote assistance system for components |
| WO2021217659A1 (en) * | 2020-04-30 | 2021-11-04 | 深圳中砼物联网科技有限公司 | Multi-source heterogeneous data processing method, computer device, and storage medium |
| CN112346618A (en) * | 2020-11-11 | 2021-02-09 | 广州小鹏汽车科技有限公司 | Vehicle service processing method and device |
| CN112685154A (en) * | 2020-12-25 | 2021-04-20 | 北京有竹居网络技术有限公司 | Data processing method of task flow engine, device and medium |
| CN112652012A (en) * | 2020-12-31 | 2021-04-13 | 北京百度网讯科技有限公司 | Intelligent control method, device and equipment for excavator, storage medium and excavator |
| CN112836404A (en) * | 2021-01-07 | 2021-05-25 | 大连理工大学 | Method for constructing digital twin body of structural performance of intelligent excavator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200249936A1 (en) | Method and system for a platform for api based user supplied algorithm deployment | |
| CN108153670A (en) | A kind of interface test method, device and electronic equipment | |
| CN110909942B (en) | Method and system for training model and method and system for predicting sequence data | |
| CN112988130A (en) | Visual modeling method, device, equipment and medium based on big data | |
| CN110377209B (en) | Method and device for realizing visual flow configuration through dragging | |
| KR20210091682A (en) | Method and apparatus for acquiring sample deviation data, and electronic device | |
| EP3869404A2 (en) | Vehicle loss assessment method executed by mobile terminal, device, mobile terminal and medium | |
| US20230092453A1 (en) | Parameter updating method and apparatus and storage medium | |
| CN115113528B (en) | Operation control method, device, equipment and medium of neural network model | |
| CN114787738A (en) | Formally secure tokenized reinforcement learning for visual input | |
| CN115437339A (en) | Remote diagnosis method and device, electronic equipment and storage medium | |
| CN114417780B (en) | State synchronization method and device, electronic equipment and storage medium | |
| CN114296716A (en) | Function configuration method and device for intelligent operation of engineering machinery and electronic equipment | |
| CN105027089B (en) | Core functions detector | |
| CN114610200A (en) | Intelligent control method and device for engineering mechanical equipment and engineering mechanical equipment | |
| CN116481513A (en) | Map generation method and device and electronic equipment | |
| CN115543534A (en) | Training task management method and device, electronic equipment and storage medium | |
| CN115269285A (en) | Test method and device, equipment and computer readable storage medium | |
| CN111768007B (en) | Method and device for mining data | |
| CN116627434B (en) | Model deployment service method, electronic equipment and medium | |
| KR20200051278A (en) | Method of managing task in artificial neural network and system comprising the same | |
| CN115576205B (en) | Feedback control method, universal feedback controller, training method, readable storage medium, computer program product and system | |
| CN114936052B (en) | Model visualization method, system and related equipment | |
| CN117909165A (en) | Data acquisition method and device, electronic equipment and storage medium | |
| CN116795611A (en) | Test method, test device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |