CN114779651A - Control method and device of five-constant space system based on Internet of things - Google Patents
Control method and device of five-constant space system based on Internet of things Download PDFInfo
- Publication number
- CN114779651A CN114779651A CN202210689157.4A CN202210689157A CN114779651A CN 114779651 A CN114779651 A CN 114779651A CN 202210689157 A CN202210689157 A CN 202210689157A CN 114779651 A CN114779651 A CN 114779651A
- Authority
- CN
- China
- Prior art keywords
- oxygen concentration
- time node
- difference
- values
- time
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/80—Homes; Buildings
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
Landscapes
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Architecture (AREA)
- Accounting & Taxation (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Environmental & Geological Engineering (AREA)
- Toxicology (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a control method and device of a five-constant space system based on the Internet of things. Acquiring oxygen concentration information of a current time node in a space based on an oxygen concentration sensor of the Internet of things according to a preset time interval, and sending the information to a five-constant space system controller; the five constant space system controller predicts a predicted value of the oxygen concentration of the time node of the next time according to the oxygen concentration information of the current time node and the first neural network model; and executing pre-regulation control of the oxygen concentration based on the predicted value of the oxygen concentration at the next time node. The system prediction model is reversely adjusted by comparing the prediction of a plurality of neural networks based on the historical data and the real data of the first neural network model, so that the prediction of the first neural network model is more accurate and effective.
Description
Technical Field
The invention relates to the field of five-constant space systems, in particular to a control method and device of a five-constant space system based on the Internet of things.
Background
With the development of economy, the requirements of people on living quality are higher and higher, and the traditional air conditioning system can not meet the requirements, so a new concept of a five-constant ecological air conditioning system, namely a regulating system meeting the five requirements of constant temperature, constant humidity, constant oxygen, constant static and constant cleanness, is proposed.
In the prior art, temperature and humidity regulation of a five-constant space system is common, and feedback regulation is executed based on a sensor and a PID. For the adjustment of oxygen concentration, the prediction precision and accuracy are very critical, and the influence on the comfort level of the user is very great, so that a prediction scheme which is more accurate and effective in prediction is urgently needed to predict the oxygen concentration so as to facilitate the adjustment in advance.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a prediction scheme with more accurate and effective prediction to predict the oxygen concentration for adjusting in advance.
The invention provides a control method of a pentastatic space system based on the Internet of things, which comprises the following steps:
s1, acquiring oxygen concentration information of a current time node in a space based on the oxygen concentration sensor of the Internet of things according to a preset time interval, and sending the information to a pentastatic space system controller;
s2, the quintet space system controller predicts the predicted value of the oxygen concentration of the time node of the next time according to the oxygen concentration information of the current time node and the first neural network model; the first neural network model comprises a plurality of neural networks, and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node, and executing acquisition of oxygen concentration difference at adjacent time and oxygen concentration difference at random time; reversely adjusting the first neural network model according to the oxygen concentration difference of the adjacent time and the oxygen concentration difference of the random time;
and S3, the quintet space system controller executes the pre-regulation control of the oxygen concentration based on the predicted value of the oxygen concentration of the time node of the next time node.
Further, the first neural network model comprises a plurality of neural networks, and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node, and executing to obtain an oxygen concentration difference at adjacent time and an oxygen concentration difference at random time; reversely adjusting the first neural network model according to the adjacent time oxygen concentration difference and the random time oxygen concentration difference, wherein the method comprises the following steps:
the number of the neural networks is three, the weights of the three neural networks are the same, the input values of the three neural networks are respectively the oxygen concentration values of the current time node, the previous time node and the historical random time node, and the output values of the oxygen concentration values of the current time node, the previous time node and the historical random time node are respectively the predicted values of the oxygen concentration of the next time node;
the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, compare the oxygen concentration predicted values of the different time nodes with real data difference values after pairwise difference to generate total error cost, and then receive the same total error cost value, so that the weight of each neuron is updated based on a back propagation algorithm.
Further, any one of the three neural networks is represented as a function f (x), wherein the outputs of the three neural networks are:
wherein, the first and the second end of the pipe are connected with each other,to the oxygen concentration value based on the previous time nodePredicting an oxygen concentration prediction value with respect to the time node t;to the oxygen concentration value based on the current time nodeA predicted value of oxygen concentration with respect to the time node t +1, which is predicted;oxygen concentration value based on historical random time nodeA predicted oxygen concentration value for the time node t-s +1 is made.
Further, the three neural networks take the data sets of the nodes at different times as input, then output predicted values of the oxygen concentration of the nodes at different times, and compare the differences between every two nodes with the difference value of the real data to generate total error cost, which comprises the following steps:
wherein the content of the first and second substances,、respectively expressed as the difference between the predicted oxygen concentration values of time nodes t and t +1 and the difference between the predicted oxygen concentration values of time nodes t-s +1 and t + 1;、respectively expressed as the difference between the real oxygen concentration values of the time nodes t and t +1 and the difference between the real oxygen concentration values of the time nodes t-s +1 and t + 1;
further, based on、Performing error cost calculation to obtain Loss1 and Loss 2; and obtains the total error cost based on the sum of Loss1 and Loss 2.
Further, the updating the weight of each neuron based on the back propagation algorithm includes:
based on a gradient descent method, updating the weights is performed such that the total error cost is minimized.
In addition, in a second aspect, a control device for a pentastatic space system based on the internet of things is further provided, where the system includes:
the acquisition module acquires the oxygen concentration information of a current time node in a space based on the oxygen concentration sensor of the Internet of things according to a preset time interval and sends the information to the five-constant-space system controller;
the prediction module is used for predicting the predicted value of the oxygen concentration of the time node of the next time node by the five-constant space system controller according to the oxygen concentration information of the current time node and the first neural network model; the first neural network model comprises a plurality of neural networks, and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node, and executing acquisition of oxygen concentration difference at adjacent time and oxygen concentration difference at random time; reversely adjusting the first neural network model according to the oxygen concentration difference at the adjacent time and the oxygen concentration difference at the random time;
and the five-constant space system controller executes pre-regulation control on the oxygen concentration based on the predicted value of the oxygen concentration of the time node of the next time node.
Further, the first neural network model comprises a plurality of neural networks, and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node, and executing to obtain an oxygen concentration difference at adjacent time and an oxygen concentration difference at random time; reversely adjusting the first neural network model according to the adjacent time oxygen concentration difference and the random time oxygen concentration difference, wherein the method comprises the following steps:
the number of the neural networks is three, the weights of the three neural networks are the same, the input values of the three neural networks are respectively the oxygen concentration values of the current time node, the previous time node and the historical random time node, and the output values of the three neural networks are respectively the predicted values of the oxygen concentration of the next time node under the characteristics of the oxygen concentration values of the current time node, the previous time node and the historical random time node;
the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, compare the oxygen concentration predicted values of the different time nodes with real data difference values after pairwise difference to generate total error cost, and then receive the same total error cost value, so that the weight of each neuron is updated based on a back propagation algorithm.
Further, any one of the three neural networks is represented as a function f (x), wherein the outputs of the three neural networks are:
wherein, the first and the second end of the pipe are connected with each other,to the oxygen concentration value based on the previous time nodePredicting an oxygen concentration prediction value with respect to the time node t;to the oxygen concentration value based on the current time nodeA predicted value of oxygen concentration with respect to the time node t +1, which is predicted;oxygen concentration value based on historical random time nodeA predicted oxygen concentration value for the time node t-s +1 is made.
Further, the three neural networks take different time node data sets as input, then output the oxygen concentration real data of different time nodes, and compare the difference value of every two real data to generate the total error cost, which comprises:
wherein, the first and the second end of the pipe are connected with each other,、expressed as the difference between the predicted oxygen concentration values at time nodes t and t +1, and the difference between the predicted oxygen concentration values at time nodes t-s +1 and t +1, respectively;、respectively expressed as the difference between the real oxygen concentration values of time nodes t and t +1 and the difference between the real oxygen concentration values of time nodes t-s +1 and t + 1;
further, based on、Performing error cost calculation to obtain Loss1 and Loss 2; and obtaining a total error generation based on the summation of Loss1 and Loss2And (4) price.
Further, the updating the weight of each neuron based on the back propagation algorithm includes:
based on a gradient descent method, updating the weights is performed such that the total error cost is minimized.
According to the scheme, oxygen concentration information of a current time node in a space is acquired based on an oxygen concentration sensor of the Internet of things according to a preset time interval and is sent to a five-constant space system controller; the five constant space system controller predicts a predicted value of the oxygen concentration of the time node of the next time according to the oxygen concentration information of the current time node and the first neural network model; the first neural network model comprises a plurality of neural networks and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node and executing to obtain oxygen concentration difference of adjacent time and oxygen concentration difference of random time; reversely adjusting the first neural network model according to the oxygen concentration difference at the adjacent time and the oxygen concentration difference at the random time; and the five constant space system controller executes pre-regulation control on the oxygen concentration based on the predicted value of the oxygen concentration of the time node of the next time node. The reverse adjustment of the system prediction model is executed through comparison of historical data-based prediction and real data of a plurality of neural networks based on the first neural network model, so that the prediction of the first neural network model is more accurate and effective.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a control method of a pentastatic space system based on the internet of things, which is disclosed by the embodiment of the invention;
fig. 2 is a schematic structural diagram of a control device of a five-constant space system based on the internet of things, which is disclosed by the embodiment of the invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It should be noted that: reference herein to "a plurality" means two or more.
The implementation details of the technical solution of the embodiment of the present application are set forth in detail below:
referring to fig. 1, fig. 1 is a schematic flow chart of a control method of a five-constant space system based on the internet of things according to an embodiment of the present invention. As shown in fig. 1, a control method of a five-constant space system based on the internet of things according to an embodiment of the present invention includes:
s1, acquiring oxygen concentration information of a current time node in a space based on the oxygen concentration sensor of the Internet of things according to a preset time interval, and sending the information to the five-constant space system controller;
specifically, in this embodiment, the oxygen concentration information is collected once at a predetermined time interval, for example, once at time t, and once at time t +1, where the time interval between the two is a predetermined time interval.
S2, the quintet space system controller predicts the predicted value of the oxygen concentration of the time node of the next time according to the oxygen concentration information of the current time node and the first neural network model; the first neural network model comprises a plurality of neural networks, and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node, and executing acquisition of oxygen concentration difference at adjacent time and oxygen concentration difference at random time; reversely adjusting the first neural network model according to the oxygen concentration difference of the adjacent time and the oxygen concentration difference of the random time;
and S3, the quintet space system controller executes the pre-regulation control of the oxygen concentration based on the predicted value of the oxygen concentration of the time node of the next time node.
Specifically, in this embodiment, based on the predicted value of the oxygen concentration at the time node of the next time node, if the predicted value is lower than the predetermined value range, the adjustment is performed in advance to keep the oxygen content within the constant comfortable range for the user.
Further, the first neural network model comprises a plurality of neural networks, and is used for receiving the oxygen concentration values of the current time node, the previous time node and the historical random time node, and executing to obtain the oxygen concentration difference at the adjacent time and the oxygen concentration difference at the random time; reversely adjusting the first neural network model according to the adjacent time oxygen concentration difference and the random time oxygen concentration difference, wherein the method comprises the following steps:
the number of the neural networks is three, the weights of the three neural networks are the same, the input values of the three neural networks are respectively the oxygen concentration values of the current time node, the previous time node and the historical random time node, and the output values of the three neural networks are respectively the predicted values of the oxygen concentration of the next time node under the characteristics of the oxygen concentration values of the current time node, the previous time node and the historical random time node;
the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, compare the oxygen concentration predicted values of the different time nodes with real data difference values after pairwise subtraction to generate total error cost, and then receive the same total error cost value, so that the weight of each neuron is updated based on a back propagation algorithm.
Further, any one of the three neural networks is represented as a function f (x), wherein the outputs of the three neural networks are:
wherein the content of the first and second substances,as oxygen concentration values based on previous time nodeA predicted value of oxygen concentration with respect to the time node t for making a prediction;to the oxygen concentration value based on the current time nodeA predicted value of oxygen concentration with respect to the time node t +1, which is predicted;oxygen concentration value based on historical random time nodeA predicted oxygen concentration value for the time node t-s +1 is made.
Further, the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, and compare the difference between every two nodes with a real data difference value to generate a total error cost, and the method comprises the following steps:
wherein, the first and the second end of the pipe are connected with each other,、expressed as the difference between the predicted oxygen concentration values at time nodes t and t +1, and the difference between the predicted oxygen concentration values at time nodes t-s +1 and t +1, respectively;、the real values of the oxygen concentration are respectively expressed as time nodes t and t +1The difference between the real values of the oxygen concentration at the time nodes t-s +1 and t + 1;
further, based on、Performing error cost calculation to obtain Loss1 and Loss 2; and obtains the total error cost based on the sum of Loss1 and Loss 2.
Further, the updating the weight of each neuron based on the back propagation algorithm includes:
based on a gradient descent method, updating the weights is performed so as to minimize the total error cost, thereby realizing updating of the weights of the first neural network model and facilitating more accurate prediction.
Specifically, in the present embodiment, the Back Propagation Algorithm is BP Algorithm (Error Back Propagation Algorithm).
In addition, in a second aspect, this embodiment further provides a control device for a pentastatic space system based on the internet of things, where the system includes:
the acquisition module 10 acquires oxygen concentration information of a current time node in a space based on an oxygen concentration sensor of the internet of things according to a preset time interval and sends the information to the five-constant-space system controller;
the prediction module 20 predicts the predicted value of the oxygen concentration of the time node of the next time according to the oxygen concentration information of the current time node and the first neural network model by the five constant space system controllers; the first neural network model comprises a plurality of neural networks, and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node, and executing acquisition of oxygen concentration difference at adjacent time and oxygen concentration difference at random time; reversely adjusting the first neural network model according to the oxygen concentration difference of the adjacent time and the oxygen concentration difference of the random time;
and the adjusting module 30 is used for executing the pre-adjusting control of the oxygen concentration by the five-constant space system controller based on the predicted value of the oxygen concentration at the time node of the next time node.
Further, the first neural network model comprises a plurality of neural networks, and is used for receiving the oxygen concentration values of the current time node, the previous time node and the historical random time node, and executing to obtain the oxygen concentration difference at the adjacent time and the oxygen concentration difference at the random time; reversely adjusting the first neural network model according to the adjacent time oxygen concentration difference and the random time oxygen concentration difference, wherein the method comprises the following steps:
the number of the neural networks is three, the weights of the three neural networks are the same, the input values of the three neural networks are respectively the oxygen concentration values of the current time node, the previous time node and the historical random time node, and the output values of the three neural networks are respectively the predicted values of the oxygen concentration of the next time node under the characteristics of the oxygen concentration values of the current time node, the previous time node and the historical random time node;
the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, compare the oxygen concentration predicted values of the different time nodes with real data difference values after pairwise difference to generate total error cost, and then receive the same total error cost value, so that the weight of each neuron is updated based on a back propagation algorithm.
Further, any one of the three neural networks is represented as a function f (x), wherein the outputs of the three neural networks are:
wherein the content of the first and second substances,as oxygen concentration values based on previous time nodePredicting an oxygen concentration prediction value with respect to the time node t;to the oxygen concentration value based on the current time nodeA predicted value of oxygen concentration with respect to the time node t +1, which is predicted;oxygen concentration value based on historical random time nodeA predicted value of the oxygen concentration with respect to the time node t-s +1 is made.
Further, the three neural networks take different time node data sets as input, then output the oxygen concentration real data of different time nodes, and compare the difference value of every two real data to generate the total error cost, which comprises:
wherein the content of the first and second substances,、respectively expressed as the difference between the predicted oxygen concentration values of time nodes t and t +1 and the difference between the predicted oxygen concentration values of time nodes t-s +1 and t + 1;、respectively expressed as the difference between the real oxygen concentration values of the time nodes t and t +1 and the difference between the real oxygen concentration values of the time nodes t-s +1 and t + 1;
further, based on、Performing error cost calculation to obtain Loss1 and Loss 2; and obtains the total error cost based on the sum of Loss1 and Loss 2.
Further, the updating the weight of each neuron based on the back propagation algorithm includes:
based on a gradient descent method, updating the weights is performed such that the total error cost is minimized.
In addition, the embodiment of the application also discloses an electronic device, which comprises: one or more processors, memory for storing one or more computer programs; wherein the computer program is configured to be executed by the one or more processors, the program comprising control method steps for executing an internet of things based penta-constant space system as described above.
In addition, the embodiment of the application also provides a storage medium, and the storage medium stores a computer program; the program is loaded and executed by a processor to implement the control method steps of the internet of things based pentastatic space system as described above.
Those of ordinary skill in the art will appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The elements described as separate parts may or may not be physically separate, as one of ordinary skill in the art would appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general sense in the foregoing description for clarity of explanation of the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a grid device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only examples of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A control method of a pentastatic space system based on the Internet of things is characterized by comprising the following steps:
s1, acquiring oxygen concentration information of a current time node in a space based on the oxygen concentration sensor of the Internet of things according to a preset time interval, and sending the information to the five-constant space system controller;
s2, the quintet space system controller predicts the predicted value of the oxygen concentration of the time node of the next time according to the oxygen concentration information of the current time node and the first neural network model; the first neural network model comprises a plurality of neural networks and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node and executing to obtain oxygen concentration difference of adjacent time and oxygen concentration difference of random time; reversely adjusting the first neural network model according to the oxygen concentration difference at the adjacent time and the oxygen concentration difference at the random time;
and S3, the quintet space system controller executes the pre-regulation control of the oxygen concentration based on the predicted value of the oxygen concentration of the time node of the next time node.
2. The internet of things-based five-constant space system control method according to claim 1, wherein the first neural network model comprises a plurality of neural networks, and is configured to receive oxygen concentration values of a current time node, a previous time node, and a historical random time node, and perform acquisition of an adjacent time oxygen concentration difference and a random time oxygen concentration difference; reversely adjusting the first neural network model according to the adjacent time oxygen concentration difference and the random time oxygen concentration difference, wherein the method comprises the following steps:
the number of the neural networks is three, the weights of the three neural networks are the same, the input values of the three neural networks are respectively the oxygen concentration values of the current time node, the previous time node and the historical random time node, and the output values of the oxygen concentration values of the current time node, the previous time node and the historical random time node are respectively the predicted values of the oxygen concentration of the next time node;
the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, compare the oxygen concentration predicted values of the different time nodes with real data difference values after pairwise subtraction to generate total error cost, and then receive the same total error cost value, so that the weight of each neuron is updated based on a back propagation algorithm.
3. The internet of things-based pentastatic space system control method according to claim 2, wherein any one of the three neural networks is represented as a function f (x), wherein the outputs of the three neural networks are respectively:
wherein the content of the first and second substances,to the oxygen concentration value based on the previous time nodeA predicted value of oxygen concentration with respect to the time node t for making a prediction;to the oxygen concentration value based on the current time nodeA predicted value of oxygen concentration with respect to the time node t +1, which is predicted;oxygen concentration value based on historical random time nodeA predicted value of the oxygen concentration with respect to the time node t-s +1 is made.
4. The Internet of things-based five-constant space system control method according to claim 3, wherein the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, and compare the difference between every two nodes with a real data difference value to generate a total error cost, and the method comprises the following steps:
wherein the content of the first and second substances,、respectively expressed as the difference between the predicted oxygen concentration values of time nodes t and t +1 and the difference between the predicted oxygen concentration values of time nodes t-s +1 and t + 1;、respectively expressed as the difference between the real oxygen concentration values of time nodes t and t +1 and the difference between the real oxygen concentration values of time nodes t-s +1 and t + 1;
5. The Internet of things-based pentastatic space system control method according to claim 4, wherein the updating of the weight of each neuron based on a back propagation algorithm comprises:
based on a gradient descent method, updating the weights is performed such that the total error cost is minimized.
6. The utility model provides a five permanent space system's controlling means based on thing networking which characterized in that, the system includes:
the acquisition module acquires the oxygen concentration information of a current time node in a space based on the oxygen concentration sensor of the Internet of things according to a preset time interval and sends the information to the five-constant-space system controller;
the prediction module is used for predicting the predicted value of the oxygen concentration of the time node of the next time node by the five constant space system controller according to the oxygen concentration information of the current time node and the first neural network model; the first neural network model comprises a plurality of neural networks and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node and executing to obtain oxygen concentration difference of adjacent time and oxygen concentration difference of random time; reversely adjusting the first neural network model according to the oxygen concentration difference at the adjacent time and the oxygen concentration difference at the random time;
and the regulating module is used for executing the pre-regulation control on the oxygen concentration on the basis of the predicted value of the oxygen concentration of the time node of the next time node by the five-constant space system controller.
7. The Internet of things-based five-constant-space system control device according to claim 6, wherein the first neural network model comprises a plurality of neural networks, and is used for receiving oxygen concentration values of a current time node, a previous time node and a historical random time node, and executing acquisition of an adjacent time oxygen concentration difference and a random time oxygen concentration difference; reversely adjusting the first neural network model according to the adjacent time oxygen concentration difference and the random time oxygen concentration difference, wherein the method comprises the following steps:
the number of the neural networks is three, the weights of the three neural networks are the same, the input values of the three neural networks are respectively the oxygen concentration values of the current time node, the previous time node and the historical random time node, and the output values of the oxygen concentration values of the current time node, the previous time node and the historical random time node are respectively the predicted values of the oxygen concentration of the next time node;
the three neural networks take different time node data sets as input, then output oxygen concentration predicted values of different time nodes, compare the oxygen concentration predicted values of the different time nodes with real data difference values after pairwise subtraction to generate total error cost, and then receive the same total error cost value, so that the weight of each neuron is updated based on a back propagation algorithm.
8. The internet of things-based pentastatic space system control device of claim 7, wherein any one of the three neural networks is expressed as a function f (x), wherein the outputs of the three neural networks are respectively:
wherein, the first and the second end of the pipe are connected with each other,as oxygen concentration values based on previous time nodeA predicted value of oxygen concentration with respect to the time node t for making a prediction;to the oxygen concentration value based on the current time nodeA predicted value of oxygen concentration with respect to time node t +1 for prediction;oxygen concentration value based on historical random time nodeA predicted value of the oxygen concentration with respect to the time node t-s +1 is made.
9. The internet of things-based control device for a penta-constant space system as claimed in claim 8, wherein the three neural networks take different time node data sets as input, then output oxygen concentration real data of different time nodes, and generate a total error cost by comparing the difference between every two nodes with a real data difference value, and the method comprises:
wherein the content of the first and second substances,、respectively expressed as the difference between the predicted oxygen concentration values of time nodes t and t +1 and the difference between the predicted oxygen concentration values of time nodes t-s +1 and t + 1;、respectively expressed as the difference between the real oxygen concentration values of the time nodes t and t +1 and the difference between the real oxygen concentration values of the time nodes t-s +1 and t + 1;
10. The internet of things-based pentastatic space system control device of claim 9, wherein the updating the weight of each neuron based on a back propagation algorithm comprises:
based on a gradient descent method, updating the weights is performed such that the total error cost is minimized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210689157.4A CN114779651A (en) | 2022-06-17 | 2022-06-17 | Control method and device of five-constant space system based on Internet of things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210689157.4A CN114779651A (en) | 2022-06-17 | 2022-06-17 | Control method and device of five-constant space system based on Internet of things |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114779651A true CN114779651A (en) | 2022-07-22 |
Family
ID=82421882
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210689157.4A Pending CN114779651A (en) | 2022-06-17 | 2022-06-17 | Control method and device of five-constant space system based on Internet of things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114779651A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103197538A (en) * | 2013-04-24 | 2013-07-10 | 中南林业科技大学 | Brooder temperature control method based on process neural network |
CN103309370A (en) * | 2013-06-01 | 2013-09-18 | 中南林业科技大学 | Incubating room humidity control method based on BP (back-propagation) neural network |
CN106292802A (en) * | 2016-09-18 | 2017-01-04 | 中国农业大学 | A kind of Intelligent Prediction Control System for fish and vegetable symbiotic system and method |
CN108133289A (en) * | 2017-12-21 | 2018-06-08 | 中国铁建电气化局集团有限公司 | Tunnel ventilation control method and system based on environmental forecasting |
CN108460492A (en) * | 2018-03-19 | 2018-08-28 | 国通广达(北京)技术有限公司 | A kind of pipe gallery internal oxygen concentration LSTM prediction techniques and system |
CN108921359A (en) * | 2018-07-26 | 2018-11-30 | 安徽大学 | A kind of distribution gas density prediction technique and device |
CN112378030A (en) * | 2020-08-04 | 2021-02-19 | 氧知元医疗科技(上海)有限公司 | Constant oxygen and constant humidity intelligent integrated control system and working method thereof |
CN112418498A (en) * | 2020-11-12 | 2021-02-26 | 中国农业大学 | Temperature prediction method and system for intelligent greenhouse |
CN114298270A (en) * | 2021-12-03 | 2022-04-08 | 北京彩云环太平洋科技有限公司 | Pollutant concentration prediction method fusing domain knowledge and related equipment thereof |
-
2022
- 2022-06-17 CN CN202210689157.4A patent/CN114779651A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103197538A (en) * | 2013-04-24 | 2013-07-10 | 中南林业科技大学 | Brooder temperature control method based on process neural network |
CN103309370A (en) * | 2013-06-01 | 2013-09-18 | 中南林业科技大学 | Incubating room humidity control method based on BP (back-propagation) neural network |
CN106292802A (en) * | 2016-09-18 | 2017-01-04 | 中国农业大学 | A kind of Intelligent Prediction Control System for fish and vegetable symbiotic system and method |
CN108133289A (en) * | 2017-12-21 | 2018-06-08 | 中国铁建电气化局集团有限公司 | Tunnel ventilation control method and system based on environmental forecasting |
CN108460492A (en) * | 2018-03-19 | 2018-08-28 | 国通广达(北京)技术有限公司 | A kind of pipe gallery internal oxygen concentration LSTM prediction techniques and system |
CN108921359A (en) * | 2018-07-26 | 2018-11-30 | 安徽大学 | A kind of distribution gas density prediction technique and device |
CN112378030A (en) * | 2020-08-04 | 2021-02-19 | 氧知元医疗科技(上海)有限公司 | Constant oxygen and constant humidity intelligent integrated control system and working method thereof |
CN112418498A (en) * | 2020-11-12 | 2021-02-26 | 中国农业大学 | Temperature prediction method and system for intelligent greenhouse |
CN114298270A (en) * | 2021-12-03 | 2022-04-08 | 北京彩云环太平洋科技有限公司 | Pollutant concentration prediction method fusing domain knowledge and related equipment thereof |
Non-Patent Citations (1)
Title |
---|
王丹娜等: "基于ZigBee的医用高压氧舱氧气浓度自动控制系统", 《设计与制造》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Claessens et al. | Convolutional neural networks for automatic state-time feature extraction in reinforcement learning applied to residential load control | |
Ain et al. | IoT operating system based fuzzy inference system for home energy management system in smart buildings | |
Akbilgic et al. | A novel hybrid RBF neural networks model as a forecaster | |
Pfister et al. | Learning stable and predictive structures in kinetic systems | |
Hamdi et al. | Fault diagnosis based on sliding mode observer for LPV descriptor systems | |
CN103597418A (en) | Apparatus and method for pH control in wastewater treatment plants and other systems | |
CN110458355A (en) | Event prediction method, apparatus, equipment and storage medium | |
Amasyali et al. | Deep reinforcement learning for autonomous water heater control | |
Jurado et al. | Stochastic MPC with applications to process control | |
CN112990958A (en) | Data processing method, data processing device, storage medium and computer equipment | |
Shekhar et al. | Optimal and sensitivity analysis of vacation queueing system with F-policy and vacation interruption | |
JP4698578B2 (en) | Methods and articles for detecting, verifying, and repairing collinearity | |
Bouazza et al. | Smart Petri nets temperature control framework for reducing building energy consumption | |
Fujisaki et al. | Mixed deterministic/randomized methods for fixed order controller design | |
Frenkel et al. | Experiments-based comparison of different power controllers for a solid oxide fuel cell against model imperfections and delay phenomena | |
Niembro-Ceceña et al. | Auto-regression model-based off-line PID controller tuning: An adaptive strategy for DC motor control | |
Kek et al. | An integrated optimal control algorithm for discrete-time nonlinear stochastic system | |
Hametner et al. | PID controller design for nonlinear systems represented by discrete-time local model networks | |
Korkidis et al. | Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings | |
Turhan et al. | Performance analysis of data-driven and model-based control strategies applied to a thermal unit model | |
Rauh | Kalman filter-based real-time implementable optimization of the fuel efficiency of solid oxide fuel cells | |
CN114779651A (en) | Control method and device of five-constant space system based on Internet of things | |
Mendoza-Serrano et al. | Smart grid coordination in building HVAC systems: Computational efficiency of constrained economic linear optimal control | |
Zhang et al. | A model predictive control framework for constrained uncertain positive systems | |
Ramírez et al. | Computational burden reduction in min–max MPC |
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: 20220722 |
|
RJ01 | Rejection of invention patent application after publication |