CN116243609B - Intelligent loading control method and system based on multidimensional data chain - Google Patents
Intelligent loading control method and system based on multidimensional data chain Download PDFInfo
- Publication number
- CN116243609B CN116243609B CN202310530019.6A CN202310530019A CN116243609B CN 116243609 B CN116243609 B CN 116243609B CN 202310530019 A CN202310530019 A CN 202310530019A CN 116243609 B CN116243609 B CN 116243609B
- Authority
- CN
- China
- Prior art keywords
- data
- loading
- dimensional
- rule
- space
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to an intelligent loading control method and system based on a multidimensional data chain. An intelligent loading control method based on a multidimensional data chain comprises the steps of obtaining radar point cloud data, and carrying out standardization and data compression on Lei Dadian cloud data to obtain three-dimensional geometric information; generating a standard loading flow by using the acquired radar point cloud data; according to the three-dimensional geometric information, the related data in the three-dimensional space is analyzed according to the time dimension, and the invention can promote the artificial intelligent module to perform self-perfection and data correction through the geometric features of the multi-dimensional data structure under the condition of no manual intervention.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent loading control method and system based on a multidimensional data chain.
Background
In the prior art, when the existing AI processing module is directly used in the similar actual production scenes such as automatic loading control, a large amount of historical control data is firstly required to be input into a corresponding AI processing program to perform corresponding model training, and then the actual control effect is generated through accumulation of the model training. When the control process is needed to be participated in, the AI program can carry out real-time feedback according to the input relevant parameters, such as the information of the vehicle position, the material height, the material flow rate and the like and the rules set by the training model.
However, when the input parameters are out of expectation or the training data is insufficient, the feedback result of the AI process is often unpredictable. For example, when the material height of the vehicle at 1m exceeds the limit, the historical control data is positively fed back, and the AI can output the same positive feedback control for similar scenes. However, when the vehicle is located at 2m and the vehicle is moving due to insufficient material height, if no corresponding historical data is used for model training, the AI response is often unknown, and the unknown feedback often means the occurrence of dangerous accidents in the actual production environment.
Moreover, because the AI itself lacks the actual logic judgment capability, the conditions such as the material level overrun or the material level shortage have no practical significance for the AI, the AI only feeds back the set logic, and the risk prediction can not be intelligently and timely made according to the real-time change of the actual condition. This results in the problem that AI can handle, which is actually happening, when it faces an unknown problem, all feedback results are logical-free, unknown, unpredictable.
In summary, conventional artificial intelligence systems based on model training and artificial tuning do not have commercial value for practical application in a production environment, and are mainly characterized in that:
1. the parameter adjustment and model training system is too complicated and has high cost.
2. The feedback result of the intelligent system on the input information only depends on the integrity of model training, real data which can be changed at any time in the actual working process is difficult to accurately process, and when the input information exceeds the expected value, the feedback result of the system is often uncontrollable.
3. The intelligent system in the traditional sense is complex and perfect in design, the only power for driving the intelligent system to complete work is to analyze the input result, and the quality of the analysis result cannot be judged effectively, so that the intelligent system lacks an effective self-perfecting way.
4. The perfecting process of the intelligent system needs to input various data models for training, so that the resources occupied by the models in the system are increased, and the feedback speed of the whole system is slowed down. In order to maintain effective feedback of the system, the system has to be continuously built and a huge database is maintained, thereby greatly increasing the operation cost of the system.
5. The system itself cannot make effective judgment on effective or ineffective data models and historical data, so that the growth of the system is irreversible, that is, the data models are only increased, and effective refinement and reduction cannot be achieved. This results in an increasing redundancy of the system, which eventually leads to an increasingly difficult system feedback to predict, even in the event of some uncontrolled accidents.
Disclosure of Invention
In order to solve the above-mentioned problems, the invention provides an intelligent loading control method and system based on a multidimensional data chain.
In a first aspect, the invention provides an intelligent loading control method based on a multidimensional data chain, which adopts the following technical scheme:
an intelligent loading control method based on a multidimensional data chain comprises the following steps:
acquiring Lei Dadian cloud data, and carrying out standardization and data compression on Lei Dadian cloud data to obtain three-dimensional geometric information;
generating a standard loading flow by using the acquired radar point cloud data;
according to the three-dimensional geometric information, analyzing related data in a three-dimensional space according to a time dimension, and generating a loading rule formulated according to a geometric proportion relation;
according to a standard loading flow, correlating the three-dimensional geometric information of the vehicle with an operation instruction corresponding to a loading rule in a time dimension to form an operation data chain;
and intelligently adjusting an operation data chain according to the loading rule.
Further, the generating a standard loading process by using the acquired radar point cloud data comprises creating a multi-dimensional data space, creating a four-dimensional data space in the multi-dimensional data space, and generating a standard loading process by using the acquired radar point cloud data.
Further, the creation of the multidimensional data space includes designing a related geometry structure, constituting a complete program logic and data chain.
Further, the four-dimensional data space includes a three-dimensional space and a time dimension.
Further, the analyzing the related data in the three-dimensional space according to the time dimension includes analyzing the material height, the residual height in the carriage and the carriage displacement data in the three-dimensional space according to the three-dimensional geometric information.
Further, the triggering rule in the operation data chain is intelligently adjusted according to the point cloud result after loading, and the triggering rule comprises the node position of the time dimension of the triggering instruction is advanced or delayed according to the standard point cloud data.
Further, the intelligent adjustment of the operation data chain according to the loading rule comprises intelligent adjustment of an operation instruction according to the three-dimensional geometric information after loading, and the operation data chain update is completed by inputting the operation instruction into the operation data chain.
In a second aspect, an intelligent loading control system based on a multidimensional data chain, comprising:
the data acquisition module is configured to acquire Lei Dadian cloud data, normalize the Lei Dadian cloud data and compress the data to obtain three-dimensional geometric information;
the space construction module is configured to generate a standard loading flow by using the acquired radar point cloud data;
the rule module is configured to analyze related data in the three-dimensional space according to the three-dimensional geometric information and the time dimension and generate a loading rule formulated according to the geometric proportion relation;
the data link module is configured to correlate the three-dimensional geometric information of the vehicle with the operation instruction corresponding to the loading rule in the time dimension according to the standard loading process to form an operation data link;
and the intelligent adjustment module is configured to intelligently adjust the operation data chain according to the loading rule.
In a third aspect, the present invention provides a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded and executed by a processor of a terminal device for said intelligent loading control method based on a multidimensional data chain.
In a fourth aspect, the present invention provides a terminal device, including a processor and a computer readable storage medium, where the processor is configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the method of intelligent loading control based on a multi-dimensional data chain.
In summary, the invention has the following beneficial technical effects:
the intelligent control method can automatically judge the type and the direction of the interference control which is required to be made by maintaining the integrity of the geometric structure according to the interrelationship between the geometric structures of the actual objects mapped in the multidimensional data space. If the loading level is too high and the risk of bulk cargo is about to occur, the control program can judge that the geometric structure of the vehicle is about to be destroyed (scattering material), and can change the control direction into control of the vehicle to advance, close or reduce the flashboard and the like to meet the expected logic result. When the material level in the vehicle is insufficient, and a driver can lift the vehicle by himself, the defect can be intuitively generated on the target geometric structure of the data space, namely, the material level mapped by the radar point cloud is insufficient, so that the geometric structure of the area is deficient in height, and at the moment, a control program is triggered to call the vehicle to stop, supplement the deficient material and other related operations conforming to expected logic results.
The intelligent control system can consciously self-perfect the design of the system and the feedback logic of the data, even can perfect the response speed of the system by summarizing and simplifying the historical data, and summarize the potential rules in the complex redundant data model, thereby completing the overall working efficiency of the feedback system and reducing the storage cost of the data.
Drawings
Fig. 1 is a schematic diagram of an intelligent loading control method based on a multidimensional data chain according to embodiment 1 of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example 1
Referring to fig. 1, an intelligent loading control method based on a multidimensional data chain according to the present embodiment includes:
acquiring Lei Dadian cloud data, and carrying out standardization and data compression on Lei Dadian cloud data to obtain three-dimensional geometric information;
generating a standard loading flow by using the acquired radar point cloud data;
according to the three-dimensional geometric information, analyzing related data in a three-dimensional space according to a time dimension, and generating a loading rule formulated according to a geometric proportion relation;
according to a standard loading flow, correlating the three-dimensional geometric information of the vehicle with an operation instruction corresponding to a loading rule in a time dimension to form an operation data chain;
and intelligently adjusting an operation data chain according to the loading rule.
The method comprises the steps of creating a multi-dimensional data space, creating a four-dimensional data space in the multi-dimensional data space, and generating a standard loading process by using the acquired radar point cloud data.
The creation of the multidimensional data space, including designing the associated geometry, constitutes complete program logic and data chains.
The four-dimensional data space includes a three-dimensional space and a time dimension.
And analyzing the related data in the three-dimensional space according to the time dimension, wherein the analysis comprises the step of analyzing the material height, the residual height in the carriage and the carriage displacement data in the three-dimensional space according to the three-dimensional geometric information.
The triggering rules in the operation data chain are intelligently adjusted according to the point cloud result after loading, and the triggering rules comprise node positions of the time dimension of the triggering instruction are advanced or delayed according to the standard point cloud data.
The intelligent adjustment of the operation data chain according to the loading rule comprises intelligent adjustment of an operation instruction according to the three-dimensional geometric information after loading, and the operation data chain updating is completed by inputting the operation instruction into the operation data chain.
Specifically, the method comprises the following steps:
s1, acquiring Lei Dadian cloud data, and carrying out standardization and data compression on Lei Dadian cloud data to obtain three-dimensional geometric information;
patent number CN202211298492.8, a multidimensional information fusion method based on various types of data acquisition equipment, and patent number CN202211373020.4, a point cloud data processing method and a system based on multidimensional point cloud fusion data comprehensively disclose how to perform standardized processing and data compression on Lei Dadian cloud tree bureau to obtain three-dimensional geometric information. By using the methods in the two patents, the point cloud data is standardized and compressed, and finally an abstract three-dimensional geometric proportion graph formed by data space coordinates is generated, so that three-dimensional geometric information is obtained.
The standard loading flow is a loading function call sequence stored in a data chain form, and Lei Dadian cloud data, loading data and information thereof are interaction parameters of the functions. The standardized sequence is a general sequence of the loading process, and comprises the most basic operation process and data interaction.
The information here refers to the relevant geometric data of the vehicle, displacement data in the loading process, wagon balance data and the like, and all relevant data can be acquired according to different production scenes.
The general standardized loading sequence refers to a standard operation flow of correct loading with the least unexpected phenomenon, the simplest loading instruction and no unexpected situation, and the related operation sequence converted from the flow is called a standardized sequence.
S2, generating a standard loading flow by using the acquired radar point cloud data;
wherein, by the method described in CN202310015225.3, a self-configuration method, a self-configuration system and a storage medium for functions of an application system, a multidimensional data space is created in a computer, and related geometric structures are designed to form a complete program logic and a data chain.
Creating a four-dimensional data space (three-dimensional space plus time dimension) in the multi-dimensional data space, and generating a standard loading flow record by using the laser radar point cloud data recorded in the loading process.
S3, according to the three-dimensional geometric information, analyzing related data in the three-dimensional space according to the time dimension, and generating a loading rule formulated according to the geometric proportion relation;
and analyzing the related data in the three-dimensional space according to the time dimension, wherein the analysis comprises the step of analyzing the material height, the residual height in the carriage and the carriage displacement data in the three-dimensional space according to the three-dimensional geometric information. The method comprises the steps of generating and compensating a standard lattice sequence according to point cloud data in a three-dimensional data space, and calculating and identifying the composition information (geometric information parameters) and displacement data of a carriage by using the space lattice sequence. And calculating the specific carriage state and the triggering condition of the loading action according to the proportional relation (the three-dimensional coordinate axis and the coordinate scale thereof). And generates it as a specific rule. For example, when the carriage reaches the coordinate position XXX, the lifting operation is triggered after the material height reaches XXX.
And analyzing related data such as material height, residual height in a carriage, carriage displacement and the like in the three-dimensional space according to the time dimension, and generating a loading rule formulated according to the geometric proportion relation. For example, when the vehicle is displaced at the time point A, the proportional relation between the material height and the residual height in the carriage is found before the time point A, and the mark triggers the vehicle lifting instruction when the condition is met.
S4, according to a standard loading flow, correlating the three-dimensional geometric information of the vehicle with an operation instruction corresponding to a loading rule in a time dimension to form an operation data chain;
wherein, the geometric information parameter of the vehicle is obtained by the last step.
The time dimension association refers to different states of the geometric information parameter in the multidimensional data space at different moments, and the states are automatically associated by time attributes of the multidimensional data space.
The operation data chain and the operation instruction are associated by recording function operation information, and the operation data chain and the operation instruction are specifically completed by the last step.
When the operation instruction is triggered, different geometric information parameters are used as starting conditions for triggering the execution of the function, such as triggering the lifting function when the material height is higher than a certain value.
The geometric information parameters of the vehicle are associated with the operation instructions in the time dimension to form an operation data chain, the operation instructions are triggered according to the input loading point cloud in the intelligent loading process, and the execution time of the instructions, such as the time interval for opening and closing the chute, is adjusted according to the time dimension.
S5, intelligently adjusting an operation data chain according to the loading rule.
And intelligently adjusting a trigger rule in the instruction data chain according to the point cloud result after loading, such as advancing or postponing the node position of the time dimension of the trigger instruction. In this process, the standard point cloud input in step 2 is the basis for triggering the system to perform intelligent adjustment, and the final working result is based on the point cloud, and the working result is more close to the standard expectation by adjusting the working parameters of the point cloud.
As described above, when the system finds that the triggering rule causes an accident to occur, such as when the driver has a slow reaction speed, the set lift level triggering condition may no longer be applicable to the current condition. The program can trigger and change the setting of the lifting material level by monitoring the multidimensional geometric information of the multidimensional data space, for example, the time from sending the lifting message to monitoring the movement of the vehicle is longer, or when the material level reaches the warning material level, the condition of reducing the lifting material level to avoid risks can be triggered, so that the loading rule is temporarily changed.
And when this happens multiple times (where a trigger threshold may be set), the program will trigger a condition that permanently alters a certain rule.
When the loading instruction is changed, the system can automatically complete learning and update operation steps only by inputting a new operation rule into the multidimensional data space, and a more complete and complex intelligent space data chain is generated. For example, when the car is offset, the first few frames of the input point cloud trigger a command to adjust the car. The matching of the triggering condition of the instruction and the instruction only needs to input a multidimensional data space, and the system can find the triggering rule for a new instruction by itself, namely, different points are searched after the same geometric characteristic parameters are eliminated, and the triggering rule is related to the new instruction. The whole process is completed by the intelligent system in the multidimensional data space without manual intervention or updating or changing the program code.
The multi-dimensional geometric information of the vehicle is used as a trigger condition and a verification result of the previous operation, and when the intrinsic rule is influenced (as described above, the adjustment of the data chain is triggered due to the change of some rules, such as the lowering of the level of the lifting vehicle), the partial setting or the sequence of function triggering in the data chain can be adjusted according to the change of the related rule.
For example, when the material is scattered due to the delay of the lifting operation during the loading process, if the original data chain does not contain the abnormal processing, the loading process fails. At this time, the system increases a processing sequence when the material level reaches the warning value, and actions to be executed by the sequence are based on reducing or stopping blanking, so that the processing sequence is sequentially invoked according to priority in related operation functions of reducing the opening and closing degree of the flashboard, closing the flashboard and the like.
When the level reaches the warning value again, the system can trigger the related flashboard operation to verify the feasibility of the operation. If the operation meets the expectations, the rule is reserved and updated in the main data chain, otherwise, the rule is continuously adjusted, or a new function meeting the corresponding requirement is searched for, and the reordering call is carried out until the loading target is achieved.
If the adjustment is not capable of meeting the requirements all the time, the system can send out corresponding defect warning, apply for manual participation and add a new function.
As a further embodiment of the method of the present invention,
the geometry of the multidimensional data is used to simulate the working result of the target. Taking an automatic loading program as an example, firstly, the geometric structure of a carriage is simulated by using multidimensional data, then, the distribution of materials in the carriage is simulated, the result is regarded as an optimal feedback result, and real-time feedback data of loading is automatically checked according to the result.
Because the simulated loading data is the result of the simulation of the multidimensional data, the information held by the simulated loading data only comprises the length, width and height proportions of the carriage, the height proportions of the materials in the carriage, the rough shape and the like. Rather than fixed, dead input type data. Therefore, in the process of checking the loading result in real time, the system does not check the dead plate numerical value, but can flexibly adjust the loading process in real time according to the change of the carriage height.
When the loading result exceeds the expected value, timely feedback is made, and the time point and related parameters of the feedback are automatically recorded. In the next loading process, intelligent adjustment is carried out on the loading process according to the parameters, and finally the degree consistent with the designed loading model target is achieved.
The whole process of observing and adjusting the loading algorithm is unnecessary to be manually participated in the whole process, and the driving algorithm makes real-time change of the simulation target of the multidimensional data model only. The observed visual data is compared with the multi-dimensional space simulation result in the computer, and the improvement of the algorithm is driven by the comparison.
The improved results of the algorithm and the adjustment of parameters are maintained in the computer in the form of a multidimensional data chain during which the data chain is adjusted using various regular geometric structures, such as: geometry A and geometry B are suitable for node B in the data chain, and the data chain can be more perfect by respectively calling algorithms in geometry A and geometry B and observing different feedback results.
The result of calculation and adjustment only needs to aim at geometry and data chain in the multidimensional data space, and does not need to add more redundant data models or change the logic structure of the program, so that the method has the advantages of small input data volume, flexible expansion, convenient configuration, stronger program performance and calculation concentration, and the like.
Example 2
The embodiment provides an intelligent loading control system based on multidimensional data chain, which comprises:
the data acquisition module is configured to acquire Lei Dadian cloud data, normalize the Lei Dadian cloud data and compress the data to obtain three-dimensional geometric information;
the space construction module is configured to generate a standard loading flow by using the acquired radar point cloud data;
the rule module is configured to analyze related data in the three-dimensional space according to the three-dimensional geometric information and the time dimension and generate a loading rule formulated according to the geometric proportion relation;
the data link module is configured to correlate the three-dimensional geometric information of the vehicle with the operation instruction corresponding to the loading rule in the time dimension according to the standard loading process to form an operation data link;
and the intelligent adjustment module is configured to intelligently adjust the operation data chain according to the loading rule.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded and executed by a processor of a terminal device for said intelligent loading control method based on a multi-dimensional data chain.
A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the method of intelligent loading control based on a multi-dimensional data chain.
The above embodiments are not intended to limit the scope of the present invention, so: all equivalent changes in structure, shape and principle of the invention should be covered in the scope of protection of the invention.
Claims (5)
1. An intelligent loading control method based on a multidimensional data chain is characterized by comprising the following steps:
acquiring Lei Dadian cloud data, and carrying out standardization and data compression on Lei Dadian cloud data to obtain three-dimensional geometric information;
generating a standard loading flow by using the acquired radar point cloud data;
according to the three-dimensional geometric information, analyzing related data in a three-dimensional space according to a time dimension, and generating a loading rule formulated according to a geometric proportion relation;
according to a standard loading flow, correlating the three-dimensional geometric information of the vehicle with an operation instruction corresponding to a loading rule in a time dimension to form an operation data chain;
intelligently adjusting an operation data chain according to a loading rule;
analyzing relevant data in a three-dimensional space according to a time dimension, including analyzing material height, residual height in a carriage and carriage displacement data in the three-dimensional space according to three-dimensional geometric information, generating and compensating for a standard lattice sequence according to point cloud data in the three-dimensional data space, calculating and identifying composition information and displacement data of the carriage by using the lattice sequence, calculating specific carriage states and triggering conditions of loading actions according to a proportional relation, and generating the specific conditions into specific rules;
creating a four-dimensional data space in the multi-dimensional data space, namely, a three-dimensional space and a time dimension, and generating a standard loading flow record by using laser radar point cloud data recorded in the loading process;
the geometric information parameters of the vehicle are associated with the operation instructions in the time dimension to form an operation data chain, the operation instructions are triggered according to the input loading point cloud in the intelligent loading process, and the execution time of the instructions is adjusted according to the time dimension, wherein the execution time comprises the time interval for opening and closing the chute;
intelligently adjusting a trigger rule in an instruction data chain according to a loading rule, wherein the trigger rule comprises a node position of a time dimension of a trigger instruction in advance or delayed;
when the loading instruction changes, only a new operation instruction is required to be input into the multidimensional data space, so that the system can automatically complete learning and update operation steps, an intelligent space data chain is generated, when the carriage is deviated, the first frames of the input point cloud trigger an instruction for adjusting the carriage, the triggering condition of the instruction and the matching of the instruction only need to be input into the multidimensional data space, and the system automatically finds a triggering rule aiming at the new instruction;
when the material scattering caused by the delay of the lifting action is found in the loading process, if the original data chain does not contain abnormal processing to cause failure of the loading process, the system increases a processing sequence when the material level reaches the warning value, and the action required to be executed by the sequence is based on the reduction or stopping of the blanking, so that the operations are sequentially called according to the priority in the related operation functions of reducing the opening and closing of the flashboard;
when the level reaches the warning value again, the system can trigger the related flashboard operation to verify the feasibility of the operation, if the operation meets the expectations, the rule is reserved and updated into the main data chain, otherwise, the rule is continuously adjusted, or a new function meeting the corresponding requirement is searched for, and the reordering call is carried out until the loading target is achieved.
2. The intelligent loading control method based on the multidimensional data link according to claim 1, wherein the creating a four-dimensional data space in the multidimensional data space comprises designing a related geometrical structure to form a complete program logic and data link.
3. An intelligent loading control system based on a multidimensional data chain, which is based on the intelligent loading control method based on the multidimensional data chain as recited in claim 1, and is characterized by comprising the following steps:
the data acquisition module is configured to acquire Lei Dadian cloud data, normalize the Lei Dadian cloud data and compress the data to obtain three-dimensional geometric information;
the space construction module is configured to generate a standard loading flow by using the acquired radar point cloud data;
the rule module is configured to analyze related data in the three-dimensional space according to the three-dimensional geometric information and the time dimension and generate a loading rule formulated according to the geometric proportion relation;
the data link module is configured to correlate the three-dimensional geometric information of the vehicle with the operation instruction corresponding to the loading rule in the time dimension according to the standard loading process to form an operation data link;
and the intelligent adjustment module is configured to intelligently adjust the operation data chain according to the loading rule.
4. A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform a multi-dimensional data chain based intelligent loading control method according to claim 1.
5. A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform a multi-dimensional data chain based intelligent launch control method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310530019.6A CN116243609B (en) | 2023-05-12 | 2023-05-12 | Intelligent loading control method and system based on multidimensional data chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310530019.6A CN116243609B (en) | 2023-05-12 | 2023-05-12 | Intelligent loading control method and system based on multidimensional data chain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116243609A CN116243609A (en) | 2023-06-09 |
| CN116243609B true CN116243609B (en) | 2023-08-29 |
Family
ID=86629949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310530019.6A Active CN116243609B (en) | 2023-05-12 | 2023-05-12 | Intelligent loading control method and system based on multidimensional data chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116243609B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU1791288C (en) * | 1989-11-01 | 1993-01-30 | Днепропетровский горный институт им.Артема | Apparatus for controlling railway car vibratory feeder |
| CN111487918A (en) * | 2020-04-26 | 2020-08-04 | 天地科技股份有限公司 | Bulk material unmanned loading control method, system and device based on multi-line laser radar |
| CN114067076A (en) * | 2021-10-11 | 2022-02-18 | 中煤科工智能储装技术有限公司 | Self-adaptive adjustment method for uniform loading and distribution of bulk materials |
| CN114781046A (en) * | 2022-06-22 | 2022-07-22 | 中交第四航务工程勘察设计院有限公司 | BIM technology-based automatic container terminal management method and system |
| CN114781761A (en) * | 2022-06-21 | 2022-07-22 | 天津港第二集装箱码头有限公司 | Real-time adjustment method for loading and unloading ship operation plan by adopting simulation rehearsal |
| CN115049345A (en) * | 2022-08-15 | 2022-09-13 | 山东矩阵软件工程股份有限公司 | Multidimensional data summarizing and comprehensive measurement and control method and system for logistics transportation |
| CN115795677A (en) * | 2022-11-28 | 2023-03-14 | 中建材凯盛机器人（上海）有限公司 | Self-adaptive loading model algorithm and system |
| CN115838084A (en) * | 2022-11-10 | 2023-03-24 | 山东矩阵软件工程股份有限公司 | Automatic material loading method and system and related device |
-
2023
- 2023-05-12 CN CN202310530019.6A patent/CN116243609B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU1791288C (en) * | 1989-11-01 | 1993-01-30 | Днепропетровский горный институт им.Артема | Apparatus for controlling railway car vibratory feeder |
| CN111487918A (en) * | 2020-04-26 | 2020-08-04 | 天地科技股份有限公司 | Bulk material unmanned loading control method, system and device based on multi-line laser radar |
| CN114067076A (en) * | 2021-10-11 | 2022-02-18 | 中煤科工智能储装技术有限公司 | Self-adaptive adjustment method for uniform loading and distribution of bulk materials |
| CN114781761A (en) * | 2022-06-21 | 2022-07-22 | 天津港第二集装箱码头有限公司 | Real-time adjustment method for loading and unloading ship operation plan by adopting simulation rehearsal |
| CN114781046A (en) * | 2022-06-22 | 2022-07-22 | 中交第四航务工程勘察设计院有限公司 | BIM technology-based automatic container terminal management method and system |
| CN115049345A (en) * | 2022-08-15 | 2022-09-13 | 山东矩阵软件工程股份有限公司 | Multidimensional data summarizing and comprehensive measurement and control method and system for logistics transportation |
| CN115838084A (en) * | 2022-11-10 | 2023-03-24 | 山东矩阵软件工程股份有限公司 | Automatic material loading method and system and related device |
| CN115795677A (en) * | 2022-11-28 | 2023-03-14 | 中建材凯盛机器人（上海）有限公司 | Self-adaptive loading model algorithm and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于IO-Link技术的散粮智能装车系统;刘子彬;《港口装卸》;第44-46+60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116243609A (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113552840B (en) | Machining control system | |
| US20230315062A1 (en) | Industrial internet of things, mthods and mediums for early warning of descending function fault of equipment | |
| CN107423205B (en) | System fault early warning method and system for data leakage prevention system | |
| CN106874483A (en) | A kind of device and method of the patterned quality of data evaluation and test based on big data technology | |
| AU2017202306B2 (en) | System and method for analyzing operation of component of machine | |
| WO2022193925A1 (en) | Correction method and device for luffing boom of heavy machinery | |
| CN112712305B (en) | Aircraft system and health assessment method and device thereof | |
| CN112164141B (en) | Machine room management method, device, equipment and storage medium based on BIM technology | |
| CN116700092B (en) | Operation control intelligent early warning system suitable for industrial personal computer | |
| CN117010867B (en) | Packaging equipment monitoring system based on data analysis | |
| CN115562225A (en) | Industrial robot operation and maintenance management method and device, computer equipment and storage medium | |
| CN111586155A (en) | Vehicle data processing method and system | |
| CN116243609B (en) | Intelligent loading control method and system based on multidimensional data chain | |
| CN115511186A (en) | Prediction management method, device and equipment for deep learning training duration | |
| US20240201156A1 (en) | Methods and internet of things systems for visual management of smart gas data center processes | |
| CN108595959B (en) | AADL model security evaluation method based on deterministic stochastic Petri network | |
| CN114139767A (en) | Health trend prediction method and system for equipment, computer equipment and storage medium | |
| CN118101697A (en) | Intelligent gateway data processing method with edge computing power | |
| CN113761802A (en) | Nuclear power structural material data performance prediction model and model construction method | |
| CN116541717A (en) | Big data analysis method based on cloud computing and deep learning | |
| CN111898993A (en) | Operation ticket management system | |
| CN117149410A (en) | AI intelligent model based training, scheduling, commanding and monitoring system | |
| CN109522536B (en) | Automatic form filling method | |
| CN114446027A (en) | Equipment fault alarm method, system, equipment and medium based on Internet of things | |
| CN117556187B (en) | Cloud data restoration method and system based on deep learning and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |