CN115375181A - Intelligent analysis method and system for laboratory environment quality - Google Patents

Intelligent analysis method and system for laboratory environment quality Download PDF

Info

Publication number
CN115375181A
CN115375181A CN202211128543.2A CN202211128543A CN115375181A CN 115375181 A CN115375181 A CN 115375181A CN 202211128543 A CN202211128543 A CN 202211128543A CN 115375181 A CN115375181 A CN 115375181A
Authority
CN
China
Prior art keywords
environment
laboratory
metering
layer
node
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
Application number
CN202211128543.2A
Other languages
Chinese (zh)
Inventor
钱斌
欧家祥
王吉
胡厚鹏
罗奕
肖艳红
林晓明
何沛林
周密
李鹏程
唐建林
李航峰
李富盛
陈泽瑞
张帆
邓钥丹
高正浩
吴欣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CSG Electric Power Research Institute
Guizhou Power Grid Co Ltd
Original Assignee
CSG Electric Power Research Institute
Guizhou Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by CSG Electric Power Research Institute, Guizhou Power Grid Co Ltd filed Critical CSG Electric Power Research Institute
Priority to CN202211128543.2A priority Critical patent/CN115375181A/en
Publication of CN115375181A publication Critical patent/CN115375181A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/02—Topology update or discovery
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Signal Processing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a laboratory environment quality intelligent analysis method and a system, which are used for acquiring a network address of each metering laboratory and a network address of an environment monitoring center, determining the maximum information transmission distance between the metering laboratory and the environment monitoring center, constructing a logic tree according to the node depth, performing routing planning on the transmission of data acquired by the metering laboratory, searching a proper next hop address, avoiding channel collision caused by the fact that a plurality of metering laboratories simultaneously send data to the metering laboratory, and ensuring the reliability of network transmission; the environmental parameter information and the meteorological parameter information are input into the pre-trained metering environment assessment neural network model to obtain the environmental quality grade of the metering laboratory, so that an intelligent regulation and control strategy can be formulated for the metering laboratory with unqualified environmental quality grade to adjust the environment of the metering laboratory, the environmental quality of the metering laboratory is in a qualified range, and the service life of an instrument is prevented from being influenced.

Description

Intelligent analysis method and system for laboratory environment quality
Technical Field
The invention relates to the technical field of laboratory environment quality monitoring, in particular to an intelligent analysis method and system for laboratory environment quality.
Background
The electric energy metering laboratory is used for measuring and recording generated energy, power supply quantity, station power consumption, line loss electric quantity and user power consumption. The refinement degree of the interior of a precision instrument in an electric energy metering laboratory is very high, for example, the temperature of an electric energy meter verification laboratory should be kept at (23 +/-2) ° C, and the relative humidity should be kept at (60 +/-15)%. Some metering equipment is easily influenced by environmental factors to cause abnormal experimental results, and the metering equipment can be damaged in serious cases. Therefore, technical means are needed to analyze and regulate the environmental quality of the electric energy metering laboratory so as to maintain the qualification of the environmental quality of the electric energy metering laboratory.
In patent application No. CN202210279308.9, the invention name is described as an environmental regulation and control method and system for a precision instrument laboratory, which is characterized in that environmental parameter information of the precision instrument laboratory is obtained; evaluating the current environmental condition in a precision instrument laboratory according to the environmental parameter information; acquiring meteorological parameter information, and determining weather characteristics according to the meteorological parameter information; if the current environmental condition is lower than a preset evaluation threshold value, generating an environmental regulation and control mode according to the current environmental condition and the weather characteristics; the environment of the precision laboratory is regulated and controlled through the environment regulation and control mode, and meanwhile, correction information is generated according to the regulated and controlled environment parameter information to correct the environment regulation and control mode, so that the condition that the laboratory is always in an environment suitable for storage of precision instruments by determining the environment regulation and control mode according to the environment change in the precision instrument laboratory is realized. However, the reliability of information transmission of multiple laboratories is not considered in the technical scheme, when the number of laboratories is too large and the transmitted data is too large, network congestion is easily caused, so that the future environmental conditions of the laboratories cannot be predicted, and an intelligent environment control strategy is lacked, so that instruments in the laboratories are operated in unqualified environments, and the service lives of the instruments are influenced.
Disclosure of Invention
The invention provides an intelligent analysis method and system for laboratory environment quality, which solve the technical problems that the reliability of information transmission of a plurality of laboratories is not considered in the existing laboratory environment regulation and control method, network congestion is easily caused when the number of the laboratories is too large and the transmitted data is too large, the future environment condition of the laboratories cannot be predicted, and the intelligent regulation and control strategy for the environment is lacked, so that instruments in the laboratories are operated in unqualified environments, and the service lives of the instruments are influenced.
In view of the above, the first aspect of the present invention provides a method for intelligently analyzing laboratory environmental quality, including:
acquiring a network address of an environment monitoring center and a network address of each metering laboratory;
calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center according to the network address of the environment monitoring center and the network address of each metering laboratory;
constructing a logic tree consisting of the environment monitoring center and all the metering laboratories by taking the environment monitoring center as a root node and taking the maximum information transmission distance between each metering laboratory and the environment monitoring center as a node depth;
for any metering laboratory, after acquiring environmental parameter information and meteorological parameter information, determining a next hop address according to the branch connection relation of a logic tree, and sending the environmental parameter information and the meteorological parameter information to an environment monitoring center, wherein if the metering laboratory and the environment monitoring center are in the relation of a root and a straight leaf node, the next hop address of the metering laboratory is the environment monitoring center, otherwise, the next hop address of the metering laboratory node is a current root node, and then the current root node searches the next hop address according to the branch connection relation of the logic tree until the next hop address of the metering laboratory is the environment monitoring center;
inputting the environmental parameter information and the meteorological parameter information into a pre-trained metering environment assessment neural network model to obtain a current environmental quality assessment grade output by the metering environment assessment neural network model;
and when the current environmental quality evaluation grade does not reach the qualified line, adjusting the environmental quality of the metering laboratory so that the environmental quality of the metering laboratory is in a qualified range.
Optionally, when the current environmental quality assessment level does not reach the qualified line, adjusting the environmental quality of the metering laboratory so that the environmental quality of the metering laboratory is within a qualified range, including:
judging whether the current environment quality evaluation grade output by the measuring environment evaluation neural network model reaches a qualified line, if not, predicting the future environment quality grade according to the current environment quality evaluation grade and calculating a real-time environment quality standard-reaching difference value;
calculating a future environmental quality adjustment parameter according to the meteorological parameter information, the future environmental quality grade and the real-time environmental quality standard-reaching difference;
and generating an environment intelligent regulation and control strategy corresponding to the future environment quality adjustment parameter according to the corresponding relation between the preset environment intelligent regulation and control strategy and the future environment quality adjustment parameter.
Optionally, the calculation formula for calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center is as follows:
Figure BDA0003849970690000031
wherein, MTD is a measurement laboratory node and an environmental monitoring center nodeMaximum transmission distance of points, d DA To measure the depth of a laboratory node, d LA Monitoring the depth of the central node for the environment, d F When the environment monitoring center node is not a leaf node of the metering laboratory node, the depth of a root node shared by the environment monitoring center node and the metering laboratory node is determined, and C is the number of address spaces capable of being allocated by the current metering laboratory node.
Optionally, the neural network model for evaluating a metering environment comprises an input layer, a fuzzy layer, a rule layer and an output layer;
the input layer inputs the neurons into the fuzzy layer, and the structure of the input layer is as follows:
Figure BDA0003849970690000032
wherein, I j Input to the jth neuron of the ambiguity layer, ω ij For the connection weight between the ith neuron of the input layer and the jth neuron of the fuzzy layer, θ j For bias of the blur layer, o i Is the ith neuron;
the calculation formula of the fuzzy layer is as follows:
Figure BDA0003849970690000033
wherein M is j Is the output of the jth neuron of the fuzzy layer, c is the center of the environment assessment neural network, and sigma is the width of the environment assessment neural network;
the formula for the fuzzy layer to send the calculation result to the rule layer is as follows:
Figure BDA0003849970690000034
wherein, A r Input to the r-th neuron of the rule layer, ω jr For the weight of the connection between the jth neuron of the fuzzy layer and the 'r' neuron of the regular layer, θ r A bias for a regular layer;
the calculation formula of the rule layer is as follows:
Figure BDA0003849970690000035
Figure BDA0003849970690000036
Figure BDA0003849970690000037
wherein, O r As a result of the nonlinear conversion, O r As a result of the non-linear transformation,F r the lower bound for the output of the nth neuron in the rule layer,
Figure BDA0003849970690000041
the upper limit of the output of the r-th neuron of the rule layer, f (-) is the activation function,Othe lower limit value in the nonlinear transformation results for all neurons in the rule layer,
Figure BDA0003849970690000042
the upper limit value in the nonlinear conversion result of all the neurons in the rule layer is obtained;
the calculation formula of the output layer is as follows:
Figure BDA0003849970690000043
where y is the output of the output layer.
Optionally, the calculation formula for predicting the future environmental quality grade according to the current environmental quality evaluation grade is as follows:
Figure BDA0003849970690000044
wherein, X Δt For future environmental quality classes, X t Evaluating the grade for the current environment quality, and t is whenTime of day, μ is a constant, Δ t is the time period length, γ t Is the autocorrelation coefficient, epsilon t To calculate the error.
Optionally, the formula for calculating the future environmental quality adjustment parameter is:
Figure BDA0003849970690000045
wherein e is 2 Adjusting parameters for future environmental quality, w t Is the influence weight, [ -k, k ] of the meteorological parameter information]To the meteorological variation range, WH t For predictive estimation of future meteorological parameter information, WH 0 For historical meteorological parameter information, σ WH Is the standard deviation of the weather parameter information,
Figure BDA0003849970690000046
is the variance of the meteorological parameter information, e 1 The difference value of the real-time environment quality reaching the standard is obtained.
The invention provides a laboratory environment quality intelligent analysis system in a second aspect, which comprises:
the system comprises an address acquisition module, a network address acquisition module and a network address acquisition module, wherein the address acquisition module is used for acquiring a network address of an environment monitoring center and a network address of each metering laboratory;
the distance calculation module is used for calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center according to the network address of the environment monitoring center and the network address of each metering laboratory;
the logic tree construction module is used for constructing a logic tree consisting of the environment monitoring center and all the metering laboratories by taking the environment monitoring center as a root node and taking the maximum information transmission distance between each metering laboratory and the environment monitoring center as a node depth;
the routing planning module is used for determining a next hop address according to the branch connection relation of the logic tree after acquiring environmental parameter information and meteorological parameter information for any metering laboratory, and sending the environmental parameter information and the meteorological parameter information to the environment monitoring center, wherein if the metering laboratory and the environment monitoring center are in the relation of a root and a straight leaf node, the next hop address of the metering laboratory is the environment monitoring center, otherwise, the next hop address of the metering laboratory node is a current root node, and then the current root node searches the next hop address according to the branch connection relation of the logic tree until the next hop address of the metering laboratory is the environment monitoring center;
the environment quality evaluation module is used for inputting the environment parameter information and the meteorological parameter information into a pre-trained metering environment evaluation neural network model to obtain the current environment quality evaluation grade output by the metering environment evaluation neural network model;
and the environment regulation and control module is used for regulating the environment quality of the metering laboratory when the current environment quality evaluation grade does not reach the qualified line, so that the environment quality of the metering laboratory is in a qualified range.
Optionally, the system further comprises an environment regulation module, specifically configured to:
judging whether the current environment quality evaluation grade output by the measuring environment evaluation neural network model reaches a qualified line, if not, predicting the future environment quality grade according to the current environment quality evaluation grade and calculating a real-time environment quality standard-reaching difference value;
calculating a future environmental quality adjustment parameter according to the meteorological parameter information, the future environmental quality grade and the real-time environmental quality standard-reaching difference;
and generating an environment intelligent regulation and control strategy corresponding to the future environment quality adjustment parameter according to the corresponding relation between the preset environment intelligent regulation and control strategy and the future environment quality adjustment parameter.
Optionally, the calculation formula for calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center is as follows:
Figure BDA0003849970690000051
wherein, MTD is the maximum transmission distance between a measurement laboratory node and an environment monitoring center node, d DA To measure the depth of a laboratory node, d LA Depth of central node for environmental monitoringDegree d of F When the environmental monitoring center node is not the leaf node of the metering laboratory node, the depth of the root node shared by the environmental monitoring center node and the metering laboratory node is calculated, and C is the number of address spaces which can be allocated by the current metering laboratory node.
Optionally, the neural network model for evaluating a metering environment comprises an input layer, a fuzzy layer, a rule layer and an output layer;
the input layer inputs the neurons into the fuzzy layer, and the structure of the input layer is as follows:
Figure BDA0003849970690000061
wherein, I j Input to the jth neuron of the ambiguity layer, ω ij For the connection weight between the ith neuron of the input layer and the jth neuron of the fuzzy layer, θ j For bias of the blur layer, o i Is the ith neuron;
the formula for calculating the blur layer is:
Figure BDA0003849970690000062
wherein, M j Is the output of the jth neuron of the fuzzy layer, c is the center of the environment assessment neural network, and sigma is the width of the environment assessment neural network;
the formula for the fuzzy layer to send the calculation result to the rule layer is as follows:
Figure BDA0003849970690000063
wherein A is r Input to the r-th neuron of the regular layer, ω jr For the weight of the connection between the jth neuron of the fuzzy layer and the 'r' neuron of the regular layer, θ r A bias for a regular layer;
the calculation formula of the rule layer is as follows:
Figure BDA0003849970690000064
Figure BDA0003849970690000065
Figure BDA0003849970690000066
wherein, O r As a result of the non-linear transformation,F r the lower bound for the output of the nth neuron of the rule layer,
Figure BDA0003849970690000067
the upper limit of the output of the r-th neuron of the rule layer, f (-) is the activation function,Othe lower limit value in the nonlinear transformation results for all neurons in the rule layer,
Figure BDA0003849970690000068
the upper limit value in the nonlinear transformation result of all neurons in the rule layer is set;
the calculation formula of the output layer is as follows:
Figure BDA0003849970690000069
where y is the output of the output layer.
According to the technical scheme, the intelligent analysis method and the intelligent analysis system for the laboratory environment quality have the following advantages:
the intelligent analysis method for the environmental quality of the laboratory, provided by the invention, comprises the steps of obtaining the network address of each metering laboratory and the network address of an environmental monitoring center, determining the maximum information transmission distance between the metering laboratory and the environmental monitoring center, constructing a logic tree according to the node depth, carrying out route planning on the transmission of data collected by the metering laboratory, searching a proper next hop address, avoiding channel collision caused by the fact that a plurality of metering laboratories simultaneously send data to the metering laboratory, and ensuring the reliability of network transmission; the method comprises the steps of inputting environmental parameter information and meteorological parameter information into a pre-trained metering environment assessment neural network model to obtain an environmental quality grade of a metering laboratory, so that an intelligent regulation and control strategy can be formulated for the metering laboratory with unqualified environmental quality grade to adjust the environment of the metering laboratory, and the environmental quality of the metering laboratory is in a qualified range.
Meanwhile, after the current environment quality evaluation grade output by the metering environment evaluation neural network model is obtained, for the condition that the current environment quality evaluation grade does not reach a qualified line, the laboratory environment quality intelligent analysis method calculates future environment quality adjustment parameters and generates a corresponding environment intelligent regulation strategy, so that the metering laboratory environment can be adjusted according to the environment intelligent regulation strategy, the metering laboratory environment quality is in a qualified range, the service life of a precision instrument in the metering laboratory is prolonged, and the abnormal experimental result caused by environmental factors is avoided.
The principle and achieved technical effect of the laboratory environment quality intelligent analysis system provided by the invention are the same as those of the laboratory environment quality intelligent analysis method provided by the invention, and the description is omitted here.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other related drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a laboratory environmental quality intelligent analysis method provided in the present invention;
FIG. 2 is a schematic diagram of a logical tree structure provided in the present invention;
fig. 3 is a schematic structural diagram of an intelligent laboratory environmental quality analysis system provided in the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For easy understanding, referring to fig. 1 and fig. 2, the present invention provides an embodiment of a laboratory environment quality intelligent analysis method, including:
step 101, acquiring a network address of an environment monitoring center and a network address of each metering laboratory.
It should be noted that a Network address (Network address) is a logical address that a node on the internet has in a Network, and the node can be addressed. The network address is dynamically allocated by a parent node when the node joins the network, is only used for a routing mechanism and data transmission, and is a unique identifier of each node. In the embodiment of the invention, the network address of the environment monitoring center needs to be acquired and is recorded as DA, and the network address of each metering laboratory is recorded as DA.
102, calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center according to the network address of the environment monitoring center and the network address of each metering laboratory.
It should be noted that, according to the network address of the environment monitoring center and the network address of each metering laboratory, the maximum information transmission distance between each metering laboratory and the environment monitoring center may be calculated. Specifically, the calculation formula for calculating the maximum information transmission distance between each measurement laboratory and the environment monitoring center is as follows:
Figure BDA0003849970690000081
wherein, MTD is the maximum transmission distance between the measurement laboratory node and the environment monitoring center node, C is the number of address spaces which can be allocated by the current measurement laboratory node, d DA To measure the depth of a laboratory node, d LA Monitoring the depth of the central node for the environment, d F The depth of a root node shared by the environment monitoring center node and the metering laboratory node is the depth of the root node shared by the environment monitoring center node and the metering laboratory node when the environment monitoring center node is not the leaf node of the metering laboratory node. The depth refers to the number of ancestors of a node, and does not include the node itself, i.e., how many edges are from the current node to the root node.
And 103, constructing a logic tree consisting of the environment monitoring center and all the metering laboratories by taking the environment monitoring center as a root node and taking the maximum information transmission distance between each metering laboratory and the environment monitoring center as a node depth.
It should be noted that, taking the environment monitoring center as a root node, if the network address of the current metering laboratory and the network address of the environment monitoring center satisfy: and if DA is more than LA and less than DA + C, the current metering laboratory node is a leaf node of the environment monitoring center node. And traversing the connection relations among all the nodes of the metering laboratory and the connection relations among the nodes of the metering laboratory and the nodes of the environment monitoring center in sequence to form a logic tree, as shown in fig. 2.
And 104, for any metering laboratory, after acquiring the environmental parameter information and the meteorological parameter information, determining a next hop address according to the branch connection relation of the logic tree, and sending the environmental parameter information and the meteorological parameter information to an environment monitoring center, wherein if the metering laboratory and the environment monitoring center are in the relation of a root and a straight leaf node, the next hop address of the metering laboratory is the environment monitoring center, otherwise, the next hop address of the metering laboratory node is a current root node, and then the current root node searches the next hop address according to the branch connection relation of the logic tree until the next hop address of the metering laboratory is the environment monitoring center.
It should be noted that, because the precision instruments in the measurement laboratories are very easily affected by environmental factors, the experimental results are abnormal, and the precision instruments themselves are damaged in severe cases, the environmental data of the measurement laboratories need to be automatically sensed, intelligently evaluated and regulated, so as to ensure that the test environments of the measurement laboratories are in a qualified state. The acquired environmental parameter information comprises temperature, humidity, air particulate matter concentration, gas concentration and the like. In order to ensure the reliability of network transmission and avoid channel collision caused by the fact that a plurality of metering laboratories simultaneously send data to an environment monitoring center, a transmission route needs to be planned. Specifically, a next hop address is determined according to the branch connection relation of the logic tree, if the metering laboratory and the environment monitoring center are in the relation of a root and a direct leaf node, the next hop address of the metering laboratory is the environment monitoring center, otherwise, the next hop address of the metering laboratory node is the current root node, the current root node searches for the next hop address according to the branch connection relation of the logic tree until the next hop address of the metering laboratory is the environment monitoring center, and then the environment parameter information and the meteorological parameter information are sent to the environment monitoring center according to a planned route.
And 105, inputting the environmental parameter information and the meteorological parameter information into a pre-trained metering environment assessment neural network model to obtain a current environmental quality assessment grade output by the metering environment assessment neural network model.
The method includes the steps of constructing a metering environment assessment neural network model, selecting data of a preset number in experimental environment standards and historical environment parameter information as training samples, using environment quality levels corresponding to the experimental environment standards and the historical environment parameter information as expected output of the metering environment assessment neural network model, correcting parameters in the metering environment assessment neural network model according to the expected output, conducting deep learning, and finally obtaining the metering environment assessment neural network model meeting preset success rate.
In one embodiment, a metered environment assessment neural network model includes an input layer, a fuzzy layer, a rules layer, and an output layer;
the input layer inputs the neurons into the fuzzy layer, and the structure of the input layer is as follows:
Figure BDA0003849970690000101
wherein, I j Input to the jth neuron of the ambiguity layer, ω ij Is the connection weight between the ith neuron of the input layer and the jth neuron of the fuzzy layer j For bias of the blur layer, o i Is the ith neuron;
the fuzzy layer selects a Gaussian function as a membership function to perform fuzzy processing on the input variable, and the calculation formula of the fuzzy layer is as follows:
Figure BDA0003849970690000102
wherein M is j The output of the jth neuron of the fuzzy layer, c is the center of the environment evaluation neural network, and sigma is the width of the environment evaluation neural network;
the formula for the fuzzy layer to send the calculation result to the rule layer is as follows:
Figure BDA0003849970690000103
wherein A is r Input to the r-th neuron of the regular layer, ω jr For the weight of the connection between the jth neuron of the fuzzy layer and the 'r' neuron of the regular layer, θ r A bias for a regular layer;
the calculation process of the rule layer is as follows:
firstly to A r Carrying out nonlinear conversion, wherein the conversion formula is as follows:
Figure BDA0003849970690000104
wherein, O r Is the result of nonlinear transformation.
And then performing activation calculation according to an output threshold value from the fuzzy layer to the rule layer, wherein the formula is as follows:
Figure BDA0003849970690000105
Figure BDA0003849970690000106
wherein the content of the first and second substances,F r the lower bound for the output of the nth neuron in the rule layer,
Figure BDA0003849970690000111
the upper limit of the output of the r-th neuron of the rule layer, f (-) is the activation function,Othe lower limit value in the nonlinear transformation results for all neurons in the rule layer,
Figure BDA0003849970690000112
the upper limit value in the nonlinear transformation result of all neurons in the rule layer. And the rule layer activates the data and transmits the data to the output layer.
The output layer calculates the environment quality grade quantification, and the calculation formula is as follows:
Figure BDA0003849970690000113
where y is the output of the output layer. And the output layer matches the calculation result with the environmental quality grade to obtain the model output corresponding to the current input sample. And performing error calculation on the calculation result according to the expected output and the model output, and reversely transmitting according to the error, so as to update parameters in the metering environment evaluation neural network model and obtain the metering environment evaluation neural network model which accords with the preset success rate.
And 106, when the current environmental quality evaluation grade does not reach the qualified line, adjusting the environmental quality of the metering laboratory so that the environmental quality of the metering laboratory is in a qualified range.
It should be noted that, if the environmental quality assessment level of the current metering laboratory does not conform to the preset level passing line, the environmental monitoring center needs to make an intelligent regulation and control strategy for the current metering laboratory by combining with the meteorological parameter information of the current metering laboratory, so as to adjust the environmental quality of the metering laboratory, and make the environmental quality of the metering laboratory within the qualified range.
The intelligent analysis method for the environmental quality of the laboratory, provided by the embodiment of the invention, comprises the steps of obtaining the network address of each metering laboratory and the network address of an environmental monitoring center, determining the maximum information transmission distance between the metering laboratory and the environmental monitoring center, constructing a logic tree according to the node depth, carrying out route planning on the transmission of data collected by the metering laboratory, searching a proper next hop address, avoiding channel collision caused by the fact that a plurality of metering laboratories simultaneously send data to the metering laboratory, and ensuring the reliability of network transmission; the method comprises the steps of inputting environmental parameter information and meteorological parameter information into a pre-trained metering environment assessment neural network model to obtain the environmental quality grade of a metering laboratory, and therefore an intelligent regulation and control strategy can be formulated for the metering laboratory with unqualified environmental quality grade to adjust the environment of the metering laboratory, so that the environmental quality of the metering laboratory is in a qualified range, and the technical problems that the reliability of information transmission of a plurality of laboratories is not considered in the existing laboratory environment regulation and control method, when the number of laboratories is too large and the transmitted data is too large, network congestion is easily caused, the future environmental conditions of the laboratory cannot be predicted, the intelligent regulation and control strategy for the environment is lacked, instruments in the laboratory are enabled to run in an unqualified environment, and the service life of the instruments is affected are solved.
In one embodiment, an analytical feature vector can be constructed that measures the quality of a laboratory environment: CVE = [ X = t ,X Δt ]Wherein X is Δt For future environmental quality classes, X t For the current environmentThe quality evaluation grade is X which is the result output by the neural network model of the measurement environment evaluation t . Evaluating grade X according to current environment quality t Calculating a future environmental quality grade:
Figure BDA0003849970690000121
where t is the current time, μ is a constant, Δ t is the time period length, γ t Is the autocorrelation coefficient, ε t To calculate the error.
X 'represents a numerical value corresponding to the lowest pass rating of the measurement laboratory' t If the real-time environmental quality meets the standard, the difference e 1 Comprises the following steps:
e 1 ＝|X t -X' t |。
combining meteorological parameter information of a metering laboratory, obtaining a future environmental quality adjustment parameter according to a future environmental quality grade predicted value and a real-time environmental quality standard-reaching difference value, wherein the calculation formula is as follows:
Figure BDA0003849970690000122
wherein e is 2 Adjusting parameters for future environmental quality, w t Is the influence weight, [ -k, k ] of the meteorological parameter information]To the meteorological variation range, WH t For predictive estimation of future meteorological parameter information, WH 0 For historical meteorological parameter information, σ WH Is the standard deviation of the weather parameter information,
Figure BDA0003849970690000123
is the variance of the meteorological parameter information, e 1 The difference value of the real-time environment quality reaching the standard is obtained.
The corresponding relation between the environment intelligent regulation strategy and the future environment quality regulation parameter can be preset. Thus, the future environmental quality adjustment parameter e is obtained 2 Then, the environment monitoring center can generate an environment intelligent regulation and control strategy of the metering laboratory according to the future environment quality regulation parameters, and the metering laboratory is surroundedAnd adjusting the environment so as to ensure that the environment quality of the metering laboratory is within a qualified range.
According to the laboratory environment quality intelligent analysis method provided by the embodiment of the invention, after the current environment quality evaluation grade output by the metering environment evaluation neural network model is obtained, for the condition that the current environment quality evaluation grade does not reach a qualified line, a future environment quality adjustment parameter is calculated, and a corresponding environment intelligent regulation and control strategy is generated, so that the metering laboratory environment can be adjusted conveniently according to the environment intelligent regulation and control strategy, the environmental quality of the metering laboratory is in a qualified range, the service life of a precision instrument in the metering laboratory is prolonged, and the abnormal experimental result caused by environmental factors is avoided.
For easy understanding, referring to fig. 3, an embodiment of an intelligent analysis system for laboratory environmental quality is provided in the present invention, including:
the system comprises an address acquisition module, a network address acquisition module and a network address acquisition module, wherein the address acquisition module is used for acquiring a network address of an environment monitoring center and a network address of each metering laboratory;
the distance calculation module is used for calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center according to the network address of the environment monitoring center and the network address of each metering laboratory;
the logic tree construction module is used for constructing a logic tree consisting of the environment monitoring center and all the metering laboratories by taking the environment monitoring center as a root node and taking the maximum information transmission distance between each metering laboratory and the environment monitoring center as a node depth;
the routing planning module is used for determining a next hop address according to the branch connection relation of the logic tree after acquiring environmental parameter information and meteorological parameter information for any metering laboratory, and sending the environmental parameter information and the meteorological parameter information to an environment monitoring center, wherein if the metering laboratory and the environment monitoring center are in the relation of a root and a straight leaf node, the next hop address of the metering laboratory is the environment monitoring center, otherwise, the next hop address of the metering laboratory node is a current root node, and then the current root node searches the next hop address according to the branch connection relation of the logic tree until the next hop address of the metering laboratory is the environment monitoring center;
the environment quality evaluation module is used for inputting the environment parameter information and the meteorological parameter information into a pre-trained metering environment evaluation neural network model to obtain the current environment quality evaluation grade output by the metering environment evaluation neural network model;
and the environment regulation and control module is used for regulating the environment quality of the metering laboratory when the current environment quality evaluation grade does not reach the qualified line, so that the environment quality of the metering laboratory is in a qualified range.
The environment regulation and control module is specifically used for:
judging whether the current environment quality evaluation grade output by the measuring environment evaluation neural network model reaches a qualified line, if not, predicting the future environment quality grade according to the current environment quality evaluation grade and calculating a real-time environment quality standard-reaching difference value;
calculating a future environmental quality adjustment parameter according to the meteorological parameter information, the future environmental quality grade and the real-time environmental quality standard-reaching difference;
and generating an environment intelligent regulation and control strategy corresponding to the future environment quality adjustment parameter according to the corresponding relation between the preset environment intelligent regulation and control strategy and the future environment quality adjustment parameter.
The calculation formula for calculating the maximum information transmission distance between each measurement laboratory and the environment monitoring center is as follows:
Figure BDA0003849970690000141
wherein, MTD is the maximum transmission distance between a measurement laboratory node and an environment monitoring center node, d DA To measure the depth of a laboratory node, d LA Monitoring the depth of the central node for the environment, d F When the environment monitoring center node is not a leaf node of the metering laboratory node, the depth of a root node shared by the environment monitoring center node and the metering laboratory node is determined, and C is the number of address spaces capable of being allocated by the current metering laboratory node.
The measuring environment evaluation neural network model comprises an input layer, a fuzzy layer, a rule layer and an output layer;
the input layer inputs the neurons into the fuzzy layer, and the structure of the input layer is as follows:
Figure BDA0003849970690000142
wherein, I j Input to the jth neuron of the fuzzy layer, ω ij Is the connection weight between the ith neuron of the input layer and the jth neuron of the fuzzy layer j For bias of the blur layer, o i Is the ith neuron;
the formula for calculating the blur layer is:
Figure BDA0003849970690000143
wherein M is j Is the output of the jth neuron of the fuzzy layer, c is the center of the environment assessment neural network, and sigma is the width of the environment assessment neural network;
the formula for the fuzzy layer to send the calculation result to the rule layer is as follows:
Figure BDA0003849970690000144
wherein A is r Input to the r-th neuron of the rule layer, ω jr For the weight of the connection between the jth neuron of the fuzzy layer and the 'r' neuron of the regular layer, θ r A bias for a regular layer;
the calculation formula of the rule layer is as follows:
Figure BDA0003849970690000145
Figure BDA0003849970690000146
Figure BDA0003849970690000147
wherein, O r As a result of the non-linear transformation,F r the lower bound for the output of the nth neuron of the rule layer,
Figure BDA0003849970690000148
the upper limit of the output of the r-th neuron of the rule layer, f (-) is the activation function,Othe lower limit value in the nonlinear transformation results for all neurons in the rule layer,
Figure BDA0003849970690000151
the upper limit value in the nonlinear transformation result of all neurons in the rule layer is set;
the calculation formula of the output layer is as follows:
Figure BDA0003849970690000152
where y is the output of the output layer.
The calculation formula for predicting the future environmental quality grade according to the current environmental quality evaluation grade is as follows:
Figure BDA0003849970690000153
wherein, X Δt For future environmental quality classes, X t For the current environment quality evaluation grade, t is the current moment, mu is a constant, delta t is the time interval length, gamma t Is the autocorrelation coefficient, epsilon t To calculate the error.
The formula for calculating the future environmental quality adjustment parameter is as follows:
Figure BDA0003849970690000154
wherein e is 2 For the future ringEnvironmental quality adjustment parameter, w t Is the influence weight, [ -k, k ] of the meteorological parameter information]To the meteorological variation range, WH t For predictive estimation of future meteorological parameter information, WH 0 For historical meteorological parameter information, σ WH Is the standard deviation of the weather parameter information,
Figure BDA0003849970690000155
is the variance of the meteorological parameter information, e 1 The difference value of the real-time environmental quality reaching the standard is obtained.
The principle and achieved technical effect of the laboratory environment quality intelligent analysis system provided by the invention are the same as those of the laboratory environment quality intelligent analysis method provided by the invention, and the description is omitted here.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. An intelligent analysis method for laboratory environment quality is characterized by comprising the following steps:
acquiring a network address of an environment monitoring center and a network address of each metering laboratory;
calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center according to the network address of the environment monitoring center and the network address of each metering laboratory;
taking an environment monitoring center as a root node, taking the maximum information transmission distance between each metering laboratory and the environment monitoring center as a node depth, and constructing a logic tree consisting of the environment monitoring center and all the metering laboratories;
for any metering laboratory, after acquiring environmental parameter information and meteorological parameter information, determining a next hop address according to the branch connection relation of a logic tree, and sending the environmental parameter information and the meteorological parameter information to an environment monitoring center, wherein if the metering laboratory and the environment monitoring center are in the relation of a root and a straight leaf node, the next hop address of the metering laboratory is the environment monitoring center, otherwise, the next hop address of the metering laboratory node is a current root node, and then the current root node searches the next hop address according to the branch connection relation of the logic tree until the next hop address of the metering laboratory is the environment monitoring center;
inputting the environmental parameter information and the meteorological parameter information into a pre-trained metering environment assessment neural network model to obtain a current environmental quality assessment grade output by the metering environment assessment neural network model;
and when the current environmental quality evaluation grade does not reach the qualified line, adjusting the environmental quality of the metering laboratory, so that the environmental quality of the metering laboratory is in a qualified range.
2. The intelligent analysis method for the environmental quality of the laboratory according to claim 1, wherein when the current environmental quality assessment level does not reach the qualified line, the environmental quality of the metering laboratory is adjusted so that the environmental quality of the metering laboratory is within the qualified range, and the method comprises the following steps:
judging whether the current environment quality evaluation grade output by the measuring environment evaluation neural network model reaches a qualified line, if not, predicting a future environment quality grade according to the current environment quality evaluation grade and calculating a real-time environment quality standard difference value;
calculating a future environmental quality adjustment parameter according to the meteorological parameter information, the future environmental quality grade and the real-time environmental quality standard-reaching difference;
and generating an environment intelligent regulation and control strategy corresponding to the future environment quality adjustment parameter according to the corresponding relation between the preset environment intelligent regulation and control strategy and the future environment quality adjustment parameter.
3. The intelligent analysis method for the environmental quality of the laboratory according to claim 1, wherein the calculation formula for calculating the maximum information transmission distance between each measurement laboratory and the environmental monitoring center is as follows:
Figure FDA0003849970680000021
wherein, MTD is the maximum transmission distance between a measurement laboratory node and an environment monitoring center node, d DA To measure the depth of a laboratory node, d LA Monitoring the depth of the central node for the environment, d F When the environmental monitoring center node is not the leaf node of the metering laboratory node, the depth of the root node shared by the environmental monitoring center node and the metering laboratory node is calculated, and C is the number of address spaces which can be allocated by the current metering laboratory node.
4. The intelligent analysis method for laboratory environment quality according to claim 1, characterized in that the neural network model for measuring environment assessment comprises an input layer, a fuzzy layer, a rule layer and an output layer;
the input layer inputs the neurons into the fuzzy layer, and the structure of the input layer is as follows:
Figure FDA0003849970680000022
wherein, I j Input to the jth neuron of the fuzzy layer, ω ij Is the connection weight between the ith neuron of the input layer and the jth neuron of the fuzzy layer j For bias of the blur layer, o i Is the ith neuron;
the formula for calculating the blur layer is:
Figure FDA0003849970680000023
wherein M is j Is the output of the jth neuron of the fuzzy layer, c is the center of the environment assessment neural network, and σ isWidth of the environment assessment neural network;
the formula for the fuzzy layer to send the calculation result to the rule layer is as follows:
Figure FDA0003849970680000024
wherein, A r Input to the r-th neuron of the rule layer, ω jr For the weight of the connection between the jth neuron of the fuzzy layer and the 'r' neuron of the regular layer, θ r A bias for a regular layer;
the formula for the rule layer is:
Figure FDA0003849970680000025
Figure FDA0003849970680000026
Figure FDA0003849970680000027
wherein, O r As a result of the non-linear transformation,F r the lower bound for the output of the nth neuron in the rule layer,
Figure FDA0003849970680000028
the upper bound of the output of the mth neuron in the rule layer, f (-) is the activation function,Othe lower limit value in the nonlinear transformation results for all neurons in the rule layer,
Figure FDA0003849970680000031
the upper limit value in the nonlinear transformation result of all neurons in the rule layer is set;
the calculation formula of the output layer is as follows:
Figure FDA0003849970680000032
where y is the output of the output layer.
5. The intelligent analysis method for laboratory environmental quality according to claim 2, wherein the calculation formula for predicting the future environmental quality grade according to the current environmental quality evaluation grade is as follows:
Figure FDA0003849970680000033
wherein, X Δt For future environmental quality classes, X t For the current environment quality evaluation grade, t is the current moment, mu is a constant, delta t is the time interval length, gamma t Is the autocorrelation coefficient, epsilon t To calculate the error.
6. The intelligent laboratory environmental quality analysis method of claim 5, wherein the formula for calculating the future environmental quality adjustment parameter is:
Figure FDA0003849970680000034
wherein e is 2 Adjusting parameters for future environmental quality, w t Is the influence weight, [ -k, k ] of the meteorological parameter information]To the meteorological variation range, WH t For predictive estimation of future meteorological parameter information, WH 0 For historical meteorological parameter information, σ WH Is the standard deviation of the weather parameter information,
Figure FDA0003849970680000035
is the variance of the meteorological parameter information, e 1 The difference value of the real-time environment quality reaching the standard is obtained.
7. An intelligent laboratory environment quality analysis system, comprising:
the system comprises an address acquisition module, a network address acquisition module and a network address acquisition module, wherein the address acquisition module is used for acquiring a network address of an environment monitoring center and a network address of each metering laboratory;
the distance calculation module is used for calculating the maximum information transmission distance between each metering laboratory and the environment monitoring center according to the network address of the environment monitoring center and the network address of each metering laboratory;
the logic tree construction module is used for constructing a logic tree consisting of the environment monitoring center and all the metering laboratories by taking the environment monitoring center as a root node and taking the maximum information transmission distance between each metering laboratory and the environment monitoring center as a node depth;
the routing planning module is used for determining a next hop address according to the branch connection relation of the logic tree after acquiring environmental parameter information and meteorological parameter information for any metering laboratory, and sending the environmental parameter information and the meteorological parameter information to an environment monitoring center, wherein if the metering laboratory and the environment monitoring center are in the relation of a root and a straight leaf node, the next hop address of the metering laboratory is the environment monitoring center, otherwise, the next hop address of the metering laboratory node is a current root node, and then the current root node searches the next hop address according to the branch connection relation of the logic tree until the next hop address of the metering laboratory is the environment monitoring center;
the environment quality evaluation module is used for inputting the environment parameter information and the meteorological parameter information into a pre-trained metering environment evaluation neural network model to obtain the current environment quality evaluation grade output by the metering environment evaluation neural network model;
and the environment regulation and control module is used for regulating the environment quality of the metering laboratory when the current environment quality evaluation grade does not reach the qualified line, so that the environment quality of the metering laboratory is in a qualified range.
8. The intelligent laboratory environmental quality analysis system of claim 7, wherein the environmental conditioning module is specifically configured to:
judging whether the current environment quality evaluation grade output by the measuring environment evaluation neural network model reaches a qualified line, if not, predicting a future environment quality grade according to the current environment quality evaluation grade and calculating a real-time environment quality standard difference value;
calculating a future environmental quality adjustment parameter according to the meteorological parameter information, the future environmental quality grade and the real-time environmental quality standard-reaching difference;
and generating an environment intelligent regulation strategy corresponding to the future environment quality regulation parameter according to the corresponding relation between the preset environment intelligent regulation strategy and the future environment quality regulation parameter.
9. The intelligent laboratory environment quality analysis system according to claim 7, wherein the calculation formula for calculating the maximum information transmission distance between each measurement laboratory and the environment monitoring center is as follows:
Figure FDA0003849970680000041
wherein MTD is the maximum transmission distance between a measurement laboratory node and an environmental monitoring center node, d DA To measure the depth of a laboratory node, d LA Monitoring the depth of the central node for the environment, d F When the environment monitoring center node is not a leaf node of the metering laboratory node, the depth of a root node shared by the environment monitoring center node and the metering laboratory node is determined, and C is the number of address spaces capable of being allocated by the current metering laboratory node.
10. The intelligent laboratory environment quality analysis system of claim 7, wherein the neural network model for assessing the metrology environment comprises an input layer, a fuzzy layer, a rules layer, and an output layer;
the input layer inputs the neurons into the fuzzy layer, and the structure of the input layer is as follows:
Figure FDA0003849970680000051
wherein, I j Input to the jth neuron of the ambiguity layer, ω ij Is the connection weight between the ith neuron of the input layer and the jth neuron of the fuzzy layer j For bias of the blur layer, o i Is the ith neuron;
the formula for calculating the blur layer is:
Figure FDA0003849970680000052
wherein, M j The output of the jth neuron of the fuzzy layer, c is the center of the environment evaluation neural network, and sigma is the width of the environment evaluation neural network;
the formula for the fuzzy layer to send the calculation result to the rule layer is as follows:
Figure FDA0003849970680000053
wherein A is r Input to the r-th neuron of the rule layer, ω jr For the weight of the connection between the jth neuron of the fuzzy layer and the r neuron of the regular layer, θ r A bias for a regular layer;
the calculation formula of the rule layer is as follows:
Figure FDA0003849970680000054
Figure FDA0003849970680000055
Figure FDA0003849970680000056
wherein, O r As a result of the non-linear transformation,F r the r-th nerve of the regular layerThe lower limit of the meta-output,
Figure FDA0003849970680000059
the upper limit of the output of the r-th neuron of the rule layer, f (-) is the activation function,Othe lower limit value in the nonlinear transformation results for all neurons in the rule layer,
Figure FDA0003849970680000057
the upper limit value in the nonlinear conversion result of all the neurons in the rule layer is obtained;
the calculation formula of the output layer is as follows:
Figure FDA0003849970680000058
where y is the output of the output layer.
CN202211128543.2A 2022-09-16 2022-09-16 Intelligent analysis method and system for laboratory environment quality Pending CN115375181A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211128543.2A CN115375181A (en) 2022-09-16 2022-09-16 Intelligent analysis method and system for laboratory environment quality

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211128543.2A CN115375181A (en) 2022-09-16 2022-09-16 Intelligent analysis method and system for laboratory environment quality

Publications (1)

Publication Number Publication Date
CN115375181A true CN115375181A (en) 2022-11-22

Family

ID=84070675

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211128543.2A Pending CN115375181A (en) 2022-09-16 2022-09-16 Intelligent analysis method and system for laboratory environment quality

Country Status (1)

Country Link
CN (1) CN115375181A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116045438A (en) * 2023-01-09 2023-05-02 江苏悦达绿色建筑科技有限公司 Fresh air system of three-constant intelligent house and control method thereof

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116045438A (en) * 2023-01-09 2023-05-02 江苏悦达绿色建筑科技有限公司 Fresh air system of three-constant intelligent house and control method thereof

Similar Documents

Publication Publication Date Title
CN110824915B (en) GA-DBN network-based intelligent monitoring method and system for wastewater treatment
CN110824914B (en) Intelligent wastewater treatment monitoring method based on PCA-LSTM network
US7406451B2 (en) Method for training neural networks
CN108038300A (en) Optical fiber state evaluating method based on improved membership function combination neutral net
CN105740991A (en) Climate change prediction method and system for fitting various climate modes based on modified BP neural network
CN112101684B (en) Plug-in hybrid electric vehicle real-time energy management method and system
JP2014105989A (en) Energy consumption prediction method of building power equipment
CN110309609B (en) Building indoor air quality evaluation method based on rough set and WNN
CN111737799B (en) Bridge safety assessment method combining dynamic Bayesian network and heuristic reasoning
CN111510500B (en) Water quality monitoring data calibration method based on edge calculation
AU2020102518A4 (en) A method of gas sensor calibration based on linear optimization
CN115375181A (en) Intelligent analysis method and system for laboratory environment quality
CN104598984A (en) Fuzzy neural network based fault prediction method
Alfred et al. A performance comparison of statistical and machine learning techniques in learning time series data
CN113919545A (en) Photovoltaic power generation power prediction method and system with integration of multiple data models
CN114994261A (en) Remote calibration method for sensor for ambient air monitoring
CN114528764A (en) Soft measurement modeling method and device based on integral optimization and instant learning
Ismail et al. Adaptive neural network prediction model for energy consumption
KR102390461B1 (en) A.I applicable operation method for air quality measurement system
CN116629918A (en) User consumption prediction method and system based on cross-border electronic commerce
CN115907204A (en) Forest transpiration water consumption prediction method for optimizing BP neural network by sparrow search algorithm
CN114993501A (en) NTC temperature sensor calibration method based on edge calculation
CN112580853A (en) Bus short-term load prediction method based on radial basis function neural network
CN115018137A (en) Water environment model parameter calibration method based on reinforcement learning
Petlíková Modeling of the time structure of construction processes using neural networks

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