CN115060625A - Method and device for obtaining slurry density, electronic equipment and storage medium - Google Patents
Method and device for obtaining slurry density, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115060625A CN115060625A CN202210557059.5A CN202210557059A CN115060625A CN 115060625 A CN115060625 A CN 115060625A CN 202210557059 A CN202210557059 A CN 202210557059A CN 115060625 A CN115060625 A CN 115060625A
- Authority
- CN
- China
- Prior art keywords
- training
- preset
- model
- control parameter
- population
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N9/00—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity
- G01N9/36—Analysing materials by measuring the density or specific gravity, e.g. determining quantity of moisture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Feedback Control In General (AREA)
Abstract
The disclosure relates to a method and a device for obtaining slurry density, electronic equipment and a storage medium, and relates to the field of thermal power generation. Firstly, a density measurement model is obtained through whale optimization algorithm training according to a preset training sample, then a target control parameter value of a target control parameter for generating limestone slurry is obtained, and finally the target control parameter value is input into the density measurement model to obtain the slurry density of the limestone slurry output by the density measurement model. The problem that a measurement result is inaccurate due to abrasion of a densimeter when the densimeter is used for directly obtaining the slurry density in the related technology is avoided, and the slurry density is obtained by adopting a target control parameter value obtained by stably measuring the slurry density, so that the cost for periodically replacing and maintaining the densimeter is reduced, the accuracy of the slurry density result is improved, and the flue gas desulfurization effect is favorably improved.
Description
Technical Field
The disclosure relates to the field of thermal power generation, and in particular to a method and a device for acquiring slurry density, an electronic device and a storage medium.
Background
In the field of thermal power generation, limestone-gypsum method desulfurization is the most mature flue gas desulfurization technology with the widest application range at present, and the quality of limestone slurry obtained by a slurry preparation system has great influence on the desulfurization effect, so that accurate measurement of the slurry density of the limestone slurry is very important.
At present, the density of the slurry is mostly measured by adopting a densimeter in a thermal power plant, the densimeter is mostly in a probe pipeline type mounting structure, and the probe of the densimeter is easily subjected to scouring wear of the slurry due to high viscosity of the slurry, so that an error exists in a measurement result of the density of the slurry.
Disclosure of Invention
To overcome the problems in the related art, the present disclosure provides a method and an apparatus for obtaining a slurry density, an electronic device, and a storage medium.
According to a first aspect of the embodiments of the present disclosure, there is provided a method for obtaining a density of a slurry, the method including:
training according to a preset training sample through a whale optimization algorithm to obtain a density measurement model, wherein elements of population members of the whale optimization algorithm are model parameters of the density measurement model, an initial element value of each element of the population members in the whale optimization algorithm is obtained through Logistic chaotic mapping, the preset training sample comprises training control parameter values of a plurality of training control parameter groups and training output parameter values of corresponding training output parameters, each training control parameter group comprises a plurality of training control parameters, and the training output parameters comprise the density of the slurry;
acquiring a target control parameter value of a target control parameter for generating limestone slurry;
and inputting the target control parameter value into the density measurement model to obtain the slurry density of the limestone slurry output by the density measurement model.
Optionally, the density measurement model is a neural network model, and the obtaining of the density measurement model through whale optimization algorithm training according to the preset training sample includes:
determining whale optimization algorithm parameters of the whale optimization algorithm according to model parameters of a preset neural network model, wherein the whale optimization algorithm parameters comprise elements of the population members, preset element value threshold values of each element value and whale population scale;
obtaining the current element value of each population member of the whale optimization algorithm through Logistic chaotic mapping according to the whale optimization algorithm parameters and preset chaotic mapping parameters, wherein the chaotic mapping parameters comprise chaotic mapping coefficients;
and obtaining target model parameter values of the preset neural network model by using the whale optimization algorithm according to the whale optimization algorithm parameters, the current element values of each population member and the preset training samples, and taking the obtained target neural network model as the density measurement model.
Optionally, the determining whale optimization algorithm parameters of the whale optimization algorithm according to the model parameters of the preset neural network model includes:
taking the training control parameter as an input node of the preset neural network model, taking the slurry density as an output node of the preset neural network model, determining a model parameter of the preset neural network model according to the input node, the output node and a hidden neuron of the preset neural network model, and taking the model parameter as an element of the population member, wherein the model parameter comprises a first connection weight, a first threshold of the hidden neuron, a second connection weight and a second threshold of the output node, the first connection weight represents a weight between the input node and the hidden neuron, and the second connection weight represents a weight between the hidden neuron and the output node;
determining the element value range of each element according to a preset model parameter value range of each model parameter;
and determining the whale population scale according to the number of the model parameter values and the expected time of model training.
Optionally, the obtaining a target model parameter value of the preset neural network model by using the whale optimization algorithm according to the whale optimization algorithm parameter, the current element value of each population member, and a preset training sample, and using the obtained target neural network model as the density measurement model includes:
acquiring a fitness value of each population member according to the preset training sample, wherein the fitness value is a mean square error between a prediction output parameter value and the corresponding training output parameter value, and the prediction output parameter value is acquired through a preset neural network model according to the training control parameter value of each training control parameter group and the current element value of the population member;
obtaining target element values of target population members of the population according to the fitness value of each population member, wherein the target population members are population members with the minimum fitness value in the population;
and adopting the whale optimization algorithm according to the whale optimization algorithm parameters to complete surrounding, predation and searching of the target element value so as to update the current element value of each population member, repeating the steps of obtaining the fitness value of each population member according to the preset training sample and obtaining the target element value of the target population member of the population according to the fitness value of each population member, so that the optimal element value corresponding to the optimal population member with the minimum fitness value in the population is obtained when a preset finishing condition is met, taking the optimal element value as the target model parameter value of the preset neural network model, and taking the obtained target neural network model as the density measurement model.
Optionally, the preset end condition includes that the fitness value corresponding to the optimal population member is less than or equal to a preset fitness value threshold, and/or the training times are greater than or equal to a preset training time threshold.
Optionally, the method further comprises:
acquiring multiple sets of historical data of the limestone slurry, wherein the historical data comprises alternative control parameter values of multiple alternative control parameter sets and corresponding output parameter values of output parameters, each alternative control parameter set comprises multiple alternative control parameters of the limestone slurry, and the output parameters comprise the slurry density;
determining the target control parameter from the multiple candidate control parameters by adopting a grey correlation method according to the multiple groups of historical data;
and acquiring the preset training samples from the multiple groups of historical data according to the target control parameters.
Optionally, the determining the target control parameter from the multiple candidate control parameters by using a gray correlation method according to the multiple sets of historical data includes:
acquiring the grey correlation degree of the alternative control parameter value of each alternative control parameter and the corresponding output parameter value according to the historical data;
and determining the target control parameter from the multiple candidate control parameters according to the gray correlation degree and a preset gray correlation degree threshold, wherein the gray correlation degree of the target control parameter is greater than or equal to the preset gray correlation degree threshold.
Optionally, the method further comprises:
after acquiring multiple sets of historical data of the limestone slurry, deleting abnormal historical data from the multiple sets of historical data according to multiple preset control parameter value ranges, wherein the abnormal historical data represents that an alternative control parameter value of any alternative control parameter in the alternative control parameter sets exceeds the corresponding control parameter value range.
Optionally, the target control parameters and the training control parameters include a cyclone station inlet pressure, an instantaneous feed volume, an instantaneous flow of dilution water, and an instantaneous flow of grinding water.
According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for obtaining a density of a slurry, the apparatus comprising:
the model training module is configured to obtain a density measurement model through whale optimization algorithm training according to a preset training sample, wherein elements of population members of the whale optimization algorithm are model parameters of the density measurement model, an initial element value of each population member of the whale optimization algorithm is obtained through Logistic chaotic mapping, the preset training sample comprises training control parameter values of a plurality of training control parameter groups and training output parameter values of corresponding training output parameters, each training control parameter group comprises a plurality of training control parameters, and the training output parameters comprise the slurry density;
a parameter acquisition module configured to acquire a target control parameter value of a target control parameter for generating the limestone slurry;
and the result acquisition module is configured to input the target control parameter value into a pre-trained density measurement model so as to obtain the slurry density of the limestone slurry output by the density measurement model.
Optionally, the density measurement model is a neural network model, and the model training module is further configured to:
determining whale optimization algorithm parameters of the whale optimization algorithm according to model parameters of a preset neural network model, wherein the whale optimization algorithm parameters comprise elements of the population members, preset element value thresholds of each element value and whale population scale;
obtaining the current element value of each population member of the whale optimization algorithm through Logistic chaotic mapping according to the whale optimization algorithm parameters and preset chaotic mapping parameters, wherein the chaotic mapping parameters comprise chaotic mapping coefficients;
and obtaining target model parameter values of the preset neural network model by using the whale optimization algorithm according to the whale optimization algorithm parameters, the current element values of each population member and the preset training samples, and taking the obtained target neural network model as the density measurement model.
Optionally, the model training module is further configured to:
taking the training control parameter as an input node of the preset neural network model, taking the slurry density as an output node of the preset neural network model, determining a model parameter of the preset neural network model according to the input node, the output node and a hidden neuron of the preset neural network model, and taking the model parameter as an element of the population member, wherein the model parameter comprises a first connection weight, a first threshold of the hidden neuron, a second connection weight and a second threshold of the output node, the first connection weight represents a weight between the input node and the hidden neuron, and the second connection weight represents a weight between the hidden neuron and the output node;
determining the element value range of each element according to a preset model parameter value range of each model parameter;
and determining the whale population scale according to the number of the model parameter values and the expected time of model training.
Optionally, the model training module is further configured to:
acquiring a fitness value of each population member according to the preset training sample, wherein the fitness value is a mean square error between a prediction output parameter value and the corresponding training output parameter value, and the prediction output parameter value is acquired through a preset neural network model according to the training control parameter value of each training control parameter group and the current element value of the population member;
obtaining target element values of target population members of the population according to the fitness value of each population member, wherein the target population members are population members with the minimum fitness value in the population;
and adopting the whale optimization algorithm according to the whale optimization algorithm parameters to complete surrounding, predation and searching of the target element value so as to update the current element value of each population member, repeating the steps of obtaining the fitness value of each population member according to the preset training sample and obtaining the target element value of the target population member of the population according to the fitness value of each population member, so that the optimal element value corresponding to the optimal population member with the minimum fitness value in the population is obtained when a preset finishing condition is met, taking the optimal element value as the target model parameter value of the preset neural network model, and taking the obtained target neural network model as the density measurement model.
Optionally, the apparatus further comprises a training sample acquisition module configured to:
acquiring multiple sets of historical data of the limestone slurry, wherein the historical data comprises alternative control parameter values of multiple alternative control parameter sets and corresponding output parameter values of output parameters, each alternative control parameter set comprises multiple alternative control parameters of the limestone slurry, and the output parameters comprise the slurry density;
determining the target control parameter from the multiple candidate control parameters by adopting a grey correlation method according to the multiple groups of historical data;
and acquiring the preset training samples from the multiple groups of historical data according to the target control parameters.
Optionally, the training sample obtaining module is further configured to:
acquiring the grey correlation degree of the alternative control parameter value of each alternative control parameter and the corresponding output parameter value according to the historical data;
and determining the target control parameter from the multiple candidate control parameters according to the gray correlation degree and a preset gray correlation degree threshold, wherein the gray correlation degree of the target control parameter is greater than or equal to the preset gray correlation degree threshold.
Optionally, the training sample obtaining module is further configured to:
after acquiring multiple sets of historical data of the limestone slurry, deleting abnormal historical data from the multiple sets of historical data according to multiple preset control parameter value ranges, wherein the abnormal historical data represents that an alternative control parameter value of any alternative control parameter in the alternative control parameter sets exceeds the corresponding control parameter value range.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any of the embodiments of the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect described above.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
according to the method, firstly, a density measurement model is obtained through whale optimization algorithm training according to a preset training sample, then a target control parameter value of a target control parameter for generating limestone slurry is obtained, and finally the target control parameter value is input into the density measurement model to obtain the slurry density of the limestone slurry output by the density measurement model. The problem that a measurement result is inaccurate due to abrasion of a densimeter when the densimeter is used for directly obtaining the slurry density in the related technology is avoided, and the slurry density is obtained by adopting a target control parameter value obtained by stably measuring the slurry density, so that the cost for periodically replacing and maintaining the densimeter is reduced, the accuracy of the slurry density result is improved, and the flue gas desulfurization effect is favorably improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and, together with the description, serve to explain the principles of the disclosure, but are not intended to limit the disclosure.
FIG. 1 is a flow chart illustrating a method of obtaining slurry density according to an exemplary embodiment.
FIG. 2 is a flow chart illustrating another method of obtaining slurry density according to an exemplary embodiment.
FIG. 3 is a flow chart illustrating yet another method of obtaining slurry density in accordance with an exemplary embodiment.
FIG. 4 is a flow chart illustrating yet another method of obtaining slurry density in accordance with an exemplary embodiment.
Fig. 5 is a block diagram illustrating a device for obtaining a density of a slurry according to an exemplary embodiment.
FIG. 6 is a block diagram illustrating another means of obtaining slurry density in accordance with an exemplary embodiment.
FIG. 7 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims, and it should be understood that the specific embodiments described herein are merely illustrative and explanatory of the disclosure and are not restrictive of the disclosure.
It should be noted that all actions of acquiring signals, information or data in the present application are performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
First, an application scenario of the present disclosure is explained, the present disclosure can be applied to the field of thermal power generation, limestone-gypsum method desulfurization is a mainstream flue gas desulfurization technology of a thermal power plant at present, and quality of limestone slurry obtained by a slurry preparation system has a large influence on desulfurization effect, so it is very important to accurately measure slurry density of limestone slurry.
At present, the density of the slurry is mostly measured by adopting a densimeter in a thermal power plant, the densimeter is mostly in a probe pipeline type mounting structure, and the probe of the densimeter is easily subjected to scouring wear of the slurry due to high viscosity of the slurry, so that an error exists in a measurement result of the density of the slurry.
The inventor notices that many control parameters of the slurry preparation system, such as the inlet pressure of the cyclone station, the instantaneous feeding amount and the like, have close relation with the final slurry density, so the accurate slurry density can be obtained through the control parameter values of the control parameters based on a deep learning method.
The present disclosure is described below with reference to specific examples.
Fig. 1 is a flow chart illustrating a method of obtaining a density of a slurry, as shown in fig. 1, which may include the steps of:
in step S101, a density measurement model is obtained by training through a whale optimization algorithm according to a preset training sample.
The preset training sample comprises training control parameter values of a plurality of training control parameter groups and training output parameter values of corresponding training output parameters, each training control parameter group comprises a plurality of training control parameters, each training output parameter comprises slurry density, the density measurement model can be a supervised deep learning model, for example, a neural network model, the density measurement model is obtained by training through the preset training sample, and the selection of the specific model is not limited.
The whale Optimization algorithm is also called WOA (white Optimization algorithm), is an algorithm for optimizing preset parameters by simulating a spiral bubble net feeding strategy of whales, and can effectively solve the problems that a traditional neural network model is low in convergence speed and easy to fall into a local extreme value.
In the whale optimization algorithm, each whale population can be considered as a value of a model parameter vector of a density measurement model, in order to improve the quality of an initial value, the whale population randomly traverses the value space of the model parameter vector, and the initial element value of each population member in each whale optimization algorithm is obtained through Logistic chaotic mapping.
Illustratively, the density measurement model may be a neural network model, and fig. 2 is a flowchart illustrating another slurry density acquisition method according to an exemplary embodiment, which may include the following steps, as shown in fig. 2:
in step S1011, whale optimization algorithm parameters of the whale optimization algorithm are determined according to the model parameters of the preset neural network model.
The whale optimization algorithm parameters comprise elements of population members, preset element value threshold values of all element values and whale population scale.
In some possible implementations, whale optimization algorithm parameters of the whale optimization algorithm are determined according to model parameters of a preset neural network model through the following steps:
step 1, taking a training control parameter as an input node of a preset neural network model, taking the slurry density as an output node of the preset neural network model, determining a model parameter of the preset neural network model according to the input node, the output node and hidden neurons of the preset neural network model, and taking the model parameter as an element of a population member.
The model parameters comprise a first connection weight, a first threshold of the hidden neuron, a second connection weight and a second threshold of the output node, wherein the first connection weight represents the weight between the input node and the hidden neuron, and the second connection weight represents the weight between the hidden neuron and the output node.
In some possible implementation manners, the upper limit of the number of the hidden neurons may be determined by the following formula one, then the upper limit of the hidden neurons is taken as the cycle number, a plurality of neural networks are constructed, a preset training sample is adopted, and the number of the hidden neurons with the smallest mean square error is selected from the plurality of neural networks.
Wherein N is h In order to imply the upper limit of the number of the neurons, m and n are the number of the input nodes and the number of the output nodes respectively, a is generally a preset integer, the value range is 1-10, and for example, the value can be 5.
After the number of the hidden neurons of the preset neural network model is determined by the method, the number of the model parameters of the preset neural network model can be determined by the following formula II according to the number of the input nodes, the number of the output nodes and the number of the hidden neurons.
K＝n i ×n h +n h +n h ×n o +n o (formula two)
Wherein K is the number of model parameters of a preset neural network model, namely the number of elements of population members in the whale optimization algorithm, and n i Is the number of input nodes, n h To imply the number of neurons, n o Is the number of output nodes. And taking the model parameters of the preset neural network model as elements of the population members.
Illustratively, when the number of the input nodes is 4, the number of the output nodes is 1, and the number of the hidden layer neurons is 5, the model parameters of the preset neural network model include 20 first connection weights, 5 first thresholds, 5 second connection weights, and 1 second threshold, and the number of the model parameters is 31, that is, the number of elements in the whale population members is 31.
And 2, determining the element value range of each element according to the preset model parameter value range of each model parameter.
Illustratively, the element value range of each corresponding element in the race member is determined according to a preset model parameter value range (for example, an upper limit and a lower limit of the first connection weight, an upper limit and a lower limit of the first threshold, an upper limit and a lower limit of the second connection weight, and an upper limit and a lower limit of the second threshold) of each model parameter. It is convenient to determine the search space for each element of a ethnic member in the whale optimization algorithm.
It should be noted that, the upper and lower limits of the model parameter value of the model parameter may be the same or different, and the upper and lower limits are the same and represent that the value range of the model parameter value is a preset fixed value, which is not limited by the present disclosure.
And 3, determining the whale population scale according to the number of the model parameter values and the expected time of model training.
The larger the population scale is, the more scattered the distribution in the whole global range is, the larger the search space range is, and the more easily the global optimal solution is found. But the larger the population size, the longer the model training time. In some possible implementation manners, the size of the whale population may be determined according to the number of model parameters of the preset neural network model and the expected time of model training, specifically referring to the related description about the determination of the whale population size in the related art.
In another possible implementation manner, a preset whale population size may also be used as the whale population size, for example, the preset whale population size may be 30, which is not limited by the present disclosure.
In step S1012, the current element value of each population member of the whale optimization algorithm is obtained through Logistic chaotic mapping according to the whale optimization algorithm parameters and the preset chaotic mapping parameters.
The chaotic mapping parameters comprise chaotic mapping coefficients.
In some possible implementations, the current element value of each population member of the whale optimization algorithm may be determined by the following steps.
Firstly, acquiring a chaotic mapping coefficient of each element of each population member according to the following formula III.
X i，j+1 ＝X i，j ×μ×(1-X i，j ) (formula three)
Wherein, X i，j Is the chaotic mapping coefficient, X, of the ith element in the jth population member i，1 Is a random number with the value range of (0,1) generated randomly, mu is a chaotic coefficient and is a preset constant, for example, 4, j has the value range of [1, N-1]]Wherein N is the population scale, i.e. the number of population members, and the value range of i is [1, K ]]And K is the number of elements in the population member.
Then, the current element value of each element in each population member is obtained according to the chaotic mapping coefficient and the following formula IV.
Y i，j ＝X i，j ×(U i -L i )+L i (formula four)
Wherein, X i，j Is the chaotic mapping coefficient of the ith element in the jth population member, Y i，j Is the current element value, U, of the ith element in the jth population member i And L i Respectively the upper and lower limits of the element value range of the ith element in the population members, U i Greater than or equal to L i J has a value range of [1, N]Wherein N is the population scale, i.e. the number of population members, and the value range of i is [1, K ]]And K is the number of elements in the population members.
In step S1013, target model parameter values of a preset neural network model are obtained by a whale optimization algorithm according to the whale optimization algorithm parameters, the current element values of each population member, and preset training samples, and the obtained target neural network model is used as a density measurement model.
Illustratively, in step S1011, having determined the model structure of the preset neural network model, in this step, the target model parameter values of the preset neural network model may be obtained by the whale optimization algorithm according to the whale optimization algorithm parameters, the current element values of each population member, and the preset training samples, so as to obtain the target neural network model, which is used as the density measurement model.
Step 1, obtaining the fitness value of each population member according to a preset training sample.
The fitness value is the mean square error of the prediction output parameter value and the corresponding training output parameter value, and the prediction output parameter value is obtained through a preset neural network model according to the training control parameter value of each training control parameter group and the current element value of the population member.
In some possible implementation manners, the current element value is used as a model parameter of the preset neural network model, and the training control parameter value is substituted into the preset neural network model, so as to obtain a predicted output parameter value corresponding to the training control parameter value.
For example, the fitness value may be determined based on the predicted output parameter value, the trained output parameter value, and equation five as follows.
Wherein S is i Is the fitness value of the ith population member,
substituting the kth training control parameter value into a preset neural network model formed by the ith population member to obtain a predicted output parameter value x i，k And T is the number of training samples in the preset training sample.
And 2, acquiring target element values of target population members of the population according to the fitness value of each population member.
Wherein, the target population member is the population member with the minimum fitness value in the population.
For example, after the fitness value of each population member is obtained, the population member with the smallest fitness value may be taken as the target population member, and the element value corresponding to the target population member is the target element value.
And 3, adopting a whale optimization algorithm according to whale optimization algorithm parameters to complete surrounding, predation and searching of the target element value so as to update the current element value of each population member, repeating the steps of obtaining the fitness value of each population member according to a preset training sample and obtaining the target element value of the target population member of the population according to the fitness value of each population member, so that the optimal element value corresponding to the optimal population member with the minimum fitness value in the population is obtained when a preset finishing condition is met, taking the optimal element value as a target model parameter value of a preset neural network model, and taking the obtained target neural network model as a density measurement model.
The enclosing predation in the whale optimization algorithm is a near-optimal solution by adopting a spiral bubble net mode in the process of simulating whale predation. The target element value is the current optimal solution in the current round of predation, each group member can contract and surround the current optimal solution, can move around a prey in a continuously reduced circle in a spiral updating mode, and can move along a spiral path at the same time, and the mathematical model for surrounding predation can refer to the description of whale optimization algorithm in the related technology, and the description of the mathematical model for surrounding predation is omitted in the present disclosure. Besides the process of surrounding predation, population members can randomly search for prey, namely position updating is carried out by using a scheme of randomly selecting individuals, so that the global optimization capacity of the WOA algorithm is improved, the whale algorithm has the capacity of jumping out of a local optimal solution, and a specific mathematical model for random search can refer to the description of the whale optimization algorithm in the related technology.
In the process of surrounding predation and searching of the population members, the current element value of each population member is updated through training, and the steps of obtaining the fitness value of each population member according to a preset training sample and obtaining the target element value of the target population member of the population according to the fitness value of each population member are repeated. In the process, the target population members and the corresponding target element values are continuously optimized and updated, the fitness value is correspondingly and continuously reduced, when a preset finishing condition is met, the optimal element value corresponding to the optimal population member with the minimum fitness value in the population is obtained and used as a target model parameter value of a preset neural network model, and the obtained target neural network model is used as a density measurement model.
In some embodiments, the preset end condition may include that the fitness value corresponding to the optimal population member is less than or equal to a preset fitness value threshold, and/or the training times are greater than or equal to a preset training time threshold.
In another embodiment, the value range of j in formula three may also be [1, k × N-1], and correspondingly, the value range of j in formula four may be [1, k × N ], where k may be a natural number greater than 1, and for example, k may be 2. Therefore, the current element values of k × N population members can be obtained through the formula three and the formula four, N population members with the minimum fitness can be selected from the k × N population members, the density measurement model is obtained for the screened population members by adopting a whale optimization algorithm, and the efficiency of the whale optimization algorithm can be further improved.
In step S102, a target control parameter value of a target control parameter for generating a limestone slurry is acquired.
For example, a target control parameter value of a target control parameter for generating a limestone slurry may be collected by a corresponding plurality of sensors.
In step S103, the target control parameter value is input into the density measurement model to obtain the slurry density of the limestone slurry output by the density measurement model.
Illustratively, the target control parameter value is input into the density measurement model obtained by training in step S101, so as to obtain the slurry density of limestone slurry output by the density measurement model.
Through the scheme, the situation that the density meter is inaccurate due to abrasion easily when the density meter is used for directly obtaining the density of the slurry in the related technology can be avoided, the density of the slurry is obtained by adopting the target control parameter value obtained by stable measurement related to the density of the slurry, the cost for periodically replacing and maintaining the density meter is reduced, the accuracy of the density result of the slurry is improved, and the effect of flue gas desulfurization is favorably improved.
The multiple control parameters of the slurry preparation system all have influence on the final slurry density (such as the instantaneous feeding amount of a weighing feeder, the instantaneous flow amount of grinding water of a wet ball mill, the density of a finished slurry box, the instantaneous flow amount of dilution water, the liquid level of a recirculation box, the phase current of a ball mill, the outlet pressure of a recirculation pump, the liquid level of a finished slurry box, the opening amount of a dilution water adjusting valve, the opening amount of a grinding water adjusting valve and the inlet pressure of a cyclone station).
In another embodiment, a target control parameter having the largest influence on the slurry density can be selected from a plurality of candidate control parameters, so that the efficiency of obtaining the density measurement model is improved.
Fig. 3 is a flow chart illustrating a method of obtaining a density of a slurry according to an exemplary embodiment, which may further include the steps of, as shown in fig. 3:
in step S104, sets of history data of the limestone slurry are acquired.
The historical data comprises a plurality of candidate control parameter values of a plurality of candidate control parameter groups and corresponding output parameter values of output parameters, each candidate control parameter group comprises a plurality of candidate control parameters of limestone slurry, and the output parameters comprise slurry density.
The mode of acquiring the multiple sets of historical data can refer to the implementation of sensors and information collectors in the related technology, and details are not repeated in the disclosure.
In step S105, a target control parameter is determined from a plurality of candidate control parameters by a gray correlation method based on a plurality of sets of history data.
The Grey Relational Analysis (Grey Relational Analysis) is a method for measuring the degree of correlation between factors according to the degree of similarity or dissimilarity of the development trends between the factors.
For example, the target control parameter may be determined from a plurality of candidate control parameters by obtaining a gray correlation of each candidate control parameter in the history data as follows.
Firstly, acquiring the gray correlation degree of the candidate control parameter value of each candidate control parameter and the corresponding output parameter value according to historical data.
In some possible implementations, the gray correlation degree of each alternative control parameter can be obtained by the following formula six.
Wherein s and e j Is an intermediate variable, x j (i) Characterizing the jth candidate control parameter value in the ith historical data, y (i) is the output parameter value in the ith historical data, N is the number of the historical data, and gamma (x) j And y) is the grey correlation degree of the jth candidate control parameter and the output parameter. To avoid inaccurate calculation of gray correlation caused by difference of absolute values of the candidate control parameter values and the output parameter values, the above x j (i) And y (i) are all required to be subjected to non-dimensionalization processing, the example given in the formula six is that the candidate control parameter value is divided by the candidate control parameter value leader to be subjected to non-dimensionalization processing, and the processing mode is not limited by the disclosure.
And then, determining a target control parameter from a plurality of candidate control parameters according to the gray correlation degree and a preset gray correlation degree threshold value.
And the grey correlation degree of the target control parameter is greater than or equal to a preset grey correlation degree threshold value.
For example, an alternative control parameter with a gray relevance greater than or equal to a preset gray relevance threshold may be selected as the target control parameter, and the preset gray relevance threshold may be 75% for example.
In another possible implementation manner, a plurality of candidate control parameters with the largest gray relevance may also be selected as the target control parameters, and for example, 4 candidate control parameters with the largest gray relevance may be selected as the target control parameters.
In step S106, preset training samples are obtained from the sets of historical data according to the target control parameters.
By the aid of the scheme, the model can be simplified as much as possible on the premise that the accuracy of the density measurement model is guaranteed, the calculated amount of model training is reduced, and the efficiency of model training is improved.
Fig. 4 is a flow chart illustrating a method of obtaining a density of a slurry according to an exemplary embodiment, which may further include the steps of, as shown in fig. 4:
in step S107, after the plurality of sets of history data of the limestone slurry are acquired, the abnormal history data is deleted from the plurality of sets of history data according to the preset plurality of control parameter value ranges.
And the abnormal historical data represents that the candidate control parameter value of any one candidate control parameter in the candidate control parameter group exceeds the corresponding control parameter value range.
By the scheme, the historical data can be screened, and abnormal historical data exceeding the preset control parameter value range in the historical data can be deleted, so that the reliability of the preset training sample is further improved, and the model training efficiency is improved.
In another embodiment, the target and training control parameters include the cyclone station inlet pressure, instantaneous feed rate, dilution water instantaneous flow rate, and mill water instantaneous flow rate.
The mode of acquiring the multiple sets of historical data can refer to the implementation of sensors and information collectors in the related technology, and details are not repeated in the disclosure.
By the aid of the scheme, the model can be simplified as much as possible on the premise that the accuracy of the density measurement model is guaranteed, the calculated amount of model training is reduced, and the efficiency of model training is improved.
Fig. 5 is a block diagram illustrating a slurry density acquisition apparatus 500 according to an exemplary embodiment, where the slurry density acquisition apparatus 500, as shown in fig. 5, includes:
the model training module 501 is configured to obtain a density measurement model through whale optimization algorithm training according to a preset training sample, wherein elements of population members of the whale optimization algorithm are model parameters of the density measurement model, an initial element value of each population member of the whale optimization algorithm is obtained through Logistic chaotic mapping, the preset training sample comprises training control parameter values of a plurality of training control parameter groups and training output parameter values of corresponding training output parameters, each training control parameter group comprises a plurality of training control parameters of limestone slurry, and the training output parameters comprise slurry density;
a parameter acquisition module 502 configured to acquire a target control parameter value of a target control parameter for generating the limestone slurry;
and a result obtaining module 503, configured to input the target control parameter value into the pre-trained density measurement model to obtain the slurry density of the limestone slurry output by the density measurement model.
Optionally, the density measurement model is a neural network model, and the model training module 501 is further configured to:
determining whale optimization algorithm parameters of a whale optimization algorithm according to model parameters of a preset neural network model, wherein the whale optimization algorithm parameters comprise elements of population members, preset element value threshold values of each element value and whale population scale;
obtaining the current element value of each population member of the whale optimization algorithm through Logistic chaotic mapping according to whale optimization algorithm parameters and preset chaotic mapping parameters, wherein the chaotic mapping parameters comprise chaotic mapping coefficients;
and obtaining target model parameter values of a preset neural network model by using a whale optimization algorithm according to whale optimization algorithm parameters, the current element value of each population member and a preset training sample, and taking the obtained target neural network model as a density measurement model.
Optionally, the model training module 501 is further configured to:
taking a training control parameter as an input node of a preset neural network model, taking the slurry density as an output node of the preset neural network model, determining a model parameter of the preset neural network model according to the input node, the output node and a hidden neuron of the preset neural network model, taking the model parameter as an element of a population member, wherein the model parameter comprises a first connection weight, a first threshold of the hidden neuron, a second connection weight and a second threshold of the output node, the first connection weight represents a weight between the input node and the hidden neuron, and the second connection weight represents a weight between the hidden neuron and the output node;
determining the element value range of each element according to the preset model parameter value range of each model parameter;
and determining the whale population scale according to the number of the model parameter values and the expected time of model training.
Optionally, the model training module 501 is further configured to:
acquiring a fitness value of each population member according to a preset training sample, wherein the fitness value is the mean square error of a prediction output parameter value and a corresponding training output parameter value, and the prediction output parameter value is obtained through a preset neural network model according to a training control parameter value of each training control parameter group and a current element value of the population member;
acquiring target element values of target population members of the population according to the fitness value of each population member, wherein the target population members are population members with the minimum fitness value in the population;
and adopting a whale optimization algorithm according to whale optimization algorithm parameters to complete surrounding, predation and searching of the target element value so as to update the current element value of each population member, repeating the steps of obtaining the fitness value of each population member according to a preset training sample and obtaining the target element value of the target population member of the population according to the fitness value of each population member, so that the optimal element value corresponding to the optimal population member with the minimum fitness value in the population is obtained when a preset finishing condition is met, taking the optimal element value as a target model parameter value of a preset neural network model, and taking the obtained target neural network model as a density measurement model.
Fig. 6 is a block diagram illustrating a slurry density acquisition apparatus 500 according to an exemplary embodiment, and as shown in fig. 6, the slurry density acquisition apparatus 500 further includes a training sample acquisition module 504 configured to:
acquiring multiple groups of historical data of limestone slurry, wherein the historical data comprises alternative control parameter values of multiple alternative control parameter groups and output parameter values of corresponding output parameters, each alternative control parameter group comprises multiple alternative control parameters of the limestone slurry, and the output parameters comprise slurry density;
determining a target control parameter from a plurality of alternative control parameters by adopting a grey correlation method according to a plurality of groups of historical data;
and acquiring preset training samples from the sets of historical data according to the target control parameters.
Optionally, the training sample obtaining module 504 is further configured to:
acquiring the gray correlation degree of the alternative control parameter value of each alternative control parameter and the corresponding output parameter value according to historical data;
and determining a target control parameter from the multiple candidate control parameters according to the gray correlation degree and a preset gray correlation degree threshold, wherein the gray correlation degree of the target control parameter is greater than or equal to the preset gray correlation degree threshold.
Optionally, the training sample obtaining module 504 is further configured to:
after acquiring multiple sets of historical data of limestone slurry, deleting abnormal historical data from the multiple sets of historical data according to a plurality of preset control parameter value ranges, wherein the abnormal historical data represents that the alternative control parameter value of any alternative control parameter in the alternative control parameter sets exceeds the corresponding control parameter value range.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Among the above-mentioned technical scheme, avoid adopting the densimeter when directly obtaining the thick liquid density among the correlation technique to lead to the inaccurate problem of measuring result because of wearing and tearing easily, and adopt the target control parameter value that stable measurement that is relevant with the thick liquid density obtained to obtain the thick liquid density, reduced the cost that the densimeter regularly changed the maintenance, improved the accuracy of thick liquid density result, be favorable to improving the effect of flue gas desulfurization.
Fig. 7 is a block diagram illustrating an electronic device 700 in accordance with an example embodiment. As shown in fig. 7, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.
The processor 701 is configured to control the overall operation of the electronic device 700, so as to complete all or part of the steps in the above-mentioned slurry density obtaining method. The memory 702 is used to store various types of data to support operation at the electronic device 700, such as instructions for any application or method operating on the electronic device 700 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and the like. The Memory 702 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia components 703 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 702 or transmitted through the communication component 705. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, which is not limited herein. The corresponding communication component 705 may thus include: Wi-Fi module, Bluetooth module, NFC module, etc.
In another exemplary embodiment, there is also provided a non-transitory computer readable storage medium including program instructions which, when executed by a processor, implement the steps of the above-described slurry density acquisition method. For example, the computer readable storage medium may be the memory 702 described above including program instructions that are executable by the processor 701 of the electronic device 700 to perform the method of obtaining the slurry density described above.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (12)
1. A method for obtaining the density of a slurry, the method comprising:
training according to a preset training sample through a whale optimization algorithm to obtain a density measurement model, wherein elements of population members of the whale optimization algorithm are model parameters of the density measurement model, an initial element value of each element of the population members in the whale optimization algorithm is obtained through Logistic chaotic mapping, the preset training sample comprises training control parameter values of a plurality of training control parameter groups and training output parameter values of corresponding training output parameters, each training control parameter group comprises a plurality of training control parameters, and the training output parameters comprise the density of the slurry;
acquiring a target control parameter value of a target control parameter for generating limestone slurry;
and inputting the target control parameter value into the density measurement model to obtain the slurry density of the limestone slurry output by the density measurement model.
2. The method of claim 1, wherein the density measurement model is a neural network model, and the training of the density measurement model by a whale optimization algorithm according to the preset training samples comprises:
determining whale optimization algorithm parameters of the whale optimization algorithm according to model parameters of a preset neural network model, wherein the whale optimization algorithm parameters comprise elements of the population members, preset element value threshold values of each element value and whale population scale;
obtaining the current element value of each population member of the whale optimization algorithm through Logistic chaotic mapping according to the whale optimization algorithm parameters and preset chaotic mapping parameters, wherein the chaotic mapping parameters comprise chaotic mapping coefficients;
and obtaining target model parameter values of the preset neural network model by using the whale optimization algorithm according to the whale optimization algorithm parameters, the current element values of each population member and the preset training samples, and taking the obtained target neural network model as the density measurement model.
3. The method of claim 2, wherein determining whale optimization algorithm parameters of the whale optimization algorithm according to model parameters of a preset neural network model comprises:
taking the training control parameter as an input node of the preset neural network model, taking the slurry density as an output node of the preset neural network model, determining a model parameter of the preset neural network model according to the input node, the output node and a hidden neuron of the preset neural network model, and taking the model parameter as an element of the population member, wherein the model parameter comprises a first connection weight, a first threshold of the hidden neuron, a second connection weight and a second threshold of the output node, the first connection weight represents a weight between the input node and the hidden neuron, and the second connection weight represents a weight between the hidden neuron and the output node;
determining the element value range of each element according to a preset model parameter value range of each model parameter;
and determining the whale population scale according to the number of the model parameter values and the expected time of model training.
4. The method according to claim 2, wherein the obtaining target model parameter values of the preset neural network model by the whale optimization algorithm according to the whale optimization algorithm parameters, the current element values of each population member and preset training samples, and the using the obtained target neural network model as the density measurement model comprises:
acquiring a fitness value of each population member according to the preset training sample, wherein the fitness value is a mean square error between a prediction output parameter value and the corresponding training output parameter value, and the prediction output parameter value is acquired through a preset neural network model according to the training control parameter value of each training control parameter group and the current element value of the population member;
obtaining target element values of target population members of the population according to the fitness value of each population member, wherein the target population members are population members with the minimum fitness value in the population;
and adopting the whale optimization algorithm according to the whale optimization algorithm parameters to complete surrounding, predation and searching of the target element value so as to update the current element value of each population member, repeating the steps of obtaining the fitness value of each population member according to the preset training sample and obtaining the target element value of the target population member of the population according to the fitness value of each population member, so that the optimal element value corresponding to the optimal population member with the minimum fitness value in the population is obtained when a preset finishing condition is met, taking the optimal element value as the target model parameter value of the preset neural network model, and taking the obtained target neural network model as the density measurement model.
5. The method according to claim 4, wherein the preset end condition includes that the fitness value corresponding to the optimal population member is less than or equal to a preset fitness value threshold, and/or the training times are greater than or equal to a preset training time threshold.
6. The method according to any one of claims 1 to 5, further comprising:
obtaining multiple sets of historical data of the limestone slurry, wherein the historical data comprises alternative control parameter values of multiple alternative control parameter sets and corresponding output parameter values of an output parameter, each alternative control parameter set comprises multiple alternative control parameters of the limestone slurry, and the output parameter comprises the slurry density;
determining the target control parameter from the multiple candidate control parameters by adopting a grey correlation method according to the multiple groups of historical data;
and acquiring the preset training samples from the multiple groups of historical data according to the target control parameters.
7. The method of claim 6, wherein determining the target control parameter from the plurality of candidate control parameters using a gray correlation method according to the plurality of sets of historical data comprises:
acquiring the grey correlation degree of the alternative control parameter value of each alternative control parameter and the corresponding output parameter value according to the historical data;
and determining the target control parameter from the multiple candidate control parameters according to the gray correlation degree and a preset gray correlation degree threshold, wherein the gray correlation degree of the target control parameter is greater than or equal to the preset gray correlation degree threshold.
8. The method of claim 6, further comprising:
after acquiring multiple sets of historical data of the limestone slurry, deleting abnormal historical data from the multiple sets of historical data according to multiple preset control parameter value ranges, wherein the abnormal historical data represents that an alternative control parameter value of any alternative control parameter in the alternative control parameter sets exceeds the corresponding control parameter value range.
9. The method according to any one of claims 1 to 5, wherein the target and training control parameters include cyclone station inlet pressure, instantaneous feed volume, dilution water instantaneous flow volume, and grinding water instantaneous flow volume.
10. An apparatus for obtaining the density of a slurry, the apparatus comprising:
the model training module is configured to obtain a density measurement model through whale optimization algorithm training according to a preset training sample, wherein elements of population members of the whale optimization algorithm are model parameters of the density measurement model, an initial element value of each population member of the whale optimization algorithm is obtained through Logistic chaotic mapping, the preset training sample comprises training control parameter values of a plurality of training control parameter groups and training output parameter values of corresponding training output parameters, each training control parameter group comprises a plurality of training control parameters, and the training output parameters comprise the slurry density;
a parameter acquisition module configured to acquire a target control parameter value of a target control parameter for generating the limestone slurry;
and the result acquisition module is configured to input the target control parameter value into a pre-trained density measurement model so as to obtain the slurry density of the limestone slurry output by the density measurement model.
11. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-9.
12. A non-transitory computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210557059.5A CN115060625A (en) | 2022-05-20 | 2022-05-20 | Method and device for obtaining slurry density, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210557059.5A CN115060625A (en) | 2022-05-20 | 2022-05-20 | Method and device for obtaining slurry density, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115060625A true CN115060625A (en) | 2022-09-16 |
Family
ID=83198492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210557059.5A Pending CN115060625A (en) | 2022-05-20 | 2022-05-20 | Method and device for obtaining slurry density, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115060625A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116440670A (en) * | 2023-04-12 | 2023-07-18 | 华能伊春热电有限公司 | Limestone slurry density stability control method |
| CN117517623A (en) * | 2024-01-05 | 2024-02-06 | 上海久澄环境工程有限公司 | Intelligent control system of soil gas probe and soil gas automatic sampling method |
-
2022
- 2022-05-20 CN CN202210557059.5A patent/CN115060625A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116440670A (en) * | 2023-04-12 | 2023-07-18 | 华能伊春热电有限公司 | Limestone slurry density stability control method |
| CN116440670B (en) * | 2023-04-12 | 2023-10-31 | 华能伊春热电有限公司 | Limestone slurry density stability control method |
| CN117517623A (en) * | 2024-01-05 | 2024-02-06 | 上海久澄环境工程有限公司 | Intelligent control system of soil gas probe and soil gas automatic sampling method |
| CN117517623B (en) * | 2024-01-05 | 2024-03-15 | 上海久澄环境工程有限公司 | Intelligent control system of soil gas probe and soil gas automatic sampling method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110427654B (en) | Landslide prediction model construction method and system based on sensitive state | |
| CN115060625A (en) | Method and device for obtaining slurry density, electronic equipment and storage medium | |
| CN108230049A (en) | The Forecasting Methodology and system of order | |
| CN109145464B (en) | Structural damage identification method integrating multi-target ant lion optimization and trace sparse regularization | |
| CN109919356B (en) | BP neural network-based interval water demand prediction method | |
| CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
| CN115271186B (en) | Reservoir water level prediction and early warning method based on delay factor and PSO RNN Attention model | |
| CN110781595B (en) | Method, device, terminal and medium for predicting energy use efficiency (PUE) | |
| CN113393057A (en) | Wheat yield integrated prediction method based on deep fusion machine learning model | |
| CN112307536B (en) | Dam seepage parameter inversion method | |
| CN112686481A (en) | Runoff forecasting method and processor | |
| CN115935834A (en) | History fitting method based on deep autoregressive network and continuous learning strategy | |
| CN114548509A (en) | Multi-type load joint prediction method and system for multi-energy system | |
| CN114912673A (en) | Water level prediction method based on whale optimization algorithm and long-term and short-term memory network | |
| CN116451556A (en) | Construction method of concrete dam deformation observed quantity statistical model | |
| CN111311001B (en) | Bi-LSTM network short-term load prediction method based on DBSCAN algorithm and feature selection | |
| US20240095535A1 (en) | Executing a genetic algorithm on a low-power controller | |
| CN112836789A (en) | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm | |
| CN113268929B (en) | Short-term load interval prediction method and device | |
| CN113283576B (en) | Spectrum sensing method for optimizing LSTM (least squares) based on whale algorithm | |
| CN116960962A (en) | Mid-long term area load prediction method for cross-area data fusion | |
| CN117371608A (en) | Pig house multi-point temperature and humidity prediction method and system based on deep learning | |
| CN113159395A (en) | Deep learning-based sewage treatment plant water inflow prediction method and system | |
| CN117291069A (en) | LSTM sewage water quality prediction method based on improved DE and attention mechanism | |
| CN109187898B (en) | Soft measurement method and device for ammonia nitrogen content of water in aquaculture environment |
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 |