CN114065949B - Intelligent water quality prediction dosing system based on historical data - Google Patents
Intelligent water quality prediction dosing system based on historical data Download PDFInfo
- Publication number
- CN114065949B CN114065949B CN202210046072.4A CN202210046072A CN114065949B CN 114065949 B CN114065949 B CN 114065949B CN 202210046072 A CN202210046072 A CN 202210046072A CN 114065949 B CN114065949 B CN 114065949B
- Authority
- CN
- China
- Prior art keywords
- prediction model
- data
- residual chlorine
- optimized
- control end
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/58—Treatment of water, waste water, or sewage by removing specified dissolved compounds
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/05—Programmable logic controllers, e.g. simulating logic interconnections of signals according to ladder diagrams or function charts
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2101/00—Nature of the contaminant
- C02F2101/10—Inorganic compounds
- C02F2101/12—Halogens or halogen-containing compounds
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/005—Processes using a programmable logic controller [PLC]
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/02—Temperature
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/06—Controlling or monitoring parameters in water treatment pH
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/14—NH3-N
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2209/00—Controlling or monitoring parameters in water treatment
- C02F2209/22—O2
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Automation & Control Theory (AREA)
- Chemical & Material Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Hydrology & Water Resources (AREA)
- Water Supply & Treatment (AREA)
- Organic Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Treatment Of Water By Oxidation Or Reduction (AREA)
Abstract
The invention provides an intelligent water quality prediction dosing system based on historical data, which comprises: the system comprises a prediction model, an AI regressor, at least one optimized prediction model subunit, a comparator, a control end and a controller, wherein the prediction model is obtained by training according to historical water quality monitoring data and is used for judging the chlorine addition amount in real time, the AI regressor intelligently trains according to real-time related data of residual chlorine influence recorded in the period T time to obtain at least one optimized prediction model subunit, the comparator compares the optimized prediction model subunit obtained by training in the period T time with the optimized prediction model subunit obtained by training in the last period T time to obtain whether the difference is beyond a set deviation threshold value or not, analyzes whether the difference beyond the set deviation threshold value is a forward difference or not, sends the optimized prediction model subunit obtained by training in the period T time to the control end of the prediction model, and the control end updates the optimized prediction model subunit obtained by training in the period T time to the prediction model, to optimize the predictive model.
Description
Technical Field
The invention relates to the technical field of water treatment, in particular to an intelligent water quality prediction dosing system based on historical data.
Background
The residual chlorine in tap water is an important index in tap water, and the existing water works are usually equipped with an online residual chlorine detector to control the residual chlorine standard in water within the national standard, the industry standard or the internal control standard of the water works and adjust the residual chlorine standard according to the fluctuation range of the residual chlorine detector. Because the water quality of various water bodies is different, accurate measurement can not be carried out by using a formula, and the water quality can only be adjusted according to the operation experience of the whole year. Although the existing water plant is basically automatically controlled, the operator only needs to operate the chlorine adding dosage on a computer of a central control room. But still needs manual operation to throw chlorine amount and monitor emergencies and take corresponding measures. Therefore, how to automatically judge the chlorine dosage and effectively monitor abnormal data is the key point to be solved by the project.
Disclosure of Invention
In view of the above, the main object of the present invention is to provide an intelligent water quality prediction dosing system based on historical data.
The technical scheme adopted by the invention is as follows:
an intelligent water quality prediction dosing system based on historical data comprises:
acquiring historical water quality monitoring data;
calling a pre-established prediction model, wherein the prediction model is obtained by training according to historical water quality monitoring data, the prediction model is used for judging chlorine adding amount in real time, collecting residual chlorine data generated by the chlorine adding amount, and analyzing the residual chlorine data by using the prediction model to obtain residual chlorine influence and record real-time related data of the residual chlorine influence so as to judge whether the residual chlorine is in a safety range;
the AI regressor carries out intelligent training according to the real-time related data of the residual chlorine influence recorded in the period T time to obtain at least one optimized prediction model subunit,
and the comparator is used for comparing the optimized prediction model subunit obtained by the T time training in the period with the optimized prediction model subunit obtained by the T time training in the previous period to obtain whether the difference is beyond a set deviation threshold value or not, analyzing whether the difference beyond the set deviation threshold value is a positive difference or not, packing and sending the optimized prediction model subunit obtained by the T time training in the period to a control end of the prediction model if the difference is the positive difference, and updating the optimized prediction model subunit obtained by the T time training in the period to the prediction model by the control end to optimize the prediction model.
Preferably, the chlorine adding amount of the prediction model is analyzed and predicted, a predicted value is given to participate in the automatic adding, and the full-automatic adding is realized.
Preferably, the AI regressor is disposed in an AI server, the AI server has a communication module, the communication module is used for communicating with the prediction model control end, and the control end is a control module set in the PLC controller.
Preferably, the AI regressor has a configuration control end, and the configuration control end is used for increasing or decreasing according to related parameters which are not recorded in the emergency plan, or modifying the existing related parameters, so that the AI regressor has dynamic optimization properties.
Preferably, the residual chlorine data are collected through a monitoring device, the monitoring device inputs the collected residual chlorine data into a memory, the memory is in two-way communication with a PLC (programmable logic controller), and the PLC acquires the residual chlorine data and then packs the residual chlorine data to send the residual chlorine data to a communication module in the AI server.
Preferably, the method for analyzing and predicting the chlorine adding amount of the prediction model and giving a predicted value to participate in automatic adding comprises the following steps:
the prediction model is used for judging whether the residual chlorine is in a safety range, if the residual chlorine is not in the safety range, an alarm signal is sent to the PLC, a judgment module in the PLC judges that real-time related data influenced by the residual chlorine deviates from a set threshold unit amount, and the PLC controls the chlorination end to revise the chlorination amount according to the set unit amount according to the deviation from the set threshold unit amount.
Preferably, the set threshold is updated in accordance with optimization of the predictive model.
Preferably, the method for updating the set threshold value according to the optimization of the prediction model comprises:
after a control end of the PLC optimizes the prediction model, a monitoring device collects the post-residual chlorine data in a plurality of cycle times after the prediction model is optimized, the post-residual chlorine data is compared with the pre-residual chlorine data collected by the monitoring device before optimization to obtain the dynamic change of the optimized post-residual chlorine data relative to the pre-residual chlorine data, a judging module in the PLC judges whether the dynamic change has positive optimization relative to the pre-residual chlorine data, if so, the control end of the PLC updates the dynamic change to a set threshold value to optimize the set threshold value; if not, repeating the steps until the prediction model is optimized again in the next period T time.
Preferably, the emergency response plan is updated according to optimization of a prediction model.
Preferably, the method for updating the emergency plan according to the optimization of the prediction model comprises the following steps:
comparing the optimized prediction model subunit obtained by the T time training in the period with the optimized prediction model subunit obtained by the T time training in the previous period through a comparator to obtain whether the difference is beyond a set deviation threshold value or not, analyzing whether the difference beyond the set deviation threshold value is a forward difference or not, if not, analyzing whether the difference beyond the set deviation threshold value triggers a burst emergency plan or not, and if so, sending an alarm signal for triggering the burst emergency plan and starting the emergency plan; and after the emergency plan is implemented, studying and judging to analyze new factors appearing in the emergency plan, and simultaneously increasing and decreasing the unrecorded related parameters or modifying the existing related parameters through the configuration control end to optimize the emergency plan.
The intelligent dosing system judges the chlorine adding amount in real time through the prediction model, collects residual chlorine data generated by the chlorine adding amount, analyzes the residual chlorine data by using the prediction model to acquire residual chlorine influence and record real-time relevant data of the residual chlorine influence so as to judge whether the residual chlorine is in a safety range.
Meanwhile, the prediction model in the application can be optimized through an AI regressor, and the set threshold value and the emergency plan are optimized while the prediction model is optimized, so that the system is continuously optimized.
Drawings
The invention is illustrated and described only by way of example and not by way of limitation in the scope of the invention as set forth in the following drawings, in which:
FIG. 1 is a schematic block diagram of the system of the present invention;
FIG. 2 is a flow chart of the optimization of setting a threshold in the present invention;
fig. 3 is a flow chart of the optimization of the emergency plan in the present invention.
Detailed Description
In order to make the objects, technical solutions, design methods, and advantages of the present invention more apparent, the present invention will be further described in detail by specific embodiments with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 to 3, the present invention provides an intelligent water quality prediction dosing system based on historical data, comprising: acquiring historical water quality monitoring data;
calling a pre-established prediction model, wherein the prediction model is obtained by training according to historical water quality monitoring data, the prediction model is used for judging chlorine adding amount in real time, collecting residual chlorine data generated by the chlorine adding amount, and analyzing the residual chlorine data by using the prediction model to obtain residual chlorine influence and record real-time related data of the residual chlorine influence so as to judge whether the residual chlorine is in a safety range; and when the residual chlorine is not in the safety range, giving an alarm signal to prompt an operator to take manual or automatic mechanical correction action. The invention can monitor the residual chlorine, and the ammonia nitrogen and pH data are consistent with the residual chlorine, and can adopt the same mode, when the ammonia nitrogen and pH data are abnormal, an alarm signal is given to prompt an operator to take the manual or automatic mechanical correction action;
the AI regressor carries out intelligent training according to the real-time related data of the residual chlorine influence recorded in the period T time to obtain at least one optimized prediction model subunit,
and the comparator is used for comparing the optimized prediction model subunit obtained by the T time training in the period with the optimized prediction model subunit obtained by the T time training in the previous period to obtain whether the optimized prediction model subunit has a difference beyond a set deviation threshold value, analyzing whether the difference beyond the set deviation threshold value is a forward difference, packing and sending the optimized prediction model subunit obtained by the T time training in the period to a control end of the prediction model if the optimized prediction model subunit is the forward difference, updating the optimized prediction model subunit obtained by the T time training in the period to the prediction model by the control end to optimize the prediction model, analyzing whether the difference beyond the set deviation threshold value triggers an emergency plan if the optimized prediction model subunit is not the forward difference, and sending an alarm signal for triggering the emergency plan if the optimized prediction model subunit is not the forward difference, so that the emergency plan is started.
In the above, the method is not limited to the whole process of residual chlorine, such as the whole process of ammonia nitrogen, the whole process of turbidity, the whole process of pH, the whole process of dissolved oxygen, the water temperature in each stage, and other data which may affect the adding effect. Therefore, the AI regressor should have elasticity, allow the user to configure the increase and decrease of the relevant parameters, and the artificial intelligence trains the parameters capable of accepting the increase and decrease to find the correlation perfection model therein. Learning processes and results can be observed in the training process, and after the training is finished, the trained model can be automatically deployed to a local platform to optimize the original prediction model.
The design scheme of combining a traditional control system and an AI regressor is adopted: the data abnormality which is easy to monitor, such as ammonia nitrogen data abnormality, abnormality of other meter reading and the like, is planned to be monitored by adopting a traditional control system; and aiming at the chlorine dosage judgment with relatively complex data relation, an AI (artificial intelligence) regressor is adopted to continuously optimize the prediction model and then predict.
The AI regressor firstly matches monitoring data, such as ammonia nitrogen, residual chlorine and the like, with chlorine dosage for training, and the process is completely machine self-training without manual programming of strategies. In contrast, existing control algorithms can handle relatively few inputs, but traditional modeling approaches can be very difficult to control complex, data-dimensionally large inputs. This will save the period of project development by the AI regressor, and the fitted regressor can guarantee the accuracy of the prediction. In the process of continuously accumulating data, the AI regressor can still adjust the weights (influence) of different observation values, such as ammonia nitrogen, residual chlorine and pH value according to the continuously accumulated new observation value and chlorine input amount, so as to achieve the purpose of improving the prediction precision. The AI regressor can find different factors from complex data relations, for example, the relations between ammonia nitrogen, residual chlorine, pH and chlorine dosage before and after the biological filter can be expressed from the weight in the AI model.
In the above, the prediction model carries out analysis and prediction of chlorine addition amount, gives a given value of the predicted value participating in automatic feeding, and realizes full-automatic feeding, and the method comprises the following steps:
the prediction model is used for judging whether the residual chlorine is in a safety range, if the residual chlorine is not in the safety range, an alarm signal is sent to the PLC, a judgment module in the PLC judges that real-time related data influenced by the residual chlorine deviates from a set threshold unit amount, and the PLC controls the chlorination end to revise the chlorination amount according to the set unit amount according to the deviation from the set threshold unit amount.
In this application, chlorine residue data are gathered through monitoring devices, and this monitoring devices inputs the chlorine residue data of gathering to the memory, and this memory carries out two-way communication with the PLC controller, and the PLC controller is packed chlorine residue data after acquireing chlorine residue data and is sent to the communication module in the AI server. For information security, the whole set of system cannot be in contact with the external network, so that the data provides a data packaging mode, and the data package is provided to the AI server for training.
The AI regressor is arranged in an AI server, the AI server is provided with a communication module, the communication module is used for communicating with the control end of the prediction model, the control end is a control module set in the PLC controller, the AI regressor is provided with a configuration control end, the configuration control end is used for increasing or decreasing or modifying the existing relevant parameters according to the relevant parameters which are not recorded in the emergency plan, so that the AI regressor has dynamic optimization properties, and specifically, the configuration control end can modify the following parameters:
1) setting the necessary parameters for the system to operate.
2) Setting system parameters: alarm start delay, alarm duration, parameter setting and the like.
3) Remote connection and other communication connection settings: the connection function is opened and closed, and the address of the PLC controller and other related parameters are set.
4) Product library management setting: new product name creation, deletion, product parameter setting, learning step guidance, and the like.
5) And (3) data statistics setting: the statistics of the number of times of predicted feeding, the number of times of alarming and the proportion of alarming in the accumulated historical range are carried out, and a reset button (the password is required to be confirmed for resetting) is arranged.
6) Daily data storage management: the cleaning device can be checked on an operation interface, and can be set to be cleaned regularly or manually.
In the above, the set threshold is updated in accordance with optimization of the prediction model. The method comprises the following steps:
after a control end of the PLC optimizes the prediction model, a monitoring device collects the post-residual chlorine data in a plurality of cycle times after the prediction model is optimized, the post-residual chlorine data is compared with the pre-residual chlorine data collected by the monitoring device before optimization to obtain the dynamic change of the optimized post-residual chlorine data relative to the pre-residual chlorine data, a judging module in the PLC judges whether the dynamic change has positive optimization relative to the pre-residual chlorine data, if so, the control end of the PLC updates the dynamic change to a set threshold value to optimize the set threshold value; if not, repeating the steps until the prediction model is optimized again in the next period T time.
In the above, the emergency plan is updated according to optimization of the prediction model, and the method includes:
comparing the optimized prediction model subunit obtained by the T time training in the period with the optimized prediction model subunit obtained by the T time training in the previous period through a comparator to obtain whether the difference is beyond a set deviation threshold value or not, analyzing whether the difference beyond the set deviation threshold value is a forward difference or not, if not, analyzing whether the difference beyond the set deviation threshold value triggers a burst emergency plan or not, and if so, sending an alarm signal for triggering the burst emergency plan and starting the emergency plan; and after the emergency plan is implemented, studying and judging to analyze new factors appearing in the emergency plan, and simultaneously increasing and decreasing the unrecorded related parameters or modifying the existing related parameters through the configuration control end to optimize the emergency plan.
The intelligent dosing system judges the chlorine adding amount in real time through the prediction model, collects residual chlorine data generated by the chlorine adding amount, analyzes the residual chlorine data by using the prediction model to acquire residual chlorine influence and record real-time relevant data of the residual chlorine influence so as to judge whether the residual chlorine is in a safety range. The chlorine adding amount can be judged in real time, the influence of residual chlorine generated by the chlorine adding amount is recorded, and whether the residual chlorine is in a safety range or not is judged. And simultaneously monitoring the abnormal states of ammonia nitrogen, pH, ammonia nitrogen in the whole process, residual chlorine in the whole process, turbidity in the whole process, pH in the whole process, dissolved oxygen in the whole process, water temperature in each stage and other data which possibly influence the adding effect in real time, and giving an alarm and recording by the system when the abnormal states exist. The system analyzes and predicts the chlorine adding amount through an AI regressor, gives a given value to participate in automatic adding, and realizes full-automatic adding.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (4)
1. The utility model provides a quality of water dosing system based on historical data intelligent prediction which characterized in that includes:
acquiring historical water quality monitoring data;
calling a pre-established prediction model, wherein the prediction model is obtained by training according to historical water quality monitoring data, the prediction model is used for judging chlorine adding amount in real time, collecting residual chlorine data generated by the chlorine adding amount, and analyzing the residual chlorine data by using the prediction model to obtain residual chlorine influence and record real-time related data of the residual chlorine influence so as to judge whether the residual chlorine is in a safety range;
the AI regressor carries out intelligent training according to the real-time related data of the residual chlorine influence recorded in the period T time to obtain at least one optimized prediction model subunit,
the comparator is used for comparing the optimized prediction model subunit obtained by the T time training in the period with the optimized prediction model subunit obtained by the T time training in the previous period to obtain whether the difference is beyond a set deviation threshold value or not, analyzing whether the difference beyond the set deviation threshold value is a forward difference or not, packing and sending the optimized prediction model subunit obtained by the T time training in the period to a control end of the prediction model if the difference is the forward difference, and updating the optimized prediction model subunit obtained by the T time training in the period to the prediction model by the control end to optimize the prediction model;
the chlorine adding amount of the prediction model is analyzed and predicted, and a given value is given, so that automatic addition can be participated in, and full-automatic addition is realized; the prediction model is used for judging whether the residual chlorine is in a safety range, if the residual chlorine is not in the safety range, an alarm signal is sent to the PLC, a judgment module in the PLC judges that real-time related data influenced by the residual chlorine deviates from a set threshold unit amount, and the PLC controls the chlorination end to revise the chlorination amount according to the set unit amount according to the deviation from the set threshold unit amount;
the AI regressor is arranged in an AI server, the AI server is provided with a communication module, the communication module is used for communicating with the control end of the prediction model, and the control end is a control module set in the PLC controller;
the AI regressor is provided with a configuration control end, and the configuration control end is used for increasing and decreasing or modifying the existing relevant parameters according to the relevant parameters which are not recorded in the emergency plan so as to ensure that the AI regressor has dynamic optimization properties;
the emergency plan is updated according to the optimization of the prediction model;
comparing the optimized prediction model subunit obtained by the T time training in the period with the optimized prediction model subunit obtained by the T time training in the previous period through a comparator to obtain whether the difference is beyond a set deviation threshold value or not, analyzing whether the difference beyond the set deviation threshold value is a forward difference or not, if not, analyzing whether the difference beyond the set deviation threshold value triggers a burst emergency plan or not, and if so, sending an alarm signal for triggering the burst emergency plan and starting the emergency plan; and after the emergency plan is implemented, studying and judging to analyze new factors appearing in the emergency plan, and simultaneously increasing and decreasing the unrecorded related parameters or modifying the existing related parameters through the configuration control end to optimize the emergency plan.
2. The intelligent water quality prediction dosing system based on historical data as claimed in claim 1, wherein the residual chlorine data is collected through a monitoring device, the monitoring device inputs the collected residual chlorine data into a memory, the memory is in two-way communication with a PLC (programmable logic controller), and the PLC acquires the residual chlorine data and then packs the residual chlorine data to be sent to a communication module in the AI server.
3. The intelligent historical data-based water quality dosing system of claim 1 wherein the set threshold is updated based on optimization of a predictive model.
4. The intelligent historical data-based water quality prediction dosing system of claim 3, wherein the set threshold is updated according to optimization of a prediction model by:
after a control end of the PLC optimizes the prediction model, the monitoring device collects the post-residual chlorine data within a plurality of cycle times after the prediction model is optimized, the post-residual chlorine data is compared with the pre-residual chlorine data collected by the monitoring device before optimization to obtain the dynamic change of the post-optimized post-residual chlorine data relative to the pre-residual chlorine data, a judgment module in the PLC judges whether the dynamic change has positive optimization relative to the pre-residual chlorine data, and if the dynamic change has positive optimization relative to the pre-residual chlorine data, the control end of the PLC updates the dynamic change to a set threshold value to optimize the set threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210046072.4A CN114065949B (en) | 2022-01-17 | 2022-01-17 | Intelligent water quality prediction dosing system based on historical data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210046072.4A CN114065949B (en) | 2022-01-17 | 2022-01-17 | Intelligent water quality prediction dosing system based on historical data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114065949A CN114065949A (en) | 2022-02-18 |
| CN114065949B true CN114065949B (en) | 2022-04-22 |
Family
ID=80231401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210046072.4A Active CN114065949B (en) | 2022-01-17 | 2022-01-17 | Intelligent water quality prediction dosing system based on historical data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114065949B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116610924B (en) * | 2023-07-17 | 2023-09-15 | 福建德尔科技股份有限公司 | Chlorine trifluoride leakage prediction system and method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009198A (en) * | 2019-03-14 | 2019-07-12 | 广州市自来水公司 | A kind of tap water supply water quality monitoring system |
| CN111436426A (en) * | 2020-05-11 | 2020-07-24 | 北京首创股份有限公司 | Secondary chlorination capsule for water delivery of water supply pipeline and preparation method thereof |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103018416B (en) * | 2012-12-05 | 2015-04-22 | 天津大学 | Water quality on-line monitoring and prediction method for water supply pipe network |
| CN112216354A (en) * | 2020-09-17 | 2021-01-12 | 江苏集萃工业过程模拟与优化研究所有限公司 | Intelligent dosing system and method based on CFD numerical simulation and machine learning |
| CN112419095A (en) * | 2020-12-01 | 2021-02-26 | 山东锋士信息技术有限公司 | Accurate dosing method based on historical data and real-time data feedback |
| CN113233557B (en) * | 2021-05-21 | 2022-03-01 | 清华大学 | Accurately-controlled secondary water supply intelligent chlorine supplementing disinfection control system |
-
2022
- 2022-01-17 CN CN202210046072.4A patent/CN114065949B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009198A (en) * | 2019-03-14 | 2019-07-12 | 广州市自来水公司 | A kind of tap water supply water quality monitoring system |
| CN111436426A (en) * | 2020-05-11 | 2020-07-24 | 北京首创股份有限公司 | Secondary chlorination capsule for water delivery of water supply pipeline and preparation method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114065949A (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102906650B (en) | Multistage process modeling approach | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN203363353U (en) | Process control valve assembly | |
| US9261862B2 (en) | Automation management system and method | |
| CN108398935A (en) | Event resolver, system, method and computer-readable nonvolatile recording medium | |
| CN109901537A (en) | Mechanical equipment method for monitoring operation states and system for edge calculations side | |
| CN114065949B (en) | Intelligent water quality prediction dosing system based on historical data | |
| CN105225979A (en) | A kind of semiconductor device processing procedure prognoses system and method | |
| CN111865407B (en) | Intelligent early warning method, device, equipment and storage medium for optical channel performance degradation | |
| US8761909B2 (en) | Batch process monitoring using local multivariate trajectories | |
| CN102885392A (en) | Quality monitoring system and method of tobacco primary process | |
| CN101788811A (en) | Data recorder for industrial automation systems | |
| CN109117565A (en) | The method, apparatus and cloud server managed to water purifier filter core | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| US20210192384A1 (en) | Device and method for monitoring a system | |
| CN110324408A (en) | The acquisition of cloud layer data and Data Analysis Software system | |
| CA3106946A1 (en) | Connected backfeeding installation and method for operating such an installation | |
| CN109947064A (en) | Intelligent water communication temperature expert system for control and hardware detection and data monitoring method | |
| RU121944U1 (en) | AUTOMATED SYSTEM FOR IDENTIFYING FAULT SENSORS AMONG SENSORS INTENDED FOR CONTROL OF TECHNOLOGICAL PROCESSES | |
| CN117455242A (en) | Water conservancy management system based on digital twinning | |
| JP7438187B2 (en) | Method and apparatus for training machine learning routines to control technical systems | |
| US20140052425A1 (en) | Method and apparatus for evaluating a model of an industrial plant process | |
| KR102562025B1 (en) | AI Small Water Purification System and method with Self-Diagnosis | |
| CN115356990A (en) | Material yard equipment fault prediction method and system based on deep learning and storage medium | |
| CN110517731A (en) | Genetic test quality monitoring data processing method and system |
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 |