CN116755496A - Clean room temperature humidity control method and system - Google Patents
Clean room temperature humidity control method and system Download PDFInfo
- Publication number
- CN116755496A CN116755496A CN202311041660.XA CN202311041660A CN116755496A CN 116755496 A CN116755496 A CN 116755496A CN 202311041660 A CN202311041660 A CN 202311041660A CN 116755496 A CN116755496 A CN 116755496A
- Authority
- CN
- China
- Prior art keywords
- control
- temperature
- humidity
- clean room
- relation
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000007405 data analysis Methods 0.000 claims abstract description 67
- 238000005457 optimization Methods 0.000 claims abstract description 63
- 239000013068 control sample Substances 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims description 35
- 230000008878 coupling Effects 0.000 claims description 35
- 238000010168 coupling process Methods 0.000 claims description 35
- 238000005859 coupling reaction Methods 0.000 claims description 35
- 239000000523 sample Substances 0.000 claims description 24
- 238000010276 construction Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000005265 energy consumption Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000013210 evaluation model Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000012482 interaction analysis Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 13
- 238000013507 mapping Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 230000009467 reduction Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
Abstract
The application provides a clean room temperature and humidity control method and system, which relate to the technical field of intelligent control, and are characterized in that a temperature and humidity control sample set is collected, then a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement, a temperature and humidity set value-acquisition value functional relation is fitted, a plurality of data analysis channels are constructed, a data analysis optimization model is constructed by channel connection, the current clean room control requirement is obtained, the parameter control requirement is decomposed, the control parameter optimization model is input, a temperature and humidity control scheme is obtained and sent to a controller for temperature and humidity control, the technical problems that the temperature and humidity control method of the clean room has technical limitations, insufficient control stability and accuracy and certain energy waste in the prior art are solved, the control parameter is determined and modeled for parameter control optimization by control interaction analysis, reasonable planning of control energy is performed, and the control stability and accuracy are ensured.
Description
Technical Field
The application relates to the technical field of intelligent control, in particular to a clean room temperature and humidity control method and system.
Background
Because of the control of the clean room of the pharmaceutical factory has the advantages of multiple variables, nonlinearity and hysteresis, and the control of the temperature and the humidity has the mutual influence, the control of the stability and the accuracy of regulation and control are difficult to control. At present, control and debugging of another control amount are mainly performed through control of a single control amount, and based on a control effect, certain limitations exist.
The prior art has technical limitations on a temperature and humidity control method of a clean room, has insufficient control stability and accuracy, and has certain energy waste.
Disclosure of Invention
The application provides a clean room temperature and humidity control method and a clean room temperature and humidity control system, which are used for solving the technical problems that the temperature and humidity control method for the clean room in the prior art has technical limitations, the control stability and accuracy are insufficient, and certain energy is wasted.
In view of the above, the present application provides a clean room temperature humidity control method and system.
In a first aspect, the present application provides a clean room temperature humidity control method comprising:
collecting clean room temperature and humidity control sample data, and constructing a temperature and humidity control sample set, wherein the temperature and humidity control sample set comprises a temperature and humidity set value, a temperature and humidity acquisition value and a clean room variable control requirement;
fitting a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement and temperature and humidity set value-acquisition value function relation based on the temperature and humidity set value, temperature and humidity acquisition value and clean room variable control requirement in the temperature and humidity control sample set;
based on all the functional relationships, constructing a plurality of corresponding data analysis channels, wherein the data analysis channels are used for carrying out data control quantity analysis conversion based on the functional relationships;
connecting a plurality of data analysis channels to construct a data analysis optimization model;
acquiring the current clean room control requirement, and decomposing parameter control requirements according to the current clean room control requirement;
and inputting the parameter control requirement into the data analysis optimization model, performing control parameter optimization, obtaining a temperature and humidity control scheme, and sending the temperature and humidity control scheme to a controller for temperature and humidity control.
In a second aspect, the present application provides a clean room temperature humidity control system, the system comprising:
the sample set construction module is used for collecting clean room temperature and humidity control sample data and constructing a temperature and humidity control sample set, and the temperature and humidity control sample set comprises a temperature and humidity set value, a temperature and humidity acquisition value and a clean room variable control requirement;
the functional relation fitting module is used for fitting a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement and temperature and humidity set value-acquisition value functional relation based on the temperature and humidity set value, the temperature and humidity acquisition value and the clean room variable control requirement in the temperature and humidity control sample set;
the channel construction module is used for constructing a plurality of corresponding data analysis channels based on all the functional relationships, and the data analysis channels are used for carrying out data control quantity analysis conversion based on the functional relationships;
the model construction module is used for connecting a plurality of data analysis channels to construct a data analysis optimization model;
the control requirement decomposition module is used for acquiring the current clean room control requirement and decomposing the parameter control requirement according to the current clean room control requirement;
and the optimization control module is used for inputting the parameter control requirements into the data analysis optimization model to control parameter optimization, obtaining a temperature and humidity control scheme and sending the temperature and humidity control scheme to a controller to perform temperature and humidity control.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
according to the clean room temperature and humidity control method provided by the embodiment of the application, clean room temperature and humidity control sample data are collected, a temperature and humidity control sample set is constructed, the temperature and humidity control sample set comprises a temperature and humidity set value, a temperature and humidity acquisition value and a clean room variable control requirement, and then a temperature-humidity function relationship, a temperature-temperature function relationship, a temperature-clean room variable control requirement, a temperature and humidity set value-acquisition value function relationship are fitted, and a plurality of corresponding data analysis channels are constructed based on all the function relationships and used for carrying out data control quantity analysis conversion based on the function relationships; connecting a plurality of data analysis channels to construct a data analysis optimization model; the method comprises the steps of obtaining the control requirements of a current clean room and decomposing the parameter control requirements, inputting the control parameters into the data analysis optimization model, optimizing the control parameters to obtain a temperature and humidity control scheme, sending the temperature and humidity control scheme to a controller for temperature and humidity control, solving the technical problems that the temperature and humidity control method of the clean room in the prior art is limited, the control stability and the accuracy are insufficient, and certain energy is wasted.
Drawings
FIG. 1 is a schematic flow chart of a clean room temperature humidity control method provided by the application;
FIG. 2 is a schematic diagram of a process for obtaining a temperature-humidity function relationship in a clean room temperature humidity control method according to the present application;
FIG. 3 is a schematic diagram of a data analysis optimization model construction flow in the clean room temperature humidity control method;
FIG. 4 is a schematic diagram of a clean room temperature humidity control system according to the present application.
Reference numerals illustrate: the system comprises a sample set constructing module 11, a functional relation fitting module 12, a channel constructing module 13, a model constructing module 14, a control requirement decomposing module 15 and an optimizing control module 16.
Detailed Description
According to the clean room temperature and humidity control method and system, a temperature and humidity control sample set is collected, a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement and temperature and humidity set value-acquisition value functional relation are fitted, a plurality of data analysis channels are constructed, channel connection is carried out to construct a data analysis optimization model, the current clean room control requirement is obtained, parameter control requirement is decomposed, control parameter optimization is carried out in the data analysis optimization model, a temperature and humidity control scheme is obtained and sent to a controller for temperature and humidity control, and the technical limitations of the temperature and humidity control method for the clean room in the prior art are solved, the control stability and accuracy are insufficient, and a certain energy waste technical problem is solved.
Example 1
As shown in fig. 1, the present application provides a clean room temperature humidity control method, comprising:
step S100: collecting clean room temperature and humidity control sample data, and constructing a temperature and humidity control sample set, wherein the temperature and humidity control sample set comprises a temperature and humidity set value, a temperature and humidity acquisition value and a clean room variable control requirement;
specifically, as the control of the clean room of the pharmaceutical factory has multiple variables, nonlinearity and hysteresis, and the control of the temperature and the humidity has mutual influence, the control of the regulation stability and the precision is difficult. According to the clean room temperature humidity control method provided by the application, the control parameter analysis is performed according to the control requirement by analyzing the interaction relation among the control parameters, the parameter control optimization is performed by modeling, and the control effect is maximally ensured to be consistent with the control requirement.
Specifically, in the predetermined time interval, that is, in the time range of data acquisition and calling, performing temperature and humidity history control record acquisition on the clean room, performing record identification to determine the same time sequence data and integrating the same time sequence data, and determining a preset temperature and humidity required regulation value as the temperature and humidity set value; determining to execute control operation based on the temperature and humidity set value, and acquiring actual control temperature and humidity aiming at a control effect as the temperature and humidity acquisition value; and determining the other control requirements such as the air composition requirement, the air flow speed, the cleanliness and the like in the clean room, namely, synchronizing the control requirements with the cross-correlation of the temperature and the humidity to measure the ultra-clean environment, and taking the control requirements as the variable control requirements of the clean room. Integrating the temperature and humidity control value, the temperature and humidity acquisition value and the clean room variable control requirement, and performing mapping association to generate a temperature and humidity control sample set, wherein the temperature and humidity control sample set is a basic acquisition data source for performing interaction analysis.
Step S200: fitting a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement and temperature and humidity set value-acquisition value function relation based on the temperature and humidity set value, temperature and humidity acquisition value and clean room variable control requirement in the temperature and humidity control sample set;
specifically, the temperature and humidity control sample set is subjected to data identification, each control parameter is subjected to interaction analysis based on the temperature and humidity set value, the temperature and humidity acquisition value and the clean room variable control requirement corresponding to mapping, and the temperature-humidity, the temperature-clean room variable control requirement, the humidity-clean room variable control requirement and the temperature and humidity set value-acquisition value function relation are obtained through fitting. Specifically, mapping and correlating the temperature and humidity set values with the temperature and humidity acquisition values, and determining the relative trend of the two sets of data as the temperature and humidity set value-acquisition value function relation.
Further, as shown in fig. 2, based on the temperature and humidity set value, the temperature and humidity acquisition value, the clean room variable control requirement, the temperature-humidity, the temperature-clean room variable control requirement, and the humidity-clean room variable control requirement function relationship in the temperature and humidity control sample set, step S200 of the present application further includes:
step S210-1: classifying the temperature and humidity control sample set based on preset environmental parameters to construct a multi-environment sample set;
step S220-1: respectively carrying out temperature and humidity set value and loss amount calculation of a temperature and humidity acquisition value on the multi-environment sample cluster, determining temperature loss amount and humidity loss amount, and fitting a temperature and humidity loss relation based on the temperature loss amount and the humidity loss amount;
step S230-1: performing temperature and humidity coupling relation analysis according to the temperature and humidity set values, and determining a temperature and humidity coupling relation;
step S240-1: performing adjustment trend relation analysis based on the temperature loss amount, the humidity loss amount and the temperature and humidity coupling relation, and fitting the humidity coupling loss relation and the temperature coupling loss relation respectively;
step S250-1: determining a relationship adjustment coefficient by utilizing the humidity coupling loss relationship and the temperature coupling loss relationship;
step S260-1: and fitting to obtain a temperature-humidity function relation based on the relation adjustment coefficient and the temperature and humidity loss relation.
Specifically, the change of the external environment affects the control energy efficiency of the clean room to a certain extent, that is, the control effect finally achieved by the influence of the external environment is different for the same control parameters. And performing external environment division, for example, determining corresponding multi-class external environment parameters based on seasonal climate change, and defining corresponding temperature interval, humidity interval and other measurement standards for different climates as the preset environment parameters. And carrying out interval attribution division on the temperature and humidity control sample set based on the preset environmental parameters to obtain the multi-environment sample cluster.
Furthermore, under the synchronous regulation and control operation of temperature and humidity, the temperature rise can cause the reduction of relative humidity, and the relative humidity is reduced by 2% -3% every 1 ℃ when the temperature rises generally, and meanwhile, the temperature and humidity are influenced by external environment, the specific temperature and humidity interaction degree is different, and targeted refinement analysis is respectively carried out based on multiple environments. Based on the multi-environment sample clusters, carrying out difference calculation on the temperature set value and the temperature acquisition value, and the humidity set value and the humidity acquisition value corresponding to the mapping according to sample data in each environment sample cluster, and taking a difference calculation result as the temperature loss amount and the humidity loss amount. And further determining a measure of a mutual loss limit based on the temperature loss amount and the humidity loss amount, for example, a temperature rise-a relative humidity fall, a humidity rise-a relative temperature fall.
Further, based on the temperature and humidity set values, analysis of the temperature and humidity coupling relation is performed, under the condition of determining synchronous control operation, cooperative control quantity of the temperature and humidity is performed, for example, different temperature set values respectively correspond to a relatively stable humidity set value, and the temperature and humidity set values are used as the temperature and humidity coupling relation. Carrying out temperature and humidity coupling loss analysis based on the temperature loss value, the humidity loss value and the temperature and humidity coupling relation, specifically taking the temperature as a fixed value, carrying out loss measurement of a humidity set value corresponding to a temperature set value, determining humidity values adjusted based on corresponding humidity loss amounts, for example, the humidity set values are respectively 25-30%, and carrying out adjustment of the humidity set values, for example, the humidity set values are adjusted to 28% based on the humidity loss amounts corresponding to the temperature, wherein 25-28% is the humidity coupling loss relation after loss assessment; and similarly, taking the humidity as a fixed value, measuring the loss of a temperature set value corresponding to the humidity set value, and determining the coupling relation between the humidity set value and the temperature set value after the temperature loss is regulated, wherein the coupling relation is taken as the temperature coupling loss relation, and specifically, the corresponding loss measurement values are different in different external environments.
Further, based on the humidity coupling relation and the temperature coupling relation, corresponding temperature amplitude modulation and humidity amplitude modulation in the current environment are determined and used as the relation adjustment coefficient. And performing loss reduction adjustment on the coupling temperature and humidity based on the relation adjustment coefficient and the temperature and humidity loss relation, determining an accurate functional relation after mutual influence loss reduction under the coupling cooperative regulation, namely performing relative control on the pre-controlled temperature and humidity relation after loss reduction when the actual temperature and humidity control is met.
Preferably, the measurement of the above-mentioned relations of temperature, humidity, loss amount, coupling and the like can be respectively carried out by constructing a coordinate system, so that the relation analysis is convenient, for example, when the loss amount analysis is carried out, the temperature and the humidity loss amount are taken as the coordinate axes, the distribution of sample coordinate points is carried out, and the corresponding temperature loss trend is determined based on the humidity loss amounts at different temperatures and is used for assisting in carrying out the temperature and humidity loss relation measurement.
Further, based on the temperature and humidity set point, the temperature and humidity acquisition value, the clean room variable control requirement in the temperature and humidity control sample set, fitting a temperature-humidity, a temperature-clean room variable control requirement, and a humidity-clean room variable control requirement function relationship, the step S200 of the present application further includes:
step S210-2: respectively analyzing the adjustment relation between the temperature and humidity set values and the control requirement of the clean room variables to the multi-environment sample cluster, and determining the adjustment relation between the clean room variables and the temperature set values and the adjustment relation between the clean room variables and the humidity set values;
step S220-2: and respectively fitting to obtain a temperature-clean room variable control requirement function relation and a humidity-clean room variable control requirement function relation based on the adjustment relation between each clean room variable and the temperature set value and the adjustment relation between each clean room variable and the humidity set value.
Specifically, under temperature and humidity regulation, synchronization can influence other control variables in a clean room, such as humidity reduction, relative increase of air dust content and the like, and simultaneously, under different external environment influences, corresponding variable amplitude modulation is different. Based on the multi-environment sample clusters, respectively analyzing the adjustment relation between the temperature set values and the clean room variable control requirements, for example, the influence relation between different temperature set values and the clean room variables, namely, the mapping relation between the temperature amplitude modulation and the one-to-many relation between the clean room variable amplitude modulation; and respectively carrying out an adjustment relation between the humidity set value and each clean room variable, namely a mapping relation between humidity amplitude modulation and one-to-many relation between each clean room variable amplitude modulation. Further, based on the adjustment relation between each clean room variable and the temperature set value, a mapping function relation between the clean room variable control requirement and the temperature, namely, a total probability relation for measuring the interaction degree between the temperature change and each control variable is determined, and based on one party, the influence degree to the other party can be determined. And similarly, fitting and determining a humidity-clean room variable control requirement function relation based on the adjustment relation between each clean room variable and the humidity set value. By refining the interaction relationship between the control parameters based on the sample data, a subsequent parametric control analysis is padded.
Step S300: based on all the functional relationships, constructing a plurality of corresponding data analysis channels, wherein the data analysis channels are used for carrying out data control quantity analysis conversion based on the functional relationships;
step S400: connecting a plurality of data analysis channels to construct a data analysis optimization model;
based on all functional relations, including temperature-humidity, temperature-clean room variable control requirements, humidity-clean room variable control requirements and temperature and humidity set value-acquisition values, respectively constructing a plurality of data analysis channels, embedding the corresponding functional relations into the corresponding data analysis channels for channel processing mechanism configuration, respectively performing analysis conversion of data control amounts, for example, aiming at temperature and humidity set value-acquisition values, determining actual temperature and humidity values under temperature and humidity set value regulation based on channel analysis, and outputting the channels. And the data analysis channels are distributed in parallel, a rear full-connection layer is connected with the channel output end, and an optimal control sub-model is configured and connected with the full-connection layer in a rear mode to generate a data analysis optimal model which is a self-built auxiliary analysis tool for data conversion analysis.
Further, as shown in fig. 3, a plurality of data analysis channels are connected to construct a data analysis optimization model, and step S400 of the present application further includes:
step S410: based on the data analysis channels, a plurality of classifiers are obtained through training a data set, and a multi-layer sub-model is built respectively;
step S420: connecting the multi-layer sub-model by using a full connection layer, constructing an adaptability function based on all functional relations, and establishing an optimized control sub-model;
step S430: and integrating the multi-layer sub-model, the full-connection layer and the optimization control sub-model according to the data connection relation to obtain the data analysis optimization model.
Further, based on all the functional relationships, constructing the fitness function and establishing the optimization control sub-model, and the step S420 of the application further comprises:
step S421: based on all functional relations, constructing an adaptability function by taking energy consumption and parameter control precision as evaluation variables;
step S422: inputting the parameter control requirements into a weighting channel, and carrying out weight distribution on each control parameter by a weighting algorithm to obtain each parameter weight;
step S423: and adding the weight of each parameter into the fitness function, setting an optimization iteration rule based on the fitness function, and establishing the optimization control sub-model.
Specifically, training the plurality of data analysis channels, where the plurality of data analysis channels respectively correspond to the temperature-humidity, the temperature-clean room variable control requirement, the humidity-clean room variable control requirement and the temperature and humidity set value-acquisition value functional relationship, for example, using the multi-environment sample cluster as sample data, performing sample data attribution division based on the channel data types, determining multiple sets of training data, respectively performing neural network training based on the multiple sets of training data, and generating the multi-layer submodel, where each submodel is a multi-layer fully-connected neural network model. And connecting the output end of the multi-layer submodel with the input end of the full-connection layer, and integrating the data flow of the multi-layer submodel to the full-connection layer. And constructing the fitness function based on the function relation, and constructing the optimal control sub-model which is connected with the full-connection layer at the rear position and is used for analyzing the control parameters integrated with the full-connection layer to perform weighting optimization.
Specifically, based on all functional relationships, the energy consumption and the parameter control precision are taken as evaluation variables, the control parameters which are analyzed and output by the multi-layer submodel are taken as evaluation ranges, and the fitness function is determined, namely, the cooperative control energy efficiency of each control parameter, namely, the total energy consumption sum and the comprehensive control precision which represent the sum of the energy consumption, is calculated, so that the control effect is ensured, and the energy waste is avoided. Further, the parameter control requirements are input into a weighting channel to carry out weight configuration, specifically, based on a weighting algorithm, for example, based on control requirements, the control importance is used as a measurement standard, the weight calculation configuration of the control parameters is carried out, namely, the weights of the temperature and the humidity are higher, the control weights of the other control parameters are lower, the relative configuration is carried out according to the control importance, the sum of the distribution weights is 1, and the weight values of the parameters are obtained. And adding the weight of each parameter into the fitness function to ensure the calculation accuracy of the fitness function. Further setting an optimization iteration rule, for example, optimizing control parameters based on an invasive weed optimization algorithm, calculating the adaptability of the expansion control parameters to determine the expansion quantity of the control parameters at the later stage, setting the maximum iteration times, selecting the control parameter corresponding to the highest adaptability value from the obtained expansion control parameters as an optimal control parameter, taking the optimal control parameter as an optimization iteration rule, combining the adaptability function, and constructing the optimization control sub-model, wherein the optimization control sub-model is used for carrying out the iterative optimization of the control parameters.
Furthermore, the multi-layer sub-model is of the same level, the output end of the multi-layer sub-model is connected with the input end of the full-connection layer, the output end of the full-connection layer is connected with the input end of the optimizing control sub-model, the data analyzing optimizing model is generated, and the control optimizing is carried out based on the data analyzing optimizing model, so that the accuracy and objectivity of an analyzing result can be effectively ensured, and the analyzing and processing efficiency is ensured.
Step S500: acquiring the current clean room control requirement, and decomposing parameter control requirements according to the current clean room control requirement;
step S600: and inputting the parameter control requirement into the data analysis optimization model, performing control parameter optimization, obtaining a temperature and humidity control scheme, and sending the temperature and humidity control scheme to a controller for temperature and humidity control.
Specifically, the control requirement of the clean room is obtained, namely the current environment condition which the clean room needs to actually reach. And decomposing the current clean room control requirement, and determining the temperature, humidity and variable control referring to the corresponding specific effect as the parameter control requirement. And based on the parameter control requirement, combining the interaction and the control loss, and carrying out setting configuration analysis of control parameters.
Further, the parameter control requirements are input into the data analysis optimization model, control parameter analysis is performed according to a functional relation based on each layer of sub-model, integrated connection and iterative optimization are performed on analysis results, a temperature and humidity control optimal scheme is determined, the temperature and humidity control optimal scheme is a global optimal scheme, the global optimal scheme is used as the temperature and humidity control scheme to be executed, the temperature and humidity control scheme is sent to the controller, accurate temperature and humidity control is performed in a divided manner, and the control effect is guaranteed to the greatest extent.
Further, the parameter control requirement is input into the data analysis optimization model to perform control parameter optimization, and the step S600 of the present application further includes:
step S610: identifying the parameter control requirements according to data types, respectively inputting the parameter control requirements into corresponding data analysis channels, carrying out control requirement-control value relation analysis, and determining data control information;
step S620: the output results of all layers of submodels, including the corresponding relation of temperature data control information, humidity data control information and parameter control requirements, are subjected to data connection through the full connection layer;
step S630: and connecting the data to an optimization control sub-model, optimizing the parameter control requirements based on the corresponding relation of the temperature data control information, the humidity data control information and the parameter control requirements, and determining a temperature and humidity control optimal scheme to output.
Specifically, the parameter control requirements are input into the data analysis optimization model, the data type recognition, such as temperature control requirements, humidity control requirements and the like, the matching of analysis channels is performed, the data analysis channels are input into the corresponding data analysis channels, the sub-model corresponding to the result data analysis channels performs the relation analysis of control requirements-control values, and specific parameter control values are determined, wherein the specific parameter control values comprise the corresponding relation between the temperature data control information, the humidity data control information and the parameter control requirements, namely the control requirements and the corresponding control information, and are used as the data control information. And taking the data control information as an output result of each layer of sub-model, transferring the data control information to the fully-connected layer, carrying out integration regulation and interaction correlation of the output result of each sub-model, further inputting the corresponding relation between the temperature data control information, the humidity data control information and the parameter control requirement into the optimized control sub-model, carrying out optimizing iteration based on the fitness function and the optimized iteration rule, determining control information corresponding to the maximum fitness, and carrying out model output by taking the control information as the optimal temperature and humidity control scheme to determine a globally optimal control scheme, wherein the control execution effect of the maximized guaranteed control information accords with the control requirement.
Further, the temperature and humidity control scheme is controlled and divided,
further, the method for obtaining the temperature and humidity control scheme and sending the temperature and humidity control scheme to the controller for temperature and humidity control includes step S640, including:
step S641: controlling the temperature and humidity control scheme to obtain a branch control node;
step S642: determining the split control information of each controller based on the split control node matching a plurality of controllers;
step S643: based on the split-control information of each controller, a Markov chain evaluation model is constructed, and the control result of each split-control node is evaluated;
step S644: and tracing the split control information based on the evaluation information of the control result, and adjusting the split control information which does not meet the control result until the control result is met.
Specifically, the temperature and humidity control scheme is sent to the controller, and the temperature and humidity control scheme is divided. Specifically, the output of the controller is converted into a control interval, for example, -100% to 100%, the control interval is divided, for example, -100% to-30%, -30% -0, 0-30%, 30% -100%, and the specific interval can be adjusted in a self-defined manner to serve as the control information of the control of each controller. For temperature control and humidity control, the split control of hot water valve, cold water valve, etc. is performed. And constructing the Markov chain evaluation model based on the split control information, wherein specific link nodes are consistent with the number of the splits and are used for evaluating the control state of each split interval. And taking a temperature and humidity control standard corresponding to the section node as a reference, checking with the section control effect, determining a temperature and humidity difference value as evaluation information of a control result, wherein the temperature difference value is provided with a sign mark and is used for determining a difference value orientation. Judging the evaluation information of the control result, tracing the split degree control information if the control abnormality exists, determining the abnormal control parameter corresponding to the current control section, adjusting the split control information which does not meet the control result, effectively reducing the abnormal tracing analysis data quantity, improving the abnormal tracing efficiency until the corresponding control effect is met, and continuing the follow-up split control.
Because the control process has certain time ductility, the time delay is weakened by performing the path-dividing control, the control section is subdivided to perform gradual progressive control, the control precision can be further improved, and the control effect is synchronously analyzed so as to trace the abnormal control effect.
Example two
Based on the same inventive concept as the clean room temperature humidity control method in the previous embodiment, as shown in fig. 4, the present application provides a clean room temperature humidity control system comprising:
the sample set construction module 11 is used for collecting clean room temperature and humidity control sample data and constructing a temperature and humidity control sample set, wherein the temperature and humidity control sample set comprises a temperature and humidity set value, a temperature and humidity collection value and a clean room variable control requirement;
the functional relation fitting module 12 is configured to fit a functional relation between temperature and humidity, temperature and clean room variable control requirements, humidity and clean room variable control requirements, and temperature and humidity set values and acquisition values based on the temperature and humidity set values, the temperature and humidity acquisition values, and the clean room variable control requirements in the temperature and humidity control sample set;
the channel construction module 13 is used for constructing a plurality of corresponding data analysis channels based on all the functional relationships, and the data analysis channels are used for carrying out data control quantity analysis conversion based on the functional relationships;
the model construction module 14 is used for connecting a plurality of data analysis channels to construct a data analysis optimization model;
the control requirement decomposition module 15 is used for acquiring the current clean room control requirement and decomposing the parameter control requirement according to the current clean room control requirement;
and the optimization control module 16 is used for inputting the parameter control requirement into the data analysis optimization model, optimizing control parameters, obtaining a temperature and humidity control scheme, and sending the temperature and humidity control scheme to a controller for temperature and humidity control.
Further, the system further comprises:
the sample classification module is used for classifying the temperature and humidity control sample set based on preset environmental parameters to construct a multi-environment sample set;
the loss calculation fitting module is used for calculating the loss of the temperature and humidity set values and the temperature and humidity acquisition values of the multi-environment sample cluster respectively, determining the temperature loss and the humidity loss, and fitting the temperature and humidity loss relation based on the temperature loss and the humidity loss;
the coupling relation determining module is used for carrying out temperature and humidity coupling relation analysis according to the temperature and humidity set value and determining a temperature and humidity coupling relation;
the loss relation fitting module is used for carrying out adjustment trend relation analysis based on the temperature loss amount, the humidity loss amount and the temperature and humidity coupling relation and respectively fitting the humidity coupling loss relation and the temperature coupling loss relation;
the coefficient determining module is used for determining a relationship adjustment coefficient by utilizing the humidity coupling loss relationship and the temperature coupling loss relationship;
and the function relation acquisition module is used for obtaining a temperature-humidity function relation by fitting based on the relation adjustment coefficient and the temperature and humidity loss relation.
Further, the system further comprises:
the adjustment relation analysis module is used for respectively carrying out adjustment relation analysis on the temperature and humidity set values and the clean room variable control requirements on the multi-environment sample cluster and determining adjustment relation between each clean room variable and the temperature set value and adjustment relation between each clean room variable and the humidity set value;
and the adjustment relation fitting module is used for respectively fitting and obtaining a temperature-clean room variable control requirement function relation and a humidity-clean room variable control requirement function relation based on the adjustment relation between each clean room variable and the temperature set value and the adjustment relation between each clean room variable and the humidity set value.
Further, the system further comprises:
the multi-layer sub-model building module is used for obtaining a plurality of classifiers through training a data set based on the plurality of data analysis channels and respectively building a multi-layer sub-model;
the optimizing control sub-model building module is used for connecting the multi-layer sub-models by utilizing the full connection layer, building the fitness function based on all functional relations and building the optimizing control sub-model;
and the data analysis optimization model acquisition module is used for integrating the multi-layer sub-model, the full-connection layer and the optimization control sub-model according to the data connection relation to obtain the data analysis optimization model.
Further, the system further comprises:
the data control information determining module is used for identifying the parameter control requirements according to data types, respectively inputting the parameter control requirements into corresponding data analysis channels, carrying out control requirement-control value relation analysis, and determining data control information;
the data connection module is used for carrying out data connection on output results of all layers of sub-models, including corresponding relations of temperature data control information, humidity data control information and parameter control requirements, through the full connection layer;
and the optimal scheme determining module is used for connecting data to the optimal control sub-model, optimizing parameter control requirements based on the corresponding relation of the temperature data control information, the humidity data control information and the parameter control requirements, and determining the output of the optimal scheme of temperature and humidity control.
Further, the system further comprises:
the fitness function construction module is used for constructing a fitness function by taking energy consumption and parameter control precision as evaluation variables based on all functional relations;
the parameter weighting module is used for inputting the parameter control requirement into a weighting channel, and carrying out weight distribution on each control parameter through a weighting algorithm to obtain each parameter weight;
and the rule setting module is used for adding the weight of each parameter into the fitness function, setting an optimization iteration rule based on the fitness function and establishing the optimization control sub-model.
Further, the system further comprises:
the scheme control path dividing module is used for controlling the temperature and humidity control scheme to obtain a path dividing control node;
the system comprises a split control information determining module, a split control information processing module and a control information processing module, wherein the split control information determining module is used for determining split control information of each controller based on the matching of the split control nodes with a plurality of controllers;
the control result evaluation module is used for constructing a Markov chain evaluation model based on the split-control information of each controller and evaluating the control result of each split-control node;
and the information tracing and adjusting module is used for tracing the split control information based on the evaluation information of the control result and adjusting the split control information which does not meet the control result until the control result is met.
The foregoing detailed description of the method for controlling the humidity of the clean room temperature will be clear to those skilled in the art, and the method and the system for controlling the humidity of the clean room temperature in this embodiment are relatively simple for the device disclosed in the embodiments, and the relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The clean room temperature humidity control method is characterized by comprising the following steps:
collecting clean room temperature and humidity control sample data, and constructing a temperature and humidity control sample set, wherein the temperature and humidity control sample set comprises a temperature and humidity set value, a temperature and humidity acquisition value and a clean room variable control requirement;
fitting a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement and temperature and humidity set value-acquisition value function relation based on the temperature and humidity set value, temperature and humidity acquisition value and clean room variable control requirement in the temperature and humidity control sample set;
based on all the functional relationships, constructing a plurality of corresponding data analysis channels, wherein the data analysis channels are used for carrying out data control quantity analysis conversion based on the functional relationships;
connecting a plurality of data analysis channels to construct a data analysis optimization model;
acquiring the current clean room control requirement, and decomposing parameter control requirements according to the current clean room control requirement;
and inputting the parameter control requirement into the data analysis optimization model, performing control parameter optimization, obtaining a temperature and humidity control scheme, and sending the temperature and humidity control scheme to a controller for temperature and humidity control.
2. The method of claim 1, wherein fitting a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement functional relationship based on the temperature and humidity set point, temperature and humidity acquisition value, clean room variable control requirement in the temperature and humidity control sample set comprises:
classifying the temperature and humidity control sample set based on preset environmental parameters to construct a multi-environment sample set;
respectively carrying out temperature and humidity set value and loss amount calculation of a temperature and humidity acquisition value on the multi-environment sample cluster, determining temperature loss amount and humidity loss amount, and fitting a temperature and humidity loss relation based on the temperature loss amount and the humidity loss amount;
performing temperature and humidity coupling relation analysis according to the temperature and humidity set values, and determining a temperature and humidity coupling relation;
performing adjustment trend relation analysis based on the temperature loss amount, the humidity loss amount and the temperature and humidity coupling relation, and fitting the humidity coupling loss relation and the temperature coupling loss relation respectively;
determining a relationship adjustment coefficient by utilizing the humidity coupling loss relationship and the temperature coupling loss relationship;
and fitting to obtain a temperature-humidity function relation based on the relation adjustment coefficient and the temperature and humidity loss relation.
3. The method of claim 2, wherein fitting a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement functional relationship based on the temperature and humidity set point, temperature and humidity acquisition value, clean room variable control requirement in the temperature and humidity control sample set, further comprises:
respectively analyzing the adjustment relation between the temperature and humidity set values and the control requirement of the clean room variables to the multi-environment sample cluster, and determining the adjustment relation between the clean room variables and the temperature set values and the adjustment relation between the clean room variables and the humidity set values;
and respectively fitting to obtain a temperature-clean room variable control requirement function relation and a humidity-clean room variable control requirement function relation based on the adjustment relation between each clean room variable and the temperature set value and the adjustment relation between each clean room variable and the humidity set value.
4. The method of claim 1, wherein connecting the plurality of data analysis channels to construct the data analysis optimization model comprises:
based on the data analysis channels, a plurality of classifiers are obtained through training a data set, and a multi-layer sub-model is built respectively;
connecting the multi-layer sub-model by using a full connection layer, constructing an adaptability function based on all functional relations, and establishing an optimized control sub-model;
and integrating the multi-layer sub-model, the full-connection layer and the optimization control sub-model according to the data connection relation to obtain the data analysis optimization model.
5. The method of claim 4, wherein inputting the parameter control requirement into the data analysis optimization model for control parameter optimization comprises:
identifying the parameter control requirements according to data types, respectively inputting the parameter control requirements into corresponding data analysis channels, carrying out control requirement-control value relation analysis, and determining data control information;
the output results of all layers of submodels, including the corresponding relation of temperature data control information, humidity data control information and parameter control requirements, are subjected to data connection through the full connection layer;
and connecting the data to an optimization control sub-model, optimizing the parameter control requirements based on the corresponding relation of the temperature data control information, the humidity data control information and the parameter control requirements, and determining a temperature and humidity control optimal scheme to output.
6. The method of claim 4, wherein constructing an fitness function based on all functional relationships, creating an optimization control sub-model, further comprises:
based on all functional relations, constructing an adaptability function by taking energy consumption and parameter control precision as evaluation variables;
inputting the parameter control requirements into a weighting channel, and carrying out weight distribution on each control parameter by a weighting algorithm to obtain each parameter weight;
and adding the weight of each parameter into the fitness function, setting an optimization iteration rule based on the fitness function, and establishing the optimization control sub-model.
7. The method of claim 1, wherein the obtaining the temperature and humidity control scheme, and sending the temperature and humidity control scheme to a controller for temperature and humidity control, comprises:
controlling the temperature and humidity control scheme to obtain a branch control node;
determining the split control information of each controller based on the split control node matching a plurality of controllers;
based on the split-control information of each controller, a Markov chain evaluation model is constructed, and the control result of each split-control node is evaluated;
and tracing the split control information based on the evaluation information of the control result, and adjusting the split control information which does not meet the control result until the control result is met.
8. Clean room temperature humidity control system, characterized by comprising:
the sample set construction module is used for collecting clean room temperature and humidity control sample data and constructing a temperature and humidity control sample set, and the temperature and humidity control sample set comprises a temperature and humidity set value, a temperature and humidity acquisition value and a clean room variable control requirement;
the functional relation fitting module is used for fitting a temperature-humidity, temperature-clean room variable control requirement, humidity-clean room variable control requirement and temperature and humidity set value-acquisition value functional relation based on the temperature and humidity set value, the temperature and humidity acquisition value and the clean room variable control requirement in the temperature and humidity control sample set;
the channel construction module is used for constructing a plurality of corresponding data analysis channels based on all the functional relationships, and the data analysis channels are used for carrying out data control quantity analysis conversion based on the functional relationships;
the model construction module is used for connecting a plurality of data analysis channels to construct a data analysis optimization model;
the control requirement decomposition module is used for acquiring the current clean room control requirement and decomposing the parameter control requirement according to the current clean room control requirement;
and the optimization control module is used for inputting the parameter control requirements into the data analysis optimization model to control parameter optimization, obtaining a temperature and humidity control scheme and sending the temperature and humidity control scheme to a controller to perform temperature and humidity control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311041660.XA CN116755496B (en) | 2023-08-18 | 2023-08-18 | Clean room temperature humidity control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311041660.XA CN116755496B (en) | 2023-08-18 | 2023-08-18 | Clean room temperature humidity control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116755496A true CN116755496A (en) | 2023-09-15 |
| CN116755496B CN116755496B (en) | 2023-10-20 |
Family
ID=87953687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311041660.XA Active CN116755496B (en) | 2023-08-18 | 2023-08-18 | Clean room temperature humidity control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116755496B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309083A (en) * | 2020-03-11 | 2020-06-19 | 湖南省西瓜甜瓜研究所 | Seedbed greenhouse control method, seedbed greenhouse control system and storage medium |
| CN111856930A (en) * | 2020-06-16 | 2020-10-30 | 北京农业信息技术研究中心 | Cold chain environment and fruit temperature and humidity coupling sensing and controlling method and system |
| CN112577159A (en) * | 2020-12-10 | 2021-03-30 | 广东省科学院智能制造研究所 | Air conditioner energy-saving intelligent control method and device based on human body thermal comfort |
| CN114036813A (en) * | 2021-11-11 | 2022-02-11 | 华南农业大学 | Greenhouse temperature and humidity method controlled by particle swarm BP neural network PID |
| CN115840480A (en) * | 2021-11-18 | 2023-03-24 | 中国电子工程设计院有限公司 | Method, device and system for controlling environmental parameters of clean room |
-
2023
- 2023-08-18 CN CN202311041660.XA patent/CN116755496B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309083A (en) * | 2020-03-11 | 2020-06-19 | 湖南省西瓜甜瓜研究所 | Seedbed greenhouse control method, seedbed greenhouse control system and storage medium |
| CN111856930A (en) * | 2020-06-16 | 2020-10-30 | 北京农业信息技术研究中心 | Cold chain environment and fruit temperature and humidity coupling sensing and controlling method and system |
| CN112577159A (en) * | 2020-12-10 | 2021-03-30 | 广东省科学院智能制造研究所 | Air conditioner energy-saving intelligent control method and device based on human body thermal comfort |
| CN114036813A (en) * | 2021-11-11 | 2022-02-11 | 华南农业大学 | Greenhouse temperature and humidity method controlled by particle swarm BP neural network PID |
| CN115840480A (en) * | 2021-11-18 | 2023-03-24 | 中国电子工程设计院有限公司 | Method, device and system for controlling environmental parameters of clean room |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116755496B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Malthouse et al. | Nonlinear partial least squares | |
| Coakley et al. | A review of methods to match building energy simulation models to measured data | |
| CN101630376B (en) | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process | |
| KR102181966B1 (en) | Soft survey method and system for hydraulic cylinder comprehensive test station | |
| CN110442911B (en) | High-dimensional complex system uncertainty analysis method based on statistical machine learning | |
| CN115601000B (en) | BIM5D model engineering construction cost method and system under complex environment | |
| CN114578011A (en) | Water quality monitoring method based on multi-sensor multi-source data fusion | |
| CN101364277B (en) | Model building system based on T-S fuzzy model of interval type-2 fuzzy set | |
| Qaisar et al. | Energy baseline prediction for buildings: A review | |
| CN116975645A (en) | Industrial process soft measurement modeling method based on VAE-MRCNN | |
| CN101446828A (en) | Nonlinear process quality prediction method | |
| CN116755496B (en) | Clean room temperature humidity control method and system | |
| CN114583767A (en) | Data-driven wind power plant frequency modulation response characteristic modeling method and system | |
| CN110880044A (en) | Markov chain-based load prediction method | |
| CN116307405B (en) | Diode performance prediction method and system based on production data | |
| CN108563201B (en) | DMAIC-driven small-batch part machining process quality improvement method | |
| CN103279030A (en) | Bayesian framework-based dynamic soft measurement modeling method and device | |
| Ashar et al. | ARX model identification for the real-time temperature process with Matlab-arduino implementation | |
| CN110909492A (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
| Tümer et al. | Artificial neural network models for predicting the energy consumption of the process of crystallization syrup in Konya sugar factory | |
| CN115660468A (en) | Diversified product inspection and detection method and system | |
| CN115221796A (en) | Cloud manufacturing mode-oriented process flow simulation method and system | |
| CN115577856A (en) | Method and system for predicting construction cost and controlling balance of power transformation project | |
| Blasco et al. | Nonlinear parametric model identification with Genetic Algorithms. Application to a Thermal Process | |
| CN116823215B (en) | Intelligent operation and maintenance management and control method and system for power station |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Clean room temperature and humidity control method and system Granted publication date: 20231020 Pledgee: Bank of Nanjing Limited by Share Ltd. Suzhou branch Pledgor: Suzhou Jichang Automation Technology Development Co.,Ltd. Registration number: Y2024980003745 |