CN107664680B - Self-adaptive acquisition method and device of water quality soft measurement model - Google Patents
Self-adaptive acquisition method and device of water quality soft measurement model Download PDFInfo
- Publication number
- CN107664680B CN107664680B CN201610601948.1A CN201610601948A CN107664680B CN 107664680 B CN107664680 B CN 107664680B CN 201610601948 A CN201610601948 A CN 201610601948A CN 107664680 B CN107664680 B CN 107664680B
- Authority
- CN
- China
- Prior art keywords
- soft measurement
- measurement model
- water quality
- characteristic information
- model
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The embodiment of the invention relates to the field of measurement, and discloses a self-adaptive acquisition method and device of a water quality soft measurement model. The invention discloses a self-adaptive acquisition method of a water quality soft measurement model, which comprises the following steps: pre-storing a plurality of water quality soft measurement models to form a water quality soft measurement model library, and adding characteristic information for each water quality soft measurement model; receiving characteristic information of a model to be selected; matching the soft measurement model from the water quality soft measurement model library according to the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model by using the received characteristic information; testing the soft measurement model, and adjusting parameters of the soft measurement model when the testing accuracy does not exceed a preset value until the testing accuracy reaches the preset value; and taking the soft measurement model with the tested accuracy reaching the preset value as a self-adaptive acquired water quality soft measurement model. The invention discloses a self-adaptive acquisition device of a water quality soft measurement model. The embodiment of the invention accelerates the generation speed of the soft measurement model and reduces the cost.
Description
Technical Field
The invention relates to the technical field of measurement, in particular to a self-adaptive acquisition technology of a water quality soft measurement model.
Background
The importance of water is indispensably described in all the natural elements that maintain human survival, guarantee economic construction and maintain social development. At present, with the development of industry, the increase of population, the increase of urbanization and the increase of the usage amount of fertilizers and pesticides, water as a life source is seriously polluted. The water pollution reduces the use function of the water body and aggravates the shortage of water resources; water pollution seriously damages the ecological environment and influences human survival. Moreover, water drunk by people usually can be polluted in various aspects, so that the detection of the water quality is gradually paid attention to by people.
With the emphasis of the country on the industry, the scale of the water quality monitoring industry is continuously enlarged, wherein the number of water quality monitoring equipment production enterprises is rapidly increased, and when the water quality needs to be measured in the prior art, a new water quality soft measurement model needs to be generated firstly, which needs to consume huge funds. In generating a new water quality soft measurement model, a large amount of historical data is also required, and a new measurement model is generated through training of the historical data. In this case, the historical data needs to be directly acquired by devices such as sensors and accumulated for a long time, which results in time consumption.
Disclosure of Invention
The invention aims to provide a self-adaptive acquisition method and a self-adaptive acquisition device for a water quality soft measurement model, which are used for accelerating the generation speed of the soft measurement model and reducing the cost.
In order to solve the technical problem, an embodiment of the present invention provides a method for adaptively acquiring a water quality soft measurement model, including:
pre-storing a plurality of water quality soft measurement models to form a water quality soft measurement model library, and adding characteristic information for each water quality soft measurement model;
receiving characteristic information of a model to be selected;
matching a first soft measurement model from a water quality soft measurement model library by using the received characteristic information according to the similarity of the received characteristic information and the characteristic information of each water quality soft measurement model;
testing the first soft measurement model, and adjusting parameters of the first soft measurement model when the tested accuracy does not exceed a preset value until the tested accuracy reaches the preset value;
and taking the first soft measurement model with the tested accuracy reaching the preset value as a self-adaptively obtained water quality soft measurement model.
The embodiment of the invention also provides a self-adaptive acquisition device of the water quality soft measurement model, which comprises:
the storage module is used for prestoring a plurality of water quality soft measurement models to form a water quality soft measurement model library and adding characteristic information to each water quality soft measurement model;
the communication module is used for receiving the characteristic information of the model to be selected;
the processing module is used for matching a first soft measurement model from the water quality soft measurement model library according to the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model by using the received characteristic information;
the testing module is used for testing the first soft measurement model, and adjusting parameters of the first soft measurement model when the tested accuracy does not exceed a preset value until the tested accuracy reaches the preset value;
and the output module is used for taking the first soft measurement model with the tested accuracy reaching the preset value as the self-adaptively acquired water quality soft measurement model.
Compared with the prior art, the method and the device have the advantages that the closest first soft measurement model is found by utilizing the similarity matching of the existing water quality soft measurement model and the received water quality soft measurement model, and the local parameter adaptability adjustment is carried out by utilizing continuous testing, so that the soft measurement model conforming to the water quality to be measured is quickly obtained, the generation speed of the water quality soft measurement model is greatly increased, the new water quality soft measurement model is prevented from being generated again, and the generation cost of the model is reduced.
In addition, still include: and storing the water quality soft measurement model obtained in a self-adaptive manner into a water quality soft measurement model library. The water quality soft measurement model base is continuously updated, the number of the water quality soft measurement models can be expanded, so that the water quality soft measurement models which are matched with the model to be selected with high accuracy can be found more easily, and the possibility of finding the model to be selected which is more accordant is improved.
In addition, the characteristic information is set according to the application environment of the water quality soft measurement model; and determining the similarity of the received characteristic information and the characteristic information of each water quality soft measurement model according to the similarity of the application environments of the model to be selected and the water quality soft measurement model. Because the application environments are similar, the models to be tested are more similar, and therefore the more similar models to be tested can be found by comparing the similarity of the application environments.
In addition, the application environment includes one or any combination of the following: the water quality index to be measured, the water treatment process adopted by the water to be measured and the geographical position of the water to be measured. Different parameters are used as application environments, so that the selection is more diversified, the similarity determination of different angles is realized, and the larger deviation of the comparison result caused by different application environments is prevented.
In addition, if the application environment includes: and determining the similarity of the water treatment process adopted by the water to be detected according to the process correlation. The method limits how to obtain the process similarity, so that the process similarity judgment basis is clearer.
In addition, in the test of the first soft measurement model, the method specifically includes: sampling in a water environment measured by a model to be selected; and testing the first soft measurement model by using the collected water sample. The sampling samples are tested, online real-time measurement can be avoided, an offline measurement mode is adopted instead, equipment required by online measurement is avoided as much as possible, and the testing cost is further reduced.
In addition, if the number of the matched first soft measurement models is greater than 1, the step of testing the first soft measurement models and adjusting the parameters of the first soft measurement models according to the test result specifically includes: and selecting the first soft measurement model with the highest accuracy according to the test result, and adjusting the parameters of the first soft measurement model. More than one first soft measurement model is allowed to be matched, so that the first soft measurement model with the highest accuracy can be selected from the first soft measurement models and the parameters of the first soft measurement model can be adjusted.
Drawings
Fig. 1 is a flowchart of an adaptive acquisition method of a water quality soft measurement model according to a first embodiment of the invention;
fig. 2 is a flowchart of an adaptive acquisition method of a water quality soft measurement model according to a fourth embodiment of the invention;
fig. 3 is a schematic structural diagram of an adaptive acquisition device of a water quality soft measurement model according to a fifth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to an adaptive acquisition method of a water quality soft measurement model. The flow is shown in fig. 1, and specifically comprises the following steps:
step 101: and pre-storing a plurality of water quality soft measurement models, and adding characteristic information.
Specifically, a plurality of water quality soft measurement models are prestored to form a water quality soft measurement model library, and characteristic information is added to each water quality soft measurement model. A plurality of water quality soft measurement models are prestored, can be obtained from water quality soft measurement models frequently used in the prior art, and are prestored in a water quality soft measurement model library. Meanwhile, characteristic information needs to be added to each water quality soft measurement model added into the water quality soft measurement model library, the characteristic information can be set according to the structural characteristics of the water quality soft measurement model or information such as a water treatment process to be measured, and the characteristic information of each water quality soft measurement model can be different.
It should be noted that the characteristic information of each water quality soft measurement model can be set according to various parameters, and is not described herein any more.
Step 102: and receiving characteristic information of the model to be selected.
Specifically, each water quality soft measurement model prestored in the water quality soft measurement model library is an existing water quality soft measurement model, and when the water environment needs to be measured, the characteristic information of the model to be measured is received.
Step 103: and matching a first soft measurement model from the water quality soft measurement model library.
Specifically, the received characteristic information is used for matching a first soft measurement model from the water quality soft measurement model base according to the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model. In step 102, the characteristic information of the model to be measured is received, a pre-stored water quality soft measurement model with high similarity to the received characteristic information is found in the water quality soft measurement model base, and the pre-stored water quality soft measurement model is used as a first soft measurement model.
Step 104: and judging whether the accuracy of the first soft measurement model reaches a preset value.
Specifically, the first soft measurement model obtained in step 103 is tested, and when the tested accuracy does not exceed a preset value, the procedure goes to step 105, otherwise, the procedure goes to step 106. The preset value in this embodiment may be a value preset by a user. In this step, the accuracy of the first soft measurement model may also be set to a value, for example, if the accuracy of the first soft measurement model is 4, which may represent that the accuracy of the first soft measurement model is low, it is only necessary to determine whether the value 4 reaches a preset value.
Step 105: and adjusting the parameters of the first soft measurement model.
Specifically, if the accuracy of the first soft measurement model does not reach the preset value, the parameters of the first soft measurement model are adjusted, and the first soft measurement model after the parameters are adjusted enters step 104 again to perform judgment until the tested accuracy reaches the preset value.
Step 106: and storing the water quality soft measurement model obtained in a self-adaptive manner into a water quality soft measurement model library.
Specifically, the first soft measurement model with the tested accuracy reaching the preset value is used as the water quality soft measurement model obtained in a self-adaptive mode. In step 104, the accuracy of the first soft measurement model determined reaches a preset value, and the model acquired at this time is used as a self-adaptively acquired water quality soft measurement model. At the moment, the water quality soft measurement model which best accords with the water quality to be measured is obtained and can be actually used for measuring the water quality to be measured.
In addition, the water quality soft measurement model acquired in a self-adaptive mode is stored in a water quality soft measurement model base. Therefore, the number of the water quality soft measurement models is expanded, when the water quality is detected for the new time, the water quality soft measurement models which are matched with the model to be selected with high accuracy can be found more easily, and the possibility of finding the model to be selected which is more accordant is improved.
Compared with the prior art, the present embodiment has the main differences and effects that: the method comprises the steps of utilizing similarity matching of an existing water quality soft measurement model and a received water quality soft measurement model to find out the closest first soft measurement model, utilizing continuous testing to carry out adaptive adjustment on local parameters, and further rapidly obtaining the soft measurement model which accords with the water quality to be measured, thereby greatly accelerating the generation speed of the water quality soft measurement model, further avoiding the regeneration of a new water quality soft measurement model, and reducing the generation cost of the model.
The second embodiment of the invention relates to an adaptive acquisition method of a water quality soft measurement model. The second embodiment is substantially the same as the first embodiment, and mainly differs therefrom in that: in the second embodiment of the present invention, the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model is determined according to the similarity between the application environments of the model to be selected and the water quality soft measurement model, and since the application environments are similar, the models to be measured are more similar, and therefore, the more similar models to be measured can be found by comparing the similarities between the application environments.
Setting characteristic information according to the application environment of the water quality soft measurement model; and determining the similarity of the received characteristic information and the characteristic information of each water quality soft measurement model according to the similarity of the application environments of the model to be selected and the water quality soft measurement model.
Specifically, when the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model is compared, the similarity can be determined according to the similarity between the application environments of the model to be selected and the water quality soft measurement model.
Wherein, the application environment comprises one or any combination of the water quality index to be measured, the water treatment process adopted by the water to be measured, and the geographical position of the water to be measured. For example, the similarity of the water quality indexes of the candidate model and the water quality soft measurement model can be compared to determine whether the received characteristic information is consistent with the characteristic information of each water quality soft measurement model. Therefore, different parameters can be used as application environments, so that the selection is more diversified, the similarity determination at different angles is realized, and the larger deviation of the comparison result caused by different application environments is prevented.
It is worth mentioning that if the application environment includes: and determining the similarity of the water treatment process adopted by the water to be detected according to the process correlation. And if the application environment comprises a water treatment process, determining the process similarity according to the process correlation. The limitation on how to obtain the process similarity ensures that the process similarity judgment basis is clearer
Compared with the prior art, the present embodiment has the main differences and effects that: the similarity of the received characteristic information and the characteristic information of each water quality soft measurement model is determined according to the similarity of the application environments of the model to be selected and the water quality soft measurement model, the models to be tested are more similar due to the similarity of the application environments, and the more similar models to be tested can be found by comparing the similarity of the application environments.
The third embodiment of the invention relates to a self-adaptive acquisition method of a water quality soft measurement model. The third embodiment is substantially the same as the first embodiment, and mainly differs therefrom in that: in the third embodiment of the present invention, the first soft measurement model samples in the water environment measured by the model to be selected, the first soft measurement model is tested by using the sampled water sample, and the sampled sample is tested, so that the online real-time measurement can be avoided.
In the test of the first soft measurement model, the method specifically includes: sampling in a water environment measured by a model to be selected; and testing the first soft measurement model by using the collected water sample. When the first soft measurement model is tested, only sampling is needed in the water environment measured by the model to be selected, and the sampled water sample can be measured at any place and any time, and the online real-time data measurement is not needed, but the offline measurement is carried out, so that equipment used in the online real-time data measurement is reduced, and the effect of reducing the test cost can be achieved.
Compared with the prior art, the present embodiment has the main differences and effects that: the first soft measurement model is used for sampling in the water environment measured by the model to be selected, the first soft measurement model is tested by using a sampled water sample, the sampled sample is tested, online real-time measurement can be avoided, an offline measurement mode is used instead, equipment required by online measurement is avoided as much as possible, and the test cost is further reduced.
The fourth embodiment of the invention relates to an adaptive acquisition method of a water quality soft measurement model. The fourth embodiment is substantially the same as the first embodiment, and mainly differs therefrom in that: in the fourth embodiment of the present invention, if the number of the matched first soft measurement models is greater than 1, the first soft measurement model with the highest accuracy is selected according to the test result, and the parameters of the first soft measurement model are adjusted so as to allow more than one number of the matched first soft measurement models, so that one first soft measurement model with the highest accuracy can be selected from the first soft measurement models and the parameters of the first soft measurement model are adjusted.
A flow chart of a method for adaptively acquiring a water quality soft measurement model according to a fourth embodiment is shown in fig. 2.
Since steps 201 to 202 are completely consistent with steps 101 to 102, and steps 206 to 208 are completely consistent with steps 104 to 106, detailed description thereof is omitted.
Step 203: and matching a first soft measurement model from the water quality soft measurement model library.
Specifically, in this embodiment, all the first soft measurement models whose similarity of the feature information is greater than the preset percentage may be selected, and the number of the first soft measurement models matched in step 203 may be greater than 1.
Step 204: and judging whether the number of the matched first soft measurement models is more than 1.
Specifically, if the number of the matched first soft measurement models is greater than 1, step 205 is entered, otherwise, step 206 is entered. The number of the matched first soft measurement models may be multiple, and when the number is greater than 1, there may be more choices, and then step 205 is entered for further operation.
It should be noted that, in the present embodiment, when performing matching, the first 5 soft measurement models with the highest similarity of the feature information may be defined as the first soft measurement models, and then a plurality of first soft measurement models may also be matched.
It should be noted that, in practical applications, the selection may be performed according to the first 6 or 7 first soft measurement models with the highest similarity of the feature information, where the number of the models with the highest similarity may be set by a user. In addition, in all the first soft measurement models in which the similarity of the selected feature information is greater than a preset percentage, the preset percentage may also be determined by the user, for example, 95%, 98%, and the like. And if the values set by the user are different, the number of the matched first soft measurement models meeting the conditions is more than or equal to 1.
Step 205: and acquiring a first soft measurement model with the highest accuracy.
Specifically, if the number of the matched first soft measurement models is greater than 1, the first soft measurement model with the highest accuracy is selected according to the test result. The first soft measurement model with the highest accuracy is used as the further adjusted soft measurement model and the process continues to step 206.
Compared with the prior art, the present embodiment has the main differences and effects that: if the number of the matched first soft measurement models is more than 1, selecting the first soft measurement model with the highest accuracy according to the test result, and adjusting the parameters of the first soft measurement model, so that more than one first soft measurement models are allowed to be matched, and one first soft measurement model with the highest accuracy can be selected from the first soft measurement models and the parameters of the first soft measurement model are adjusted.
The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the steps contain the same logical relationship, which is within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.
A fifth embodiment of the present invention relates to an adaptive acquisition apparatus for a water quality soft measurement model, as shown in fig. 3, including:
and the storage module 31 is used for prestoring a plurality of water quality soft measurement models to form a water quality soft measurement model library and adding characteristic information for each water quality soft measurement model.
And the communication module 32 is used for receiving the characteristic information of the model to be selected.
And the processing module 33 is configured to match the first soft measurement model from the water quality soft measurement model library according to the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model by using the received characteristic information.
And the testing module 34 is configured to test the first soft measurement model, and adjust parameters of the first soft measurement model when the tested accuracy does not exceed a preset value until the tested accuracy reaches the preset value.
And the output module 35 is configured to use the first soft measurement model with the tested accuracy reaching the preset value as the adaptively acquired water quality soft measurement model.
The storage module 31 is further configured to store the adaptively obtained water quality soft measurement model in a water quality soft measurement model library.
Compared with the prior art, the present embodiment has the main differences and effects that: the method comprises the steps of utilizing similarity matching of an existing water quality soft measurement model and a received water quality soft measurement model to find out the closest first soft measurement model, utilizing continuous testing to carry out adaptive adjustment on local parameters, and further rapidly obtaining the soft measurement model which accords with the water quality to be measured, thereby greatly accelerating the generation speed of the water quality soft measurement model, further avoiding the regeneration of a new water quality soft measurement model, and reducing the generation cost of the model.
It should be understood that this embodiment is a system example corresponding to the first embodiment, and may be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that each module referred to in this embodiment is a logical module, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that other elements are not present in the present embodiment.
The sixth embodiment of the present invention relates to an adaptive acquisition device for a water quality soft measurement model. The sixth embodiment is substantially the same as the fifth embodiment, and mainly differs therefrom in that: in the sixth embodiment of the present invention, the characteristic information is set according to the application environment of the water quality soft measurement model, and the models to be measured are more similar due to similar application environments, so that a more similar model to be measured can be found by comparing the similarity of the application environments.
Setting characteristic information according to the application environment of the water quality soft measurement model; and determining the similarity of the received characteristic information and the characteristic information of each water quality soft measurement model according to the similarity of the application environments of the model to be selected and the water quality soft measurement model.
Compared with the prior art, the present embodiment has the main differences and effects that: the characteristic information is set according to the application environment of the water quality soft measurement model, and the models to be measured are more similar due to the similar application environments, so that the more similar models to be measured can be found by comparing the similarity of the application environments.
Since the second embodiment corresponds to the present embodiment, the present embodiment can be implemented in cooperation with the second embodiment. The related technical details mentioned in the second embodiment are still valid in this embodiment, and the technical effects that can be achieved in the second embodiment can also be achieved in this embodiment, and are not described herein again in order to reduce the repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the second embodiment.
Those skilled in the art can understand that all or part of the steps in the method of the foregoing embodiments may be implemented by a program to instruct related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (4)
1. A self-adaptive acquisition method of a water quality soft measurement model is characterized by comprising the following steps:
pre-storing a plurality of existing water quality soft measurement models to form a water quality soft measurement model library, and adding characteristic information for each water quality soft measurement model, wherein the characteristic information is set according to the application environment of the water quality soft measurement model, and the application environment comprises one of the following or any combination thereof: the water quality index to be detected, the water treatment process adopted by the water to be detected and the geographical position of the water to be detected;
receiving characteristic information of a model to be selected;
matching a first soft measurement model from the water quality soft measurement model library by using the received characteristic information according to the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model, wherein the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model is determined according to the similarity between the model to be selected and the application environment of the water quality soft measurement model;
sampling in the water environment measured by the model to be selected, testing the first soft measurement model by using the sampled water sample, and adjusting parameters of the first soft measurement model when the tested accuracy does not exceed a preset value until the tested accuracy reaches the preset value;
and taking the first soft measurement model with the tested accuracy reaching the preset value as a water quality soft measurement model obtained in a self-adaptive mode, and storing the water quality soft measurement model obtained in the self-adaptive mode into the water quality soft measurement model base.
2. The adaptive acquisition method of the water quality soft measurement model according to claim 1, wherein if the application environment includes: and determining the similarity of the water treatment process adopted by the water to be detected according to the process correlation.
3. The adaptive acquisition method of a water quality soft measurement model according to claim 1, wherein if the number of the matched first soft measurement models is greater than 1, the step of testing the first soft measurement model and adjusting the parameters of the first soft measurement model according to the test result specifically comprises:
and selecting the first soft measurement model with the highest accuracy according to the test result, and adjusting the parameters of the first soft measurement model.
4. An adaptive acquisition device of a water quality soft measurement model is characterized by comprising:
the storage module is used for prestoring a plurality of existing water quality soft measurement models to form a water quality soft measurement model library and adding characteristic information to each water quality soft measurement model;
the communication module is used for receiving characteristic information of a model to be selected, the characteristic information is set according to an application environment of the water quality soft measurement model, and the application environment comprises one of the following or any combination thereof: the water quality index to be detected, the water treatment process adopted by the water to be detected and the geographical position of the water to be detected;
the processing module is used for matching a first soft measurement model from the water quality soft measurement model library according to the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model by using the received characteristic information, wherein the similarity between the received characteristic information and the characteristic information of each water quality soft measurement model is determined according to the similarity between the application environments of the model to be selected and the water quality soft measurement model;
the test module is used for sampling in the water environment measured by the model to be selected, testing the first soft measurement model by using the sampled water sample, and adjusting parameters of the first soft measurement model when the tested accuracy does not exceed a preset value until the tested accuracy reaches the preset value;
and the output module is used for taking the first soft measurement model with the tested accuracy reaching the preset value as a water quality soft measurement model obtained in a self-adaptive mode and storing the water quality soft measurement model obtained in the self-adaptive mode into the water quality soft measurement model base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610601948.1A CN107664680B (en) | 2016-07-27 | 2016-07-27 | Self-adaptive acquisition method and device of water quality soft measurement model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610601948.1A CN107664680B (en) | 2016-07-27 | 2016-07-27 | Self-adaptive acquisition method and device of water quality soft measurement model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107664680A CN107664680A (en) | 2018-02-06 |
| CN107664680B true CN107664680B (en) | 2020-08-14 |
Family
ID=61115291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610601948.1A Active CN107664680B (en) | 2016-07-27 | 2016-07-27 | Self-adaptive acquisition method and device of water quality soft measurement model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107664680B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109187534A (en) * | 2018-08-01 | 2019-01-11 | 江苏凯纳水处理技术有限公司 | Water quality detection method and its water sample pattern recognition device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318325A (en) * | 2014-10-14 | 2015-01-28 | 广东省环境监测中心 | Multi-basin real-time intelligent water quality predication method and system |
| CN105550492A (en) * | 2014-10-23 | 2016-05-04 | 胜科工业有限公司 | System and method for predicting parameter of wastewater treatment process |
| CN105630656A (en) * | 2014-11-06 | 2016-06-01 | 阿里巴巴集团控股有限公司 | Log model based system robustness analysis method and apparatus |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI413006B (en) * | 2010-06-01 | 2013-10-21 | Nat Univ Tsing Hua | Method for buliding adaptive soft sensor |
| CN103810309B (en) * | 2012-11-08 | 2016-08-17 | 连晓峰 | A based on bounding theory2the soft-measuring modeling method of O urban sewage treatment process |
| CN103295165A (en) * | 2013-06-26 | 2013-09-11 | 上海铂尔怡环境技术股份有限公司 | Water quality environmental quality assessment pre-warning system and method |
| CN105205224B (en) * | 2015-08-28 | 2018-10-30 | 江南大学 | Time difference Gaussian process based on fuzzy curve analysis returns soft-measuring modeling method |
-
2016
- 2016-07-27 CN CN201610601948.1A patent/CN107664680B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318325A (en) * | 2014-10-14 | 2015-01-28 | 广东省环境监测中心 | Multi-basin real-time intelligent water quality predication method and system |
| CN105550492A (en) * | 2014-10-23 | 2016-05-04 | 胜科工业有限公司 | System and method for predicting parameter of wastewater treatment process |
| CN105630656A (en) * | 2014-11-06 | 2016-06-01 | 阿里巴巴集团控股有限公司 | Log model based system robustness analysis method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107664680A (en) | 2018-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110275148B (en) | Sea clutter amplitude distribution parameter estimation method and system | |
| CN108876021B (en) | Medium-and-long-term runoff forecasting method and system | |
| CN111174370A (en) | Fault detection method and device, storage medium and electronic device | |
| KR20180114983A (en) | Apparatus and method for detecting anomaly behavior in plant pipe using multiple meta-learning | |
| CN112948937B (en) | Intelligent pre-judging method and device for concrete strength | |
| CN110890998A (en) | Method and device for determining threshold | |
| CN110231447A (en) | The method, apparatus and terminal device of water quality abnormality detection | |
| CN112418921A (en) | Power demand prediction method, device, system and computer storage medium | |
| CN105824783B (en) | A kind of parameter identification method of the nonlinear dampling system for the mixing ant colony algorithm looked for food based on bacterium | |
| CN115296984B (en) | Abnormal network node detection method and device, equipment and storage medium | |
| CN105954695B (en) | Synchronization-based homogeneous sensor mutation parameter identification method and device | |
| CN112990082A (en) | Detection and identification method of underwater sound pulse signal | |
| CN107664680B (en) | Self-adaptive acquisition method and device of water quality soft measurement model | |
| US20140052385A1 (en) | Method computer program and system to analyze mass spectra | |
| CN112949944A (en) | Underground water level intelligent prediction method and system based on space-time characteristics | |
| CN117192057A (en) | Water quality detection method, device and storage medium | |
| CN111353526A (en) | Image matching method and device and related equipment | |
| CN110929506A (en) | Junk information detection method, device and equipment and readable storage medium | |
| CN116629686A (en) | Method and device for evaluating enterprise energy consumption data | |
| CN115436342A (en) | Method and device for reducing LIBS detection uncertainty among multiple batches of samples | |
| CN114938339A (en) | Data processing method and related device | |
| CN112532562B (en) | Malicious data flow detection method and system for adversarial network | |
| CN114385468A (en) | Log analysis method, system and related components | |
| CN109945075B (en) | Method and device for detecting leakage degree of water supply pipeline | |
| CN106772306B (en) | A kind of detection method and server of object |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |