CN117590752B - Multi-axis cooperative control method and system based on action decomposition - Google Patents
Multi-axis cooperative control method and system based on action decomposition Download PDFInfo
- Publication number
- CN117590752B CN117590752B CN202410057248.5A CN202410057248A CN117590752B CN 117590752 B CN117590752 B CN 117590752B CN 202410057248 A CN202410057248 A CN 202410057248A CN 117590752 B CN117590752 B CN 117590752B
- Authority
- CN
- China
- Prior art keywords
- subtask
- cooperative control
- information
- axis
- task
- 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
- 230000009471 action Effects 0.000 title claims abstract description 179
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013210 evaluation model Methods 0.000 claims abstract description 49
- 230000033001 locomotion Effects 0.000 claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims description 89
- 230000002159 abnormal effect Effects 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 13
- 238000007726 management method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 abstract description 5
- 230000001419 dependent effect Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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)
- Feedback Control In General (AREA)
Abstract
The invention discloses a multi-axis cooperative control method and system based on action decomposition, and relates to the technical field of multi-axis control. According to the method, the task actions are divided through the action decomposition factors, the complexity of the whole system is reduced, the subtasks with execution sequences are ordered according to the subtask complexity index and the axis action threshold value, the workload and the complexity of the subtasks are prevented from being too high or too low, task action abnormality is prevented from being caused, the subtask planning efficiency is improved according to the subtask priority index, the multi-axis cooperative control is evaluated according to the multi-axis cooperative control robust evaluation model, the multi-axis cooperative control is adjusted, and the motion of each axis is accurately controlled, so that higher precision and stability are achieved.
Description
Technical Field
The invention relates to the technical field of multi-axis control, in particular to a multi-axis cooperative control method and system based on action decomposition.
Background
In recent years, with the continuous increase of the process requirements of products in the industrial field and the rapid increase of production scale, in order to obtain higher processing precision, the importance of the synergy among subsystems in the production and manufacturing stage is highlighted, in multi-axis motion control, people are always striving to obtain higher motion control precision, so that the actual motion of each axis can track an input signal more accurately, however, due to the problems of delay of a servo system, unavoidable friction of a mechanical structure and reverse clearance of a transmission system, the problem to be solved still exists in accurately tracking a planned path to obtain a high-precision track, the multi-axis cooperative control technology is used as a comprehensive technology of one-step disciplinary, and is widely applied in the fields of multi-variable control such as multi-robot system coordination control, aerospace, cooperative control of a shaftless transmission printer servo system, numerical control system position control and the like, so that a plurality of practical engineering problems are solved, the high-efficiency and stable operation of the production line is ensured, and huge benefits are brought to the social economic development.
At present, the multi-axis cooperative control has the problems that the task actions cannot be accurately and reasonably decomposed, the subtasks divided by the task actions cannot fully utilize the diversity and the resources of the system, the workload and the complexity of the subtasks cannot be fully coordinated, the management and the control are difficult, the errors in the cooperative control cannot be accurately evaluated, and the abnormality cannot be timely found.
Disclosure of Invention
In order to solve the technical problems, the technical scheme solves the problems that in the background technology, the task action cannot be accurately and reasonably decomposed, the subtasks divided by the task action cannot fully utilize the diversity and the resources of the system, the workload and the complexity of the subtasks cannot be fully coordinated, the management and the control are difficult, the errors in the cooperative control cannot be accurately evaluated, and the abnormality cannot be timely found.
In order to achieve the above purpose, the invention adopts the following technical scheme:
The multi-axis cooperative control method based on action decomposition comprises the following steps: task action information is obtained, wherein the task action information comprises action content information and action request information;
acquiring shaft function information, wherein the shaft function information comprises shaft position information, shaft state information corresponding to each shaft and shaft action information;
acquiring subtask information based on action decomposition according to task action information and shaft function information;
acquiring an action priority index based on the evaluation model according to the subtask information;
Planning the subtasks based on the action priority index to obtain subtask planning information;
acquiring cooperative control scheme information based on a task planning index according to the subtask planning information;
According to the cooperative control scheme information, performing multi-axis cooperative control to obtain multi-axis cooperative control data;
Acquiring multi-axis cooperative control historical data, wherein the multi-axis cooperative control historical data comprises cooperative axis action data and cooperative axis management data;
training the evaluation model according to the multi-axis cooperative control historical data to obtain a multi-axis cooperative control robust evaluation model;
acquiring cooperative control robust evaluation data according to the multi-axis cooperative control data and the multi-axis cooperative control robust evaluation model;
acquiring a cooperative control robust evaluation threshold based on the multi-axis cooperative control requirement and actual equipment parameters;
And adjusting the multi-axis cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold.
Preferably, the acquiring subtask information based on action decomposition according to the task action information and the shaft function information specifically includes:
According to the task action information, an action decomposition factor is obtained, wherein the action decomposition factor comprises task action step information, task action decision point information and task action related information;
Acquiring a shaft action threshold based on actual control requirements according to the shaft function information;
acquiring subtask information based on task division according to the action decomposition factors;
Acquiring a subtask complexity index according to the subtask information;
judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold, if not, enabling the subtask to be achieved, if so, enabling the subtask to be not achieved, and re-decomposing and re-judging the task action;
The subtask complex index calculation formula is as follows:
；
Where Q is the sub-task complexity index, Weight of the ith subtask type,/>For the workload of the ith subtask,/>Is the weight of the task association degree,/>Representing the association of the ith subtask with the z-th subtask, wherein/>And/>N is the total number of subtasks.
Preferably, the planning of the subtasks based on the action priority index, to obtain the subtask planning information, specifically includes:
Acquiring sub-task order information according to the sub-task information, wherein the sub-task order information comprises sub-task dependency information and sub-task parallel information;
Sequencing the subtasks with the execution sequence according to the subtask dependency information to obtain subtask sequencing information;
Acquiring a subtask order evaluation index according to the subtask ordering information, wherein the higher the subtask order evaluation index is, the earlier the task ordering of the subtask is;
Acquiring a subtask priority index according to the subtask parallel information and the subtask order evaluation index;
According to the subtask priority index, adjusting the parallel subtasks to obtain subtask planning information;
the calculation formula of the subtask priority index is as follows:
；
In the method, in the process of the invention, For the subtask priority index of the ith subtask,/>The weights of the indices are evaluated for the order of the subtasks,Assessment index for the order of the subtasks of the ith subtask,/>Weight for the ith subtask workload,/>For the workload of the ith subtask,/>Weight for the ith subtask complexity,/>For the association degree of the jth subtask with the dependent relation with the ith subtask, m is the total number of the subtasks with the dependent relation with the ith subtask.
Preferably, the acquiring cooperative control scheme information based on the task planning index according to the subtask planning information specifically includes:
predicting the sub-action completion state according to the sub-task planning information and the shaft function information to obtain sub-task prediction data;
evaluating the subtask planning according to the subtask prediction data to obtain a task planning index;
Acquiring a task planning index threshold based on the multi-axis cooperative control requirement;
Judging whether the task planning index is lower than the task planning index threshold according to the task planning index and the task planning index threshold, if yes, not conforming to the actual cooperative control requirement by sub-task planning, and if not, acquiring cooperative control scheme information according to the sub-task planning information;
the calculation formula of the task planning index is as follows:
；
In the method, in the process of the invention, Planning an index for a mission,/>Weight for the ith subtask response time,/>For the response time of the ith subtask,/>Weighting of data transitivity for the ith subtask and for the jth subtask associated with the ith subtask,/>For the ith subtask and the data transitivity associated with the ith subtask for the jth subtask,/>Weights affecting the index for task actions,/>Predicting data for the ith subtask,/>Planning data for the ith subtask,/>Is the influence coefficient of the j-th subtask with a dependency relationship with the i-th subtask.
Preferably, the obtaining the cooperative control robust evaluation data according to the multi-axis cooperative control data and the multi-axis cooperative control robust evaluation model specifically includes:
Acquiring a multi-axis cooperative control historical data average value and a multi-axis cooperative control historical data standard deviation according to the multi-axis cooperative control historical data;
Detecting abnormal values of the multi-axis cooperative control historical data according to the multi-axis cooperative control historical data average value and the multi-axis cooperative control historical data standard deviation to obtain multi-axis cooperative control historical abnormal data;
according to the multi-axis cooperative control historical abnormal data, abnormal value rejection is carried out on the multi-axis cooperative control historical data, and multi-axis cooperative control historical standard data are obtained;
Training the evaluation model according to the multi-axis cooperative control historical standard data to obtain a multi-axis cooperative control robust evaluation model;
acquiring shaft state data and shaft speed data according to the multi-shaft cooperative control data;
Acquiring cooperative control robust evaluation data based on a multi-axis cooperative control robust evaluation model according to the axis state data and the axis speed data;
the multi-axis cooperative control robust evaluation model is as follows:
；
In the method, in the process of the invention, Is the error of the s-th axis,/>And/>The first and second derivatives of the s-th axis error,For the state of the s-th axis,/>For the target state of the s-th axis,/>For speed of the s-th axis,/>For the desired speed of the s-th axis,/>Is the weight of the multiaxial anti-interference index,/>Is the anti-interference index of the s-th axis,/>AndAs the weight coefficient, h is the total number of axes.
Preferably, the adjusting the multi-axis cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold specifically includes:
judging whether the multi-axis cooperative control error is abnormal or not according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold;
If the cooperative control robust evaluation data does not exceed the cooperative control robust evaluation threshold, the multi-axis cooperative control is normal, the task action error is in a standard range, and the cooperative control robust evaluation data is recorded;
if the cooperative control robust evaluation data exceeds the cooperative control robust evaluation threshold, abnormal multi-axis cooperative control occurs, the task action error is too high, and the cooperative control scheme is adjusted according to the cooperative control robust evaluation data.
Further, a multi-axis cooperative control system based on action decomposition is provided, which is configured to implement the control method described above, and includes:
The main control module is used for predicting a sub-task completion state according to sub-task planning information and shaft function information, obtaining sub-task prediction data, evaluating sub-task planning according to the sub-task prediction data, obtaining a task planning index, judging whether the task planning index is lower than a task planning index threshold according to the task planning index and a task planning index threshold, obtaining cooperative control scheme information according to the sub-task planning information, training an evaluation model according to multi-shaft cooperative control historical standard data, obtaining a multi-shaft cooperative control robust evaluation model according to shaft state data and shaft speed data, obtaining cooperative control robust evaluation data based on the multi-shaft cooperative control robust evaluation model, and adjusting multi-shaft cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold;
The information acquisition module is used for acquiring task action information, action content information, action requirement information, shaft function information, shaft position information, shaft state information corresponding to each shaft, shaft action information, multi-shaft cooperative control historical data, cooperative shaft action data and cooperative shaft management data, and detecting and eliminating abnormal values of the multi-shaft cooperative control historical data according to the multi-shaft cooperative control historical data mean value and the multi-shaft cooperative control historical data standard deviation to acquire multi-shaft cooperative control historical standard data;
The subtask planning module is used for acquiring action decomposition factors according to task action information, acquiring subtask information based on task division according to the action decomposition factors, acquiring an axis action threshold according to axis function information, acquiring an axis action threshold according to actual control requirements, calculating a subtask complexity index according to the subtask information, judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold, acquiring subtask order information according to the subtask information, ordering the subtasks with execution order according to the subtask order information, acquiring the subtask planning information, acquiring a subtask order evaluation index according to the subtask order information, acquiring a subtask priority index according to the subtask parallel information, adjusting the parallel subtask according to the subtask priority index, and acquiring the subtask planning information.
And the display module is interacted with the main control module and is used for displaying cooperative control scheme information, multi-axis cooperative control data and cooperative control robust evaluation data.
Optionally, the main control module specifically includes:
The control unit is used for training the evaluation model according to multi-axis cooperative control historical standard data, obtaining a multi-axis cooperative control robust evaluation model, obtaining cooperative control robust evaluation data based on the multi-axis cooperative control robust evaluation model according to axis state data and axis speed data, and adjusting multi-axis cooperative control according to the cooperative control robust evaluation data and a cooperative control robust evaluation threshold;
The information receiving unit is interacted with the information acquisition module and the subtask planning module and is used for acquiring information and transmitting the information to the cooperative control unit;
The cooperative control unit is used for predicting the sub-task completion state according to the sub-task planning information and the shaft function information, obtaining sub-task prediction data, evaluating the sub-task planning according to the sub-task prediction data, obtaining a task planning index, judging whether the task planning index is lower than the task planning index threshold according to the task planning index and the task planning index threshold, and obtaining cooperative control scheme information according to the sub-task planning information.
Optionally, the information acquisition module specifically includes:
The first acquisition unit is used for acquiring task action information, action content information, action request information, shaft function information, shaft position information, shaft state information corresponding to each shaft and shaft action information;
The second acquisition unit is used for acquiring multi-axis cooperative control historical data, cooperative axis action data and cooperative axis management data, and detecting and eliminating abnormal values of the multi-axis cooperative control historical data according to the average value of the multi-axis cooperative control historical data and the standard deviation of the multi-axis cooperative control historical data to acquire multi-axis cooperative control historical standard data.
Optionally, the subtask planning module specifically includes:
The subtask division unit is used for obtaining action decomposition factors according to task action information, obtaining subtask information based on task division according to the action decomposition factors, obtaining an axis action threshold according to axis function information and based on actual control requirements, calculating a subtask complexity index according to the subtask information, and judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold;
The subtask planning unit is used for acquiring subtask order information according to the subtask information, sequencing the subtasks with execution orders according to the subtask order information, acquiring the subtask planning information, acquiring a subtask order evaluation index according to the subtask order information, acquiring a subtask priority index according to the subtask parallel information, and adjusting the parallel subtasks according to the subtask priority index to acquire the subtask planning information.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a multi-axis cooperative control method and system based on action decomposition, which divide task actions through action decomposition factors, reduce the complexity of the whole system, avoid the workload and complexity of subtasks to be too high or too low according to the subtask complex index and the axis action threshold, order the subtasks with execution orders, avoid causing task action abnormality, improve the subtask planning efficiency according to the subtask priority index, evaluate multi-axis cooperative control according to a multi-axis cooperative control robust evaluation model, adjust the multi-axis cooperative control, and accurately control the movement of each axis so as to realize higher precision and stability.
Drawings
FIG. 1 is a flow chart of a multi-axis cooperative control method based on action decomposition according to the present invention;
FIG. 2 is a flow chart of subtask division in accordance with the present invention;
FIG. 3 is a flow chart of a neutron task plan of the present invention;
FIG. 4 is a flow chart of the cooperative control robust evaluation data acquisition in the present invention;
Fig. 5 is a block diagram of a multi-axis cooperative control system based on motion decomposition according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1 to fig. 4, the multi-axis cooperative control method based on motion decomposition according to an embodiment of the present invention includes:
task action information is obtained, wherein the task action information comprises action content information and action request information;
acquiring shaft function information, wherein the shaft function information comprises shaft position information, shaft state information corresponding to each shaft and shaft action information;
acquiring subtask information based on action decomposition according to task action information and shaft function information;
specifically, the task action is subjected to action decomposition to obtain subtask information, and the method specifically comprises the following steps:
According to the task action information, an action decomposition factor is obtained, wherein the action decomposition factor comprises task action step information, task action decision point information and task action related information;
Acquiring a shaft action threshold based on actual control requirements according to the shaft function information;
acquiring subtask information based on task division according to the action decomposition factors;
Acquiring a subtask complexity index according to the subtask information;
judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold, if not, enabling the subtask to be achieved, if so, enabling the subtask to be not achieved, and re-decomposing and re-judging the task action;
The subtask complex index calculation formula is as follows:
；
Where Q is the sub-task complexity index, Weight of the ith subtask type,/>For the workload of the ith subtask,/>Is the weight of the task association degree,/>Representing the association of the ith subtask with the z-th subtask, wherein/>And/>N is the total number of subtasks.
According to the invention, task action information is analyzed to obtain task action step information, task action decision point information, task action related information and other action decomposition factors in the task action information, task actions are divided according to the action decomposition factors to obtain subtask information, the complexity of the whole system is reduced, the whole system is simpler and easy to understand, debug and maintain, the subtask complexity index is calculated, whether the subtask complexity index exceeds the axis action threshold is judged according to the subtask complexity index and the axis action threshold, the workload and complexity of subtasks are avoided to be too high or too low, and the diversity and resources of the system are fully utilized.
Acquiring an action priority index based on the evaluation model according to the subtask information;
Planning the subtasks based on the action priority index to obtain subtask planning information;
Specifically, the method comprises the steps of planning a subtask to obtain subtask planning information, and specifically comprises the following steps:
Acquiring sub-task order information according to the sub-task information, wherein the sub-task order information comprises sub-task dependency information and sub-task parallel information;
Sequencing the subtasks with the execution sequence according to the subtask dependency information to obtain subtask sequencing information;
Acquiring a subtask order evaluation index according to the subtask ordering information, wherein the higher the subtask order evaluation index is, the earlier the task ordering of the subtask is;
Acquiring a subtask priority index according to the subtask parallel information and the subtask order evaluation index;
According to the subtask priority index, adjusting the parallel subtasks to obtain subtask planning information;
the calculation formula of the subtask priority index is as follows:
；
In the method, in the process of the invention, For the subtask priority index of the ith subtask,/>The weights of the indices are evaluated for the order of the subtasks,Assessment index for the order of the subtasks of the ith subtask,/>Weight for the ith subtask workload,/>For the workload of the ith subtask,/>Weight for the ith subtask complexity,/>For the association degree of the jth subtask with the dependent relation with the ith subtask, m is the total number of the subtasks with the dependent relation with the ith subtask.
In the scheme, the subtask order information is obtained according to the subtask information, the subtasks with the execution order are ordered according to the subtask dependency information, the subtask planning information is obtained, the order of the subtasks is ensured to be normal, task action abnormality is avoided, the subtask priority index is obtained according to the subtask parallel information and the subtask order evaluation index, the parallel subtasks are adjusted according to the subtask priority index, and the subtask planning efficiency is improved.
Acquiring cooperative control scheme information based on the task planning index according to the subtask planning information;
specifically, the assessment of the subtask planning information by the mission planning index specifically includes:
predicting the sub-action completion state according to the sub-task planning information and the shaft function information to obtain sub-task prediction data;
evaluating the subtask planning according to the subtask prediction data to obtain a task planning index;
Acquiring a task planning index threshold based on the multi-axis cooperative control requirement;
Judging whether the task planning index is lower than the task planning index threshold according to the task planning index and the task planning index threshold, if yes, not conforming to the actual cooperative control requirement by sub-task planning, and if not, acquiring cooperative control scheme information according to the sub-task planning information;
the calculation formula of the task planning index is as follows:
；
In the method, in the process of the invention, Planning an index for a mission,/>Weight for the ith subtask response time,/>For the response time of the ith subtask,/>Weighting of data transitivity for the ith subtask and for the jth subtask associated with the ith subtask,/>For the ith subtask and the data transitivity associated with the ith subtask for the jth subtask,/>Weights affecting the index for task actions,/>Predicting data for the ith subtask,/>Planning data for the ith subtask,/>Is the influence coefficient of the j-th subtask with a dependency relationship with the i-th subtask.
In the scheme, the subtask completion state is predicted through the subtask planning information and the shaft function information, subtask prediction data are obtained, the subtask planning is evaluated according to the subtask prediction data, the task planning index is obtained, the task planning index threshold is obtained based on the multi-shaft cooperative control requirement, whether the subtask planning accords with the actual requirement or not is judged according to the task planning index and the task planning index threshold, the subtask planning is evaluated, and the subtask planning degree is accurately judged.
According to the cooperative control scheme information, performing multi-axis cooperative control to obtain multi-axis cooperative control data;
Acquiring multi-axis cooperative control historical data, wherein the multi-axis cooperative control historical data comprises cooperative axis action data and cooperative axis management data;
training the evaluation model according to the multi-axis cooperative control historical data to obtain a multi-axis cooperative control robust evaluation model;
acquiring cooperative control robust evaluation data according to the multi-axis cooperative control data and the multi-axis cooperative control robust evaluation model;
Specifically, the method for performing robust error evaluation on the multi-axis cooperative control data through the multi-axis cooperative control robust evaluation model specifically comprises the following steps:
Acquiring a multi-axis cooperative control historical data average value and a multi-axis cooperative control historical data standard deviation according to the multi-axis cooperative control historical data;
Detecting abnormal values of the multi-axis cooperative control historical data according to the multi-axis cooperative control historical data average value and the multi-axis cooperative control historical data standard deviation to obtain multi-axis cooperative control historical abnormal data;
according to the multi-axis cooperative control historical abnormal data, abnormal value rejection is carried out on the multi-axis cooperative control historical data, and multi-axis cooperative control historical standard data are obtained;
Training the evaluation model according to the multi-axis cooperative control historical standard data to obtain a multi-axis cooperative control robust evaluation model;
acquiring shaft state data and shaft speed data according to the multi-shaft cooperative control data;
Acquiring cooperative control robust evaluation data based on a multi-axis cooperative control robust evaluation model according to the axis state data and the axis speed data;
the multi-axis cooperative control robust evaluation model is as follows:
；
In the method, in the process of the invention, Is the error of the s-th axis,/>And/>The first and second derivatives of the s-th axis error,For the state of the s-th axis,/>For the target state of the s-th axis,/>For speed of the s-th axis,/>For the desired speed of the s-th axis,/>Is the weight of the multiaxial anti-interference index,/>Is the anti-interference index of the s-th axis,/>AndAs the weight coefficient, h is the total number of axes.
In the scheme, abnormal value detection is carried out on the multi-axis cooperative control historical data through the multi-axis cooperative control historical data mean value and the multi-axis cooperative control historical data standard deviation, abnormal value rejection is carried out on the multi-axis cooperative control historical data, the multi-axis cooperative control historical standard data is obtained, accuracy of the data is guaranteed, interference to model training is avoided, cooperative control robust evaluation data is obtained based on a multi-axis cooperative control robust evaluation model according to axis state data and axis speed data, and the multi-axis cooperative control state is accurately evaluated through the multi-axis cooperative control robust evaluation model.
Acquiring a cooperative control robust evaluation threshold based on the multi-axis cooperative control requirement and actual equipment parameters;
And adjusting the multi-axis cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold.
Specifically, judging whether the multi-axis cooperative control error is abnormal or not according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold;
If the cooperative control robust evaluation data does not exceed the cooperative control robust evaluation threshold, the multi-axis cooperative control is normal, the task action error is in a standard range, and the cooperative control robust evaluation data is recorded;
if the cooperative control robust evaluation data exceeds the cooperative control robust evaluation threshold, abnormal multi-axis cooperative control occurs, the task action error is too high, and the cooperative control scheme is adjusted according to the cooperative control robust evaluation data.
In the scheme, whether the multi-axis cooperative control error is abnormal or not is judged through cooperative control robust evaluation data and cooperative control robust evaluation threshold values, the multi-axis cooperative control is adjusted, and the motion of each axis is accurately controlled, so that higher precision and stability are realized.
Referring to fig. 5, in combination with the above-mentioned multi-axis cooperative control method based on motion decomposition, a multi-axis cooperative control system based on motion decomposition is further proposed, including:
The main control module is used for predicting a sub-task completion state according to sub-task planning information and shaft function information, obtaining sub-task prediction data, evaluating sub-task planning according to the sub-task prediction data, obtaining a task planning index, judging whether the task planning index is lower than a task planning index threshold according to the task planning index and a task planning index threshold, obtaining cooperative control scheme information according to the sub-task planning information, training an evaluation model according to multi-shaft cooperative control historical standard data, obtaining a multi-shaft cooperative control robust evaluation model according to shaft state data and shaft speed data, obtaining cooperative control robust evaluation data based on the multi-shaft cooperative control robust evaluation model, and adjusting multi-shaft cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold;
The information acquisition module is used for acquiring task action information, action content information, action requirement information, shaft function information, shaft position information, shaft state information corresponding to each shaft, shaft action information, multi-shaft cooperative control historical data, cooperative shaft action data and cooperative shaft management data, and detecting and eliminating abnormal values of the multi-shaft cooperative control historical data according to the multi-shaft cooperative control historical data mean value and the multi-shaft cooperative control historical data standard deviation to acquire multi-shaft cooperative control historical standard data;
The subtask planning module is used for acquiring action decomposition factors according to task action information, acquiring subtask information based on task division according to the action decomposition factors, acquiring an axis action threshold according to axis function information, acquiring an axis action threshold according to actual control requirements, calculating a subtask complexity index according to the subtask information, judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold, acquiring subtask order information according to the subtask information, ordering the subtasks with execution order according to the subtask order information, acquiring the subtask planning information, acquiring a subtask order evaluation index according to the subtask order information, acquiring a subtask priority index according to the subtask parallel information, adjusting the parallel subtask according to the subtask priority index, and acquiring the subtask planning information.
And the display module is interacted with the main control module and is used for displaying cooperative control scheme information, multi-axis cooperative control data and cooperative control robust evaluation data.
The main control module specifically comprises:
The control unit is used for training the evaluation model according to multi-axis cooperative control historical standard data, obtaining a multi-axis cooperative control robust evaluation model, obtaining cooperative control robust evaluation data based on the multi-axis cooperative control robust evaluation model according to axis state data and axis speed data, and adjusting multi-axis cooperative control according to the cooperative control robust evaluation data and a cooperative control robust evaluation threshold;
The information receiving unit is interacted with the information acquisition module and the subtask planning module and is used for acquiring information and transmitting the information to the cooperative control unit;
The cooperative control unit is used for predicting the sub-task completion state according to the sub-task planning information and the shaft function information, obtaining sub-task prediction data, evaluating the sub-task planning according to the sub-task prediction data, obtaining a task planning index, judging whether the task planning index is lower than the task planning index threshold according to the task planning index and the task planning index threshold, and obtaining cooperative control scheme information according to the sub-task planning information.
The information acquisition module specifically comprises:
The first acquisition unit is used for acquiring task action information, action content information, action request information, shaft function information, shaft position information, shaft state information corresponding to each shaft and shaft action information;
The second acquisition unit is used for acquiring multi-axis cooperative control historical data, cooperative axis action data and cooperative axis management data, and detecting and eliminating abnormal values of the multi-axis cooperative control historical data according to the average value of the multi-axis cooperative control historical data and the standard deviation of the multi-axis cooperative control historical data to acquire multi-axis cooperative control historical standard data.
The subtask planning module specifically comprises:
The subtask division unit is used for obtaining action decomposition factors according to task action information, obtaining subtask information based on task division according to the action decomposition factors, obtaining an axis action threshold according to axis function information and based on actual control requirements, calculating a subtask complexity index according to the subtask information, and judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold;
The subtask planning unit is used for acquiring subtask order information according to the subtask information, sequencing the subtasks with execution orders according to the subtask order information, acquiring the subtask planning information, acquiring a subtask order evaluation index according to the subtask order information, acquiring a subtask priority index according to the subtask parallel information, and adjusting the parallel subtasks according to the subtask priority index to acquire the subtask planning information.
In summary, the invention has the advantages that: the method comprises the steps of dividing task actions through action decomposition factors, obtaining sub-task information, reducing complexity of the whole system, enabling the whole system to be simpler, easy to understand, debug and maintain, judging whether the sub-task complexity index exceeds an axis action threshold according to the sub-task complexity index and the axis action threshold, avoiding excessively high or excessively low workload and complexity of the sub-tasks, fully utilizing diversity and resources of the system, sequencing the sub-tasks with execution sequences through sub-task sequence information, obtaining sub-task planning information, ensuring normal sub-task sequence, avoiding abnormal task actions, adjusting the parallel sub-tasks according to the sub-task priority index, obtaining sub-task planning information, improving sub-task planning efficiency, judging whether the sub-task planning accords with actual cooperative control requirements according to the task planning index, evaluating multi-axis cooperative control according to a multi-axis cooperative control robust evaluation model, adjusting the multi-axis cooperative control according to cooperative control robust evaluation data and a cooperative control robust evaluation threshold, accurately controlling motion of each axis so as to achieve higher precision and stability.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The multi-axis cooperative control method based on action decomposition is characterized by comprising the following steps of:
task action information is obtained, wherein the task action information comprises action content information and action request information;
acquiring shaft function information, wherein the shaft function information comprises shaft position information, shaft state information corresponding to each shaft and shaft action information;
According to the task action information, an action decomposition factor is obtained, wherein the action decomposition factor comprises task action step information, task action decision point information and task action related information;
Acquiring a shaft action threshold based on actual control requirements according to the shaft function information;
acquiring subtask information based on task division according to the action decomposition factors;
Acquiring a subtask complexity index according to the subtask information;
judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold, if not, enabling the subtask to be achieved, if so, enabling the subtask to be not achieved, and re-decomposing and re-judging the task action;
The subtask complex index calculation formula is as follows:
；
Where Q is the sub-task complexity index, Weight of the ith subtask type,/>For the workload of the ith subtask,/>Is the weight of the task association degree,/>Representing the association of the ith subtask with the z-th subtask, wherein/>And/>N is the total number of subtasks;
Acquiring sub-task order information according to the sub-task information, wherein the sub-task order information comprises sub-task dependency information and sub-task parallel information;
Sequencing the subtasks with the execution sequence according to the subtask dependency information to obtain subtask sequencing information;
Acquiring a subtask order evaluation index according to the subtask ordering information, wherein the higher the subtask order evaluation index is, the earlier the task ordering of the subtask is;
Acquiring a subtask priority index according to the subtask parallel information and the subtask order evaluation index;
According to the subtask priority index, adjusting the parallel subtasks to obtain subtask planning information;
the calculation formula of the subtask priority index is as follows:
；
In the method, in the process of the invention, For the subtask priority index of the ith subtask,/>Weights of indexes are evaluated for sub-task orders,/>Assessment index for the order of the subtasks of the ith subtask,/>Weight for the ith subtask workload,/>For the workload of the ith subtask,/>Weight for the ith subtask complexity,/>The association degree of the j-th subtask with the dependency relationship with the i-th subtask is m, and the total number of the subtasks with the dependency relationship with the i-th subtask;
acquiring cooperative control scheme information based on a task planning index according to the subtask planning information;
According to the cooperative control scheme information, performing multi-axis cooperative control to obtain multi-axis cooperative control data;
Acquiring multi-axis cooperative control historical data, wherein the multi-axis cooperative control historical data comprises cooperative axis action data and cooperative axis management data;
training the evaluation model according to the multi-axis cooperative control historical data to obtain a multi-axis cooperative control robust evaluation model;
acquiring cooperative control robust evaluation data according to the multi-axis cooperative control data and the multi-axis cooperative control robust evaluation model;
acquiring a cooperative control robust evaluation threshold based on the multi-axis cooperative control requirement and actual equipment parameters;
And adjusting the multi-axis cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold.
2. The method for multi-axis cooperative control based on motion decomposition according to claim 1, wherein the acquiring cooperative control scheme information based on the task planning index according to the subtask planning information specifically includes:
predicting the sub-action completion state according to the sub-task planning information and the shaft function information to obtain sub-task prediction data;
evaluating the subtask planning according to the subtask prediction data to obtain a task planning index;
Acquiring a task planning index threshold based on the multi-axis cooperative control requirement;
Judging whether the task planning index is lower than the task planning index threshold according to the task planning index and the task planning index threshold, if yes, not conforming to the actual cooperative control requirement by sub-task planning, and if not, acquiring cooperative control scheme information according to the sub-task planning information;
the calculation formula of the task planning index is as follows:
；
In the method, in the process of the invention, Planning an index for a mission,/>Weight for the ith subtask response time,/>For the response time of the ith subtask,/>Weighting of data transitivity for the ith subtask and for the jth subtask associated with the ith subtask,/>For the ith subtask and the data transitivity associated with the ith subtask for the jth subtask,/>Weights affecting the index for task actions,/>Predicting data for the ith subtask,/>Planning data for the ith subtask,/>Is the influence coefficient of the j-th subtask with a dependency relationship with the i-th subtask.
3. The method for multi-axis cooperative control based on motion decomposition according to claim 1, wherein the obtaining cooperative control robust evaluation data according to the multi-axis cooperative control data and the multi-axis cooperative control robust evaluation model specifically comprises:
Acquiring a multi-axis cooperative control historical data average value and a multi-axis cooperative control historical data standard deviation according to the multi-axis cooperative control historical data;
Detecting abnormal values of the multi-axis cooperative control historical data according to the multi-axis cooperative control historical data average value and the multi-axis cooperative control historical data standard deviation to obtain multi-axis cooperative control historical abnormal data;
according to the multi-axis cooperative control historical abnormal data, abnormal value rejection is carried out on the multi-axis cooperative control historical data, and multi-axis cooperative control historical standard data are obtained;
Training the evaluation model according to the multi-axis cooperative control historical standard data to obtain a multi-axis cooperative control robust evaluation model;
acquiring shaft state data and shaft speed data according to the multi-shaft cooperative control data;
Acquiring cooperative control robust evaluation data based on a multi-axis cooperative control robust evaluation model according to the axis state data and the axis speed data;
the multi-axis cooperative control robust evaluation model is as follows:
；
In the method, in the process of the invention, Is the error of the s-th axis,/>And/>First and second derivatives, respectively,/>, of the s-th axis errorFor the state of the s-th axis,/>For the target state of the s-th axis,/>For speed of the s-th axis,/>For the desired speed of the s-th axis,/>Is the weight of the multiaxial anti-interference index,/>Is the anti-interference index of the s-th axis,/>，/>，/>And/>As the weight coefficient, h is the total number of axes.
4. The method for multi-axis cooperative control based on motion decomposition according to claim 1, wherein the adjusting the multi-axis cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold value specifically comprises:
judging whether the multi-axis cooperative control error is abnormal or not according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold;
If the cooperative control robust evaluation data does not exceed the cooperative control robust evaluation threshold, the multi-axis cooperative control is normal, the task action error is in a standard range, and the cooperative control robust evaluation data is recorded;
if the cooperative control robust evaluation data exceeds the cooperative control robust evaluation threshold, abnormal multi-axis cooperative control occurs, the task action error is too high, and the cooperative control scheme is adjusted according to the cooperative control robust evaluation data.
5. A multi-axis cooperative control system based on motion decomposition for implementing the control method according to any one of claims 1 to 4, characterized by comprising
The main control module is used for predicting a sub-task completion state according to sub-task planning information and shaft function information, obtaining sub-task prediction data, evaluating sub-task planning according to the sub-task prediction data, obtaining a task planning index, judging whether the task planning index is lower than a task planning index threshold according to the task planning index and a task planning index threshold, obtaining cooperative control scheme information according to the sub-task planning information, training an evaluation model according to multi-shaft cooperative control historical standard data, obtaining a multi-shaft cooperative control robust evaluation model according to shaft state data and shaft speed data, obtaining cooperative control robust evaluation data based on the multi-shaft cooperative control robust evaluation model, and adjusting multi-shaft cooperative control according to the cooperative control robust evaluation data and the cooperative control robust evaluation threshold;
The information acquisition module is used for acquiring task action information, action content information, action requirement information, shaft function information, shaft position information, shaft state information corresponding to each shaft, shaft action information, multi-shaft cooperative control historical data, cooperative shaft action data and cooperative shaft management data, and detecting and eliminating abnormal values of the multi-shaft cooperative control historical data according to the multi-shaft cooperative control historical data mean value and the multi-shaft cooperative control historical data standard deviation to acquire multi-shaft cooperative control historical standard data;
The subtask planning module is used for acquiring action decomposition factors according to task action information, acquiring subtask information based on task division according to the action decomposition factors, acquiring an axis action threshold according to axis function information, acquiring an axis action threshold according to actual control requirements, calculating a subtask complexity index according to the subtask information, judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold, acquiring subtask order information according to the subtask information, ordering the subtasks with execution order according to the subtask order information, acquiring subtask planning information according to the subtask order information, acquiring a subtask order evaluation index according to the subtask parallel information, acquiring a subtask priority index, adjusting the parallel subtasks according to the subtask priority index, and acquiring the subtask planning information;
And the display module is interacted with the main control module and is used for displaying cooperative control scheme information, multi-axis cooperative control data and cooperative control robust evaluation data.
6. The motion decomposition-based multi-axis cooperative control system of claim 5, wherein said main control module specifically comprises:
The control unit is used for training the evaluation model according to multi-axis cooperative control historical standard data, obtaining a multi-axis cooperative control robust evaluation model, obtaining cooperative control robust evaluation data based on the multi-axis cooperative control robust evaluation model according to axis state data and axis speed data, and adjusting multi-axis cooperative control according to the cooperative control robust evaluation data and a cooperative control robust evaluation threshold;
The information receiving unit is interacted with the information acquisition module and the subtask planning module and is used for acquiring information and transmitting the information to the cooperative control unit;
The cooperative control unit is used for predicting the sub-task completion state according to the sub-task planning information and the shaft function information, obtaining sub-task prediction data, evaluating the sub-task planning according to the sub-task prediction data, obtaining a task planning index, judging whether the task planning index is lower than the task planning index threshold according to the task planning index and the task planning index threshold, and obtaining cooperative control scheme information according to the sub-task planning information.
7. The motion decomposition-based multi-axis cooperative control system of claim 5, wherein said information acquisition module specifically comprises:
The first acquisition unit is used for acquiring task action information, action content information, action request information, shaft function information, shaft position information, shaft state information corresponding to each shaft and shaft action information;
The second acquisition unit is used for acquiring multi-axis cooperative control historical data, cooperative axis action data and cooperative axis management data, and detecting and eliminating abnormal values of the multi-axis cooperative control historical data according to the average value of the multi-axis cooperative control historical data and the standard deviation of the multi-axis cooperative control historical data to acquire multi-axis cooperative control historical standard data.
8. The motion decomposition-based multi-axis cooperative control system of claim 5, wherein said sub-mission planning module specifically comprises:
The subtask division unit is used for obtaining action decomposition factors according to task action information, obtaining subtask information based on task division according to the action decomposition factors, obtaining an axis action threshold according to axis function information and based on actual control requirements, calculating a subtask complexity index according to the subtask information, and judging whether the subtask complexity index exceeds the axis action threshold according to the subtask complexity index and the axis action threshold;
The subtask planning unit is used for acquiring subtask order information according to the subtask information, sequencing the subtasks with execution orders according to the subtask order information, acquiring the subtask planning information, acquiring a subtask order evaluation index according to the subtask order information, acquiring a subtask priority index according to the subtask parallel information, and adjusting the parallel subtasks according to the subtask priority index to acquire the subtask planning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410057248.5A CN117590752B (en) | 2024-01-16 | 2024-01-16 | Multi-axis cooperative control method and system based on action decomposition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410057248.5A CN117590752B (en) | 2024-01-16 | 2024-01-16 | Multi-axis cooperative control method and system based on action decomposition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117590752A CN117590752A (en) | 2024-02-23 |
| CN117590752B true CN117590752B (en) | 2024-04-26 |
Family
ID=89920387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410057248.5A Active CN117590752B (en) | 2024-01-16 | 2024-01-16 | Multi-axis cooperative control method and system based on action decomposition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117590752B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108527367A (en) * | 2018-03-28 | 2018-09-14 | 华南理工大学 | A kind of description method of multirobot work compound task |
| CN109760073A (en) * | 2018-12-20 | 2019-05-17 | 华东师范大学 | A kind of more coordination controllers of robot |
| CN109782713A (en) * | 2019-01-12 | 2019-05-21 | 无锡物联网产业研究院 | A kind of intelligent manufacturing system with collaboration processing capacity |
| CN110682298A (en) * | 2019-09-20 | 2020-01-14 | 浙江派尼尔科技股份有限公司 | Control method for multiple sets of cooperative control software of unmanned intelligent robot on water |
| CN114241349A (en) * | 2021-11-04 | 2022-03-25 | 中国船舶工业系统工程研究院 | Multi-unmanned-boat collaborative identification method and device |
| CN116541797A (en) * | 2023-03-31 | 2023-08-04 | 四川九洲电器集团有限责任公司 | Multi-resource task planning method and system based on reinforcement learning and efficiency evaluation |
| CN116707611A (en) * | 2023-06-02 | 2023-09-05 | 北京航天飞行控制中心 | Mars detection multi-target cooperative control method and device |
| CN117151390A (en) * | 2023-08-29 | 2023-12-01 | 西安交通大学 | Greedy value representation-based multi-unmanned carrier scheduling method and greedy value representation-based multi-unmanned carrier scheduling system |
| CN117170293A (en) * | 2023-10-27 | 2023-12-05 | 湖南华鑫电子科技有限公司 | Centralized control method and system for power supply with multi-mode cooperative work |
| CN117370766A (en) * | 2023-12-07 | 2024-01-09 | 中国电子科技集团公司第五十四研究所 | Satellite mission planning scheme evaluation method based on deep learning |
-
2024
- 2024-01-16 CN CN202410057248.5A patent/CN117590752B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108527367A (en) * | 2018-03-28 | 2018-09-14 | 华南理工大学 | A kind of description method of multirobot work compound task |
| CN109760073A (en) * | 2018-12-20 | 2019-05-17 | 华东师范大学 | A kind of more coordination controllers of robot |
| CN109782713A (en) * | 2019-01-12 | 2019-05-21 | 无锡物联网产业研究院 | A kind of intelligent manufacturing system with collaboration processing capacity |
| CN110682298A (en) * | 2019-09-20 | 2020-01-14 | 浙江派尼尔科技股份有限公司 | Control method for multiple sets of cooperative control software of unmanned intelligent robot on water |
| CN114241349A (en) * | 2021-11-04 | 2022-03-25 | 中国船舶工业系统工程研究院 | Multi-unmanned-boat collaborative identification method and device |
| CN116541797A (en) * | 2023-03-31 | 2023-08-04 | 四川九洲电器集团有限责任公司 | Multi-resource task planning method and system based on reinforcement learning and efficiency evaluation |
| CN116707611A (en) * | 2023-06-02 | 2023-09-05 | 北京航天飞行控制中心 | Mars detection multi-target cooperative control method and device |
| CN117151390A (en) * | 2023-08-29 | 2023-12-01 | 西安交通大学 | Greedy value representation-based multi-unmanned carrier scheduling method and greedy value representation-based multi-unmanned carrier scheduling system |
| CN117170293A (en) * | 2023-10-27 | 2023-12-05 | 湖南华鑫电子科技有限公司 | Centralized control method and system for power supply with multi-mode cooperative work |
| CN117370766A (en) * | 2023-12-07 | 2024-01-09 | 中国电子科技集团公司第五十四研究所 | Satellite mission planning scheme evaluation method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117590752A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Toward intelligent machine tool | |
| CN105302096B (en) | Intelligent factory scheduling method | |
| Keats | Statistical process control in automated manufacturing | |
| CN114186791B (en) | Multi-model small-batch-oriented dynamic scheduling method for assembly and production of complex equipment products | |
| US10739758B2 (en) | Model-free online recursive optimization method for batch process based on variable period decomposition | |
| CN101844155B (en) | Automatic gauge control (AGC) method for rolling mill | |
| CN101630376A (en) | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process | |
| CN102354146A (en) | Motion control system and position control method thereof | |
| CN111813052A (en) | Numerical control system structure and general numerical control system | |
| CN107544450A (en) | Process industry network model construction method and system based on data | |
| Gama et al. | Stream-based electricity load forecast | |
| CN111142488B (en) | Process industrial optimization method based on working condition comparison driving | |
| CN117590752B (en) | Multi-axis cooperative control method and system based on action decomposition | |
| Zeng et al. | DDPG-based continuous thickness and tension coupling control for the unsteady cold rolling process | |
| CN117390960A (en) | Intelligent analysis method for machining precision of numerical control machine tool | |
| CN117352762A (en) | Control system of battery manufacturing equipment | |
| CN117196257A (en) | Auxiliary settlement system for power distribution network engineering | |
| CN115825340A (en) | Method for detecting concentration of hydrogen sulfide in sulfur recovery process | |
| Xiao et al. | Optimized design of battery pole control system based on dual-chip architecture | |
| CN115018162A (en) | Method and system for predicting machining quality in industrial finish machining process in real time | |
| Miletic et al. | Results analysis for real-time optimization (RTO): Deciding when to change the plant operation | |
| CN114815586B (en) | Digital twin process model construction method and application of machine tool feeding system | |
| Silvestri et al. | Experimental results of a self-learning compensation system for high precision manufacturing | |
| CN114330819B (en) | Wind turbine generator free inflow wind speed prediction method | |
| CN114912335B (en) | Coal gas generation amount prediction method based on missing data |
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 |