CN112213993A - Control system and method based on cloud - Google Patents
Control system and method based on cloud Download PDFInfo
- Publication number
- CN112213993A CN112213993A CN201910624622.4A CN201910624622A CN112213993A CN 112213993 A CN112213993 A CN 112213993A CN 201910624622 A CN201910624622 A CN 201910624622A CN 112213993 A CN112213993 A CN 112213993A
- Authority
- CN
- China
- Prior art keywords
- field
- cloud
- processing device
- module
- process data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
-
- 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
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- 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
-
- 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41845—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by system universality, reconfigurability, modularity
-
- 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/4185—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by the network communication
- G05B19/41855—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by the network communication by local area network [LAN], network structure
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/25—Pc structure of the system
- G05B2219/25232—DCS, distributed control system, decentralised control unit
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2609—Process control
-
- 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]
Abstract
The application provides a control system and a method based on a cloud end, wherein the system comprises: the system comprises a plurality of field processing devices and a cloud processing device corresponding to each field processing device; the field processing device is configured to obtain field process data; the cloud processing device is in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device; acquiring a field control strategy according to the field process data; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the control strategy. The field processing device and the cloud processing device are integrated in the cloud, remote online control over the field processing device is achieved, the cloud processing device is based on the neural network model, interactive learning can be conducted among all the cloud processing devices, performance of the cloud processing devices is effectively improved, and stable control is achieved.
Description
Technical Field
The application relates to the field of automatic control, in particular to a control method based on a cloud end and a control system based on the cloud end.
Background
Currently, concepts and technologies of advanced process control (APC for short) are gradually formed, model predictive control (MPC for short) technology has been developed in over 30 years, and model algorithm control (MAC for short), dynamic matrix control (DMC for short), generalized predictive control (GPC for short) algorithm, anti-interference robust constraint model predictive control technology and the like are successively proposed and applied to industrial production processes. In the middle and late stages of the last 80 th century, distributed control systems (DCS for short) have been widely used, and the chemical industry process realizes comprehensive automation and advanced control operation.
However, the control effect of the APC controller depends on its neural network model, and if the device operating condition changes, a model drift condition usually occurs, so that the control accuracy is reduced, and the device fluctuates. Because the neural network model has a strong self-learning function, if the controller adopts the neural network model, the situation can be effectively relieved, but the neural network model also has problems in the training process. Macroscopically, neural networks mimic the human brain, and therefore, they are good at dealing with things that have been learned, and can only be dealt with by inference for things that have not been learned. In the training process, the data source is single, and the training degree of the neural network cannot be guaranteed, so that the performance of the controller is not satisfactory in some cases.
Furthermore, APC systems are deployed in computers on site. Therefore, both debugging and maintenance require engineers to be on site, and labor costs become a bottleneck for the popularization of APC. This increases the cost of implementing the project.
Disclosure of Invention
The application provides a control method based on a cloud end, in particular to a control system based on the cloud end; the problem of high manual field maintenance cost is solved.
In order to solve the above technical problem, an embodiment of the present application provides the following technical solutions:
the application provides a control system based on high in clouds includes: the system comprises a plurality of field processing devices and a cloud processing device corresponding to each field processing device;
the field processing device is configured to obtain field process data;
the cloud processing device is in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device; acquiring a field control strategy according to the field process data; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the control strategy.
Optionally, the cloud processing apparatus includes: the system comprises a cloud control module and a neural network module;
the neural network module is in signal connection with the corresponding cloud control module, is configured to receive the change trend information of the field process data input by the cloud control module, and outputs a controlled variable value;
the cloud control module is respectively in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device, and inputting the change trend information of the field process data into an optimized neural network module to obtain the controlled variable value; generating a field control strategy according to a preset control rule and a controlled variable value; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the field control strategy.
Optionally, the system further includes a cloud storage module;
the cloud storage module is in signal connection with the plurality of cloud control modules and is configured to store and share the field process data for the plurality of cloud control modules;
the cloud control module is further configured to: acquiring the change trend information of the field process data from the cloud storage module; and training the neural network module to output the controlled variable value according to the change trend information so as to obtain the optimized neural network module.
Optionally, the cloud processing device further includes a timing module corresponding to the cloud control module;
the timing module is in signal connection with the cloud control module and is configured to send a training signal to the cloud control module at regular time according to a preset time period;
the cloud control module is configured to: respectively acquiring main variation trend information and auxiliary variation trend information from the cloud storage module according to the training signal; the main change trend information is the change trend information of the field process data stored in the cloud storage module by the cloud processing device; the secondary change trend information is the change trend information of the field process data stored in the cloud storage module by other cloud processing devices; the cloud processing device has the same function as other cloud processing devices; training the neural network module to output a controlled variable value according to the main change trend information and the corresponding preset main weight value, and the auxiliary change trend information and the corresponding preset auxiliary weight value so as to obtain an optimized neural network module; wherein the preset master weight value is greater than the preset slave weight value.
Optionally, the field processing apparatus includes: the system comprises a gateway, a distributed control module and a controlled module;
the gateway is respectively in signal connection with the distributed control module and the cloud processing device and is configured to transmit data between the distributed control module and the cloud processing device through a network;
the distributed control module is in signal connection with the controlled module and is configured to collect and send the field process data of the controlled module; and receiving the field control strategy and controlling the controlled module to work according to the field control strategy.
The application provides a control method based on a cloud, which is applied to a cloud control module and comprises the following steps:
receiving field process data sent by a corresponding field processing device;
acquiring a field control strategy according to the field process data;
and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the control strategy.
Optionally, the obtaining a field control policy according to the field process data includes:
inputting the change trend information of the field process data into an optimized neural network module to obtain the value of a controlled variable;
and generating a field control strategy according to the preset control rule and the controlled variable value.
Optionally, after receiving the field process data sent by the corresponding field processing device, the method further includes:
storing the received field process data into a shared cloud storage module;
the method further comprises the following steps:
acquiring the change trend information of the field process data from the cloud storage module;
and training the neural network module to output the controlled variable value according to the change trend information so as to obtain the optimized neural network module.
Optionally, the obtaining of the change trend information of the field process data from the cloud storage module includes:
respectively acquiring main change trend information and auxiliary change trend information from the cloud storage module at regular time according to a preset time period; the main change trend information is the change trend information of the field process data stored in the cloud storage module by the cloud processing device; the secondary change trend information is the change trend information of the field process data stored in the cloud storage module by other cloud processing devices; the cloud processing device has the same function as other cloud processing devices;
and training the neural network module to output a controlled variable value according to the main change trend information and the corresponding preset main weight value, and the auxiliary change trend information and the corresponding preset auxiliary weight value so as to obtain an optimized neural network module.
Optionally, the preset master weight value is greater than the preset slave weight value.
Based on the disclosure of the above embodiments, it can be known that the embodiments of the present application have the following beneficial effects:
the application provides a control system and a method based on a cloud end, wherein the system comprises: the system comprises a plurality of field processing devices and a cloud processing device corresponding to each field processing device; the field processing device is configured to obtain field process data; the cloud processing device is in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device; acquiring a field control strategy according to the field process data; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the control strategy.
According to the method, the field processing device and the cloud processing device are integrated in the cloud, so that remote online control over the field processing device is realized, the cloud processing devices are based on a neural network model, interactive learning can be performed among the cloud processing devices, frequent maintenance work is not needed under the condition that the working condition changes, and the performance of the cloud processing devices is effectively improved; the on-site hardware cost and on-site maintenance cost are reduced. The field processing device is monitored in real time, the output of the neural network model is adjusted in time, and stable control is achieved.
Drawings
Fig. 1 is an architecture diagram of a cloud-based control system according to an embodiment of the present disclosure;
fig. 2 is a structural diagram of a cloud processing device of a cloud-based control system according to an embodiment of the present disclosure;
fig. 3 is a structural diagram of an on-site processing device of a cloud-based control system according to an embodiment of the present disclosure;
fig. 4 is a flowchart of a cloud-based control method according to an embodiment of the present application.
Detailed Description
Specific embodiments of the present application will be described in detail below with reference to the accompanying drawings, but the present application is not limited thereto.
It will be understood that various modifications may be made to the embodiments disclosed herein. Accordingly, the foregoing description should not be construed as limiting, but merely as exemplifications of embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the application.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with a general description of the application given above and the detailed description of the embodiments given below, serve to explain the principles of the application.
These and other characteristics of the present application will become apparent from the following description of preferred forms of embodiment, given as non-limiting examples, with reference to the attached drawings.
It should also be understood that, although the present application has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of application, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.
The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely examples of the application, which can be embodied in various forms. Well-known and/or repeated functions and constructions are not described in detail to avoid obscuring the application of unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriately detailed structure.
The specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the application.
The application provides a method of cloud-based control; the application also provides a system based on cloud control. Details are described in the following examples one by one.
A first embodiment provided by the present application is an embodiment of a cloud-based control system.
The present embodiment is described in detail below with reference to fig. 1, where fig. 1 is an architecture diagram of a cloud-based control system according to an embodiment of the present disclosure; fig. 2 is a structural diagram of a cloud processing device of a cloud-based control system according to an embodiment of the present disclosure; fig. 3 is a structural diagram of a field processing device of a cloud-based control system according to an embodiment of the present disclosure.
This embodiment provides a control system based on high in clouds, includes: the system comprises a plurality of field processing devices and a cloud processing device corresponding to each field processing device.
The field processing device is configured to obtain field process data.
The field process data is a series of operation data generated by the controlled device in the automatic control process. The method comprises the following steps: operational status data, input signals, and output signals. Such as the pulverized coal flow and the oxygen flow of the gasifier plant.
Referring to fig. 3, the field processing apparatus includes: the system comprises a gateway, a distributed control module and a controlled module.
The gateway is in signal connection with the distributed control module and the cloud processing device respectively and is configured to transmit data between the distributed control module and the cloud processing device through a network.
The distributed control module is in signal connection with the controlled module and is configured to collect and send the field process data of the controlled module; and receiving a field control strategy and controlling the controlled module to work according to the field control strategy.
The controlled modules are devices with the same or similar process, for example, the controlled modules are vaporization furnace devices with the same or similar process, each vaporization furnace can be located in different places, even different cities, the distributed control module is a DCS, each DCS is connected to a cloud of a wide area network (including the internet) through a corresponding gateway, and is connected with a cloud processing device of the cloud to upload process data and download control signals.
The cloud processing device is in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device; acquiring a field control strategy according to the field process data; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the control strategy.
The control strategy is a series of control processes for controlling the work of the field processing device, and comprises the time for controlling the signal emission, the signal object and the signal quantity.
Optionally, referring to fig. 2, the cloud processing apparatus includes: the device comprises a cloud control module and a neural network module.
The neural network module is in signal connection with the corresponding cloud control module, is configured to receive the change trend information of the field process data input by the cloud control module and outputs a controlled variable value.
The neural network module is obtained by using change trend information based on historical field process data, for example, the change trend information of the field process data is used as a training sample to train the neural network module. The embodiment of the present disclosure does not describe in detail the process of analyzing the change trend information of the field process data by the neural network module to obtain the controlled variable value and the optimized neural network module, and may be implemented by referring to various implementation manners in the prior art.
The cloud control module is respectively in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device, and inputting the change trend information of the field process data into an optimized neural network module to obtain the controlled variable value; generating a field control strategy according to a preset control rule and a controlled variable value; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the field control strategy.
In the embodiment, the field processing device and the cloud processing device are integrated in the cloud, so that remote online control over the field processing devices distributed at multiple places is realized. Meanwhile, the cloud processing device is based on the neural network model, so that the control process of the cloud processing device can be continuously adjusted by continuously training the neural network model. Therefore, frequent maintenance work is not needed under the condition that the working condition changes, and the performance of the cloud processing device is effectively improved; the on-site hardware cost and on-site maintenance cost are reduced.
Optionally, please refer to fig. 1, the system further includes a cloud storage module. For example, the cloud storage module is a database.
The cloud storage module is in signal connection with the cloud control modules and is configured to store and share the field process data with the cloud control modules.
The cloud storage module stores field process data uploaded by a plurality of field processing devices. And the field process data stored in the cloud storage module from different sources are shared by each cloud processing device in the system. That is, each cloud processing device in the system can use all the field process data stored in the cloud storage module.
The cloud control module is further configured to: acquiring the change trend information of the field process data from the cloud storage module; and training the neural network module to output the controlled variable value according to the change trend information so as to obtain the optimized neural network module.
The embodiment provides the cloud storage module for storing and sharing the field process data from different sources, so that interactive learning can be performed among the neural network models, frequent maintenance work is not needed under the condition of working condition change, and the performance of the cloud processing device is effectively improved.
Optionally, as shown in fig. 2, the cloud processing device further includes a timing module corresponding to the cloud control module.
The timing module is in signal connection with the cloud control module and is configured to send training signals to the cloud control module at regular time according to a preset time period.
The cloud control module is configured to: respectively acquiring main variation trend information and auxiliary variation trend information from the cloud storage module according to the training signal; the main change trend information is the change trend information of the field process data stored in the cloud storage module by the cloud processing device; the secondary change trend information is the change trend information of the field process data stored in the cloud storage module by other cloud processing devices; the cloud processing device has the same function as other cloud processing devices; training the neural network module to output a controlled variable value according to the main change trend information and the corresponding preset main weight value, and the auxiliary change trend information and the corresponding preset auxiliary weight value so as to obtain an optimized neural network module; wherein the preset master weight value is greater than the preset slave weight value.
For example, when a process variable of the gasification furnace equipment changes, the cloud processing device acquires the variable quantity in real time, and calculates the change trend information of the interference variable through the neural network module, wherein the change trend information can influence the controlled variable to exceed the upper limit; according to the situation, the cloud processing device calculates the adjustment quantity of the operation variable corresponding to the controlled variable, and transmits a control signal to the cloud processing device through a network so as to realize optimization control; meanwhile, the neural network model is continuously trained by using the field process data in the cloud storage module so as to ensure that the performance of the cloud processing device is in an optimal state.
In the running process of the cloud processing device, the neural network module contained in the cloud processing device is trained by data in the database at regular time according to a preset time period so as to ensure that the model is in an optimal state and realize the optimal control of the gasification furnace equipment.
The field processing device is monitored in real time, the output of the neural network model is periodically adjusted, and stable control is achieved.
In the embodiment, the field processing device and the cloud processing device are integrated in the cloud, so that the remote online control of the field processing device is realized, the cloud processing devices are based on a neural network model, interactive learning can be performed among the cloud processing devices, frequent maintenance work is not needed under the condition of working condition change, and the performance of the cloud processing devices is effectively improved; the on-site hardware cost and on-site maintenance cost are reduced. The field processing device is monitored in real time, the output of the neural network model is adjusted in time, and stable control is achieved.
Corresponding to the first embodiment provided by the present application, the present application further provides a second embodiment, that is, a device based on cloud-based control. Since the second embodiment is basically similar to the first embodiment, the description is simple, and the relevant portions should be referred to the corresponding description of the first embodiment. The device embodiments described below are merely illustrative.
Fig. 4 shows an embodiment of a cloud-based control method provided in the present application. Fig. 4 is a flowchart of a cloud-based control method according to an embodiment of the present application.
Referring to fig. 4, the present application provides a cloud-based control method, including the following steps:
and step S101, receiving the field process data sent by the corresponding field processing device.
And S102, acquiring a field control strategy according to the field process data.
Optionally, the obtaining a field control policy according to the field process data includes the following steps:
and S102-1, inputting the change trend information of the field process data into an optimized neural network module to obtain the value of a controlled variable.
And S102-2, generating a field control strategy according to the preset control rule and the controlled variable value.
And step S103, sending the field control strategy to the corresponding field processing device so that the field processing device can work according to the control strategy.
Optionally, after receiving the field process data sent by the corresponding field processing device, the method further includes the following steps:
s101-1, storing the received field process data into a shared cloud storage module;
optionally, the method further includes the following steps:
and step S104, acquiring the change trend information of the field process data from the cloud storage module.
Optionally, the obtaining of the change trend information of the field process data from the cloud storage module includes the following steps:
step S104-1, respectively acquiring main change trend information and auxiliary change trend information from the cloud storage module at regular time according to a preset time period; the main change trend information is the change trend information of the field process data stored in the cloud storage module by the cloud processing device; the secondary change trend information is the change trend information of the field process data stored in the cloud storage module by other cloud processing devices; the cloud processing device has the same function as other cloud processing devices.
And S104-2, training the neural network module to output a controlled variable value according to the main change trend information and the corresponding preset main weight value, and the auxiliary change trend information and the corresponding preset auxiliary weight value so as to obtain an optimized neural network module.
Optionally, the preset master weight value is greater than the preset slave weight value.
And S105, training the neural network module to output controlled variable values according to the change trend information so as to obtain an optimized neural network module.
In the embodiment, the field processing device and the cloud processing device are integrated in the cloud, so that the remote online control of the field processing device is realized, the cloud processing devices are based on a neural network model, interactive learning can be performed among the cloud processing devices, frequent maintenance work is not needed under the condition of working condition change, and the performance of the cloud processing devices is effectively improved; the on-site hardware cost and on-site maintenance cost are reduced. The field processing device is monitored in real time, the output of the neural network model is adjusted in time, and stable control is achieved.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A cloud-based control system, comprising: the system comprises a plurality of field processing devices and a cloud processing device corresponding to each field processing device;
the field processing device is configured to obtain field process data;
the cloud processing device is in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device; acquiring a field control strategy according to the field process data; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the control strategy.
2. The control system of claim 1, wherein the cloud processing device comprises: the system comprises a cloud control module and a neural network module;
the neural network module is in signal connection with the corresponding cloud control module, is configured to receive the change trend information of the field process data input by the cloud control module, and outputs a controlled variable value;
the cloud control module is respectively in signal connection with the corresponding field processing device and is configured to: receiving the field process data sent by the corresponding field processing device, and inputting the change trend information of the field process data into an optimized neural network module to obtain the controlled variable value; generating a field control strategy according to a preset control rule and a controlled variable value; and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the field control strategy.
3. The control system of claim 2, further comprising a cloud storage module;
the cloud storage module is in signal connection with the plurality of cloud control modules and is configured to store and share the field process data for the plurality of cloud control modules;
the cloud control module is further configured to: acquiring the change trend information of the field process data from the cloud storage module; and training the neural network module to output the controlled variable value according to the change trend information so as to obtain the optimized neural network module.
4. The control system of claim 2, wherein the cloud processing device further comprises a timing module corresponding to the cloud control module;
the timing module is in signal connection with the cloud control module and is configured to send a training signal to the cloud control module at regular time according to a preset time period;
the cloud control module is configured to: respectively acquiring main variation trend information and auxiliary variation trend information from the cloud storage module according to the training signal; the main change trend information is the change trend information of the field process data stored in the cloud storage module by the cloud processing device; the secondary change trend information is the change trend information of the field process data stored in the cloud storage module by other cloud processing devices; the cloud processing device has the same function as other cloud processing devices; training the neural network module to output a controlled variable value according to the main change trend information and the corresponding preset main weight value, and the auxiliary change trend information and the corresponding preset auxiliary weight value so as to obtain an optimized neural network module; wherein the preset master weight value is greater than the preset slave weight value.
5. The control system of claim 1, wherein the field processing device comprises: the system comprises a gateway, a distributed control module and a controlled module;
the gateway is respectively in signal connection with the distributed control module and the cloud processing device and is configured to transmit data between the distributed control module and the cloud processing device through a network;
the distributed control module is in signal connection with the controlled module and is configured to collect and send the field process data of the controlled module; and receiving the field control strategy and controlling the controlled module to work according to the field control strategy.
6. A control method based on a cloud is applied to a cloud control module and is characterized by comprising the following steps:
receiving field process data sent by a corresponding field processing device;
acquiring a field control strategy according to the field process data;
and sending the field control strategy to the corresponding field processing device so that the field processing device works according to the control strategy.
7. The control method of claim 6, wherein the deriving a field control strategy from the field process data comprises:
inputting the change trend information of the field process data into an optimized neural network module to obtain the value of a controlled variable;
and generating a field control strategy according to the preset control rule and the controlled variable value.
8. The control method according to claim 7, further comprising, after the receiving field process data transmitted by the corresponding field processing device:
storing the received field process data into a shared cloud storage module;
the method further comprises the following steps:
acquiring the change trend information of the field process data from the cloud storage module;
and training the neural network module to output the controlled variable value according to the change trend information so as to obtain the optimized neural network module.
9. The control method according to claim 8, wherein the obtaining of the trend-change information of the field process data from the cloud storage module comprises:
respectively acquiring main change trend information and auxiliary change trend information from the cloud storage module at regular time according to a preset time period; the main change trend information is the change trend information of the field process data stored in the cloud storage module by the cloud processing device; the secondary change trend information is the change trend information of the field process data stored in the cloud storage module by other cloud processing devices; the cloud processing device has the same function as other cloud processing devices;
and training the neural network module to output a controlled variable value according to the main change trend information and the corresponding preset main weight value, and the auxiliary change trend information and the corresponding preset auxiliary weight value so as to obtain an optimized neural network module.
10. The control method according to claim 9, wherein the preset master weight value is greater than the preset slave weight value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910624622.4A CN112213993A (en) | 2019-07-11 | 2019-07-11 | Control system and method based on cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910624622.4A CN112213993A (en) | 2019-07-11 | 2019-07-11 | Control system and method based on cloud |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112213993A true CN112213993A (en) | 2021-01-12 |
Family
ID=74047580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910624622.4A Pending CN112213993A (en) | 2019-07-11 | 2019-07-11 | Control system and method based on cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112213993A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1128601A2 (en) * | 2000-02-21 | 2001-08-29 | Kabushiki Kaisha Toshiba | Transmission system, supervisory control device, method of outputting data in the supervisory control device, and nodes for transmitting data in the transmission system |
| CN1694025A (en) * | 2005-04-28 | 2005-11-09 | 南京科远控制工程有限公司 | Automatic control system based on artificial intelligence for heat-engine plant |
| CN106559501A (en) * | 2016-12-14 | 2017-04-05 | 厦门奥普拓自控科技有限公司 | A kind of flat industry control method and system |
| CN107193266A (en) * | 2017-07-11 | 2017-09-22 | 王焱华 | A kind of platform monitoring system of big data |
| CN108268425A (en) * | 2016-12-30 | 2018-07-10 | 英特尔公司 | Programmable matrix handles engine |
-
2019
- 2019-07-11 CN CN201910624622.4A patent/CN112213993A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1128601A2 (en) * | 2000-02-21 | 2001-08-29 | Kabushiki Kaisha Toshiba | Transmission system, supervisory control device, method of outputting data in the supervisory control device, and nodes for transmitting data in the transmission system |
| CN1694025A (en) * | 2005-04-28 | 2005-11-09 | 南京科远控制工程有限公司 | Automatic control system based on artificial intelligence for heat-engine plant |
| CN106559501A (en) * | 2016-12-14 | 2017-04-05 | 厦门奥普拓自控科技有限公司 | A kind of flat industry control method and system |
| CN108268425A (en) * | 2016-12-30 | 2018-07-10 | 英特尔公司 | Programmable matrix handles engine |
| CN107193266A (en) * | 2017-07-11 | 2017-09-22 | 王焱华 | A kind of platform monitoring system of big data |
Non-Patent Citations (3)
| Title |
|---|
| 张铭钧: "《智能控制技术》", 30 April 2008, 哈尔滨工程大学出版社 * |
| 李晗 等: "基于数据驱动的故障诊断方法综述", 《控制与决策》 * |
| 毕超 等: "工业互联网中的数据采集与控制技术", 《2018中国自动化大会(CAC2018)论文集》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112615379A (en) | Power grid multi-section power automatic control method based on distributed multi-agent reinforcement learning | |
| CN101510092B (en) | Remote control system for water electrolytic hydrogen production | |
| CN102645892B (en) | Nonuniform sampling guaranteed performance control method for multivariable communication-limited network control system | |
| CN1227639A (en) | Process and system for commisioning industrial plants, in particular in the primary industry | |
| Zhang et al. | Stochastic stability of networked control systems with network-induced delay and data dropout | |
| CN111381502A (en) | Intelligent sewage management and control system based on simulation learning and expert system | |
| CN104065168A (en) | Dynamic variable-frequency data collection method for monitoring wind-PV-ES hybrid power generation status | |
| CN112213993A (en) | Control system and method based on cloud | |
| Hua et al. | A robust H∞ control approach for a class of networked control systems with sampling jitter and packet-dropout | |
| Millán et al. | Self-triggered sampling selection based on quadratic programming | |
| CN117039852A (en) | Power prediction method, device, equipment and storage medium of wind-solar-water complementary power station | |
| CN201368471Y (en) | Closed loop combustion optimization control system | |
| CN111461915A (en) | Photovoltaic power plant operation real-time information management system and management method | |
| Hua et al. | Distributed control for uncertain nonlinear multiagent systems subject to hybrid faults | |
| CN101923318A (en) | Method for manufacturing network PID controller | |
| US20210286347A1 (en) | Method for the closed-loop control of a chemical process in an industrial-scale chemical installation | |
| Qiu et al. | Synchronization between two non-autonomous chaotic systems via intermittent event-triggered control | |
| CN110433950A (en) | A kind of pulverizer outlet temperature control device | |
| CN112799367A (en) | Intelligent control system and method based on industrial internet cloud platform | |
| Guan et al. | Stability of internet-based control systems with uncertainties and multiple time-varying delays | |
| CN117478351B (en) | Intelligent optimization method and system for industrial Internet edge calculation | |
| CN108958185A (en) | A kind of Internet of Things intelligence cultivation factory's control method | |
| Sharmila et al. | A survey—networked control systems | |
| Tang et al. | Observer-based event-triggered guaranteed cost control for networked control systems subject to random packet loss | |
| CN116599061B (en) | Power grid operation control method based on reinforcement learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210112 |
|
| RJ01 | Rejection of invention patent application after publication |