CN113885596B - Intelligent monitoring system for sewage treatment - Google Patents
Intelligent monitoring system for sewage treatment Download PDFInfo
- Publication number
- CN113885596B CN113885596B CN202111221431.7A CN202111221431A CN113885596B CN 113885596 B CN113885596 B CN 113885596B CN 202111221431 A CN202111221431 A CN 202111221431A CN 113885596 B CN113885596 B CN 113885596B
- Authority
- CN
- China
- Prior art keywords
- early warning
- liquid level
- monitoring
- layer
- emergency
- 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
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D9/00—Level control, e.g. controlling quantity of material stored in vessel
- G05D9/12—Level control, e.g. controlling quantity of material stored in vessel characterised by the use of electric means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention belongs to the technical field of intelligent monitoring, and particularly relates to an intelligent monitoring system for sewage treatment. The system collects working condition data of the operating equipment in real time, and stores and analyzes the collected data; the alarm system can realize the transmission of alarm information, and relates to high-water-level multi-level alarm, low-water-level multi-level alarm, over-temperature passive alarm, over-temperature active alarm and the like. The invention can improve the safety and reliability of the operation of the intelligent sewage treatment monitoring system. The invention can be applied to the field of intelligent monitoring of sewage treatment.
Description
Technical Field
The invention belongs to the technical field of intelligent monitoring, relates to an intelligent monitoring system of a sewage treatment plant, and particularly relates to an unattended intelligent monitoring system of sewage treatment.
Background
The operation pump rooms of the existing sewage treatment plant are generally distributed and dispersed, the geographical position is remote, and operation and maintenance personnel need to continuously patrol among a plurality of pump rooms, so that the problems of large workload, large labor workload and high personnel cost are caused. For a system adopting manual control, the problems of low working efficiency, untimely response and the like can also be caused. Therefore, the established sewage treatment intelligent monitoring system has good practical application value for improving the working efficiency, reducing the production cost and improving the system operation reliability.
Disclosure of Invention
The invention aims to solve the technical problem that in order to improve the intelligent level of monitoring management of a sewage treatment plant, an intelligent sewage treatment monitoring system is designed to improve the reliability of system operation.
The technical scheme adopted by the invention is as follows: an intelligent monitoring system for sewage treatment collects working condition data of operating equipment in real time, and stores and analyzes the collected data; the transmission of alarm information can be realized, and the alarm relates to high water level multistage alarm, low water level multistage alarm, over-temperature passive alarm, over-temperature active alarm and the like; the full-range video monitoring is realized, and data support is provided for accident occurrence or accident investigation and evidence collection.
The invention aims to construct an unattended sewage treatment monitoring system, which reduces the personnel cost and improves the working efficiency under the condition of meeting the safe and reliable operation and has good practicability.
Drawings
FIG. 1 is a diagram of an intelligent monitoring system for sewage treatment.
Fig. 2 is a diagram of a comprehensive predictive network model architecture.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The sewage treatment intelligent monitoring system adopts a three-layer structure, as shown in figure 1, and comprises a data acquisition and detection layer, an on-site monitoring and control layer and a remote monitoring layer.
The data acquisition and detection layer adopts an ultrasonic liquid level meter to realize the liquid level detection of the sewage tank, adopts a temperature sensor to carry out temperature detection on the operating environment temperature of the system, and transmits the detection results of the liquid level and the temperature to the field monitoring and control layer. And the on-site monitoring and control layer transmits the liquid level and temperature detection data results to the remote monitoring layer for storage, calculation and analysis. The on-site monitoring and control layer compares the received liquid level and temperature data with a set threshold value, gives an operation state and an early warning decision according to a comparison result, transmits the operation state and the early warning decision result to the remote monitoring layer, and the remote monitoring layer stores and displays the acquired data, so that the active early warning of the temperature is realized, and a decision suggestion is given. The field monitoring and control layer transmits physical data such as the starting and stopping state and the current value of the pump to the remote monitoring layer at the same time, and the remote monitoring layer analyzes and processes the data and stores results. And the field monitoring and control layer adopts a multi-stage early warning mode.
In a high liquid level alarm decision-making system of a field monitoring and control layer, three levels of highest liquid level emergency early warning, high liquid level reminding early warning and higher liquid level attention early warning are set according to the emergency degree from high to low.
In the field monitoring and control layer, a maximum liquid level emergency early warning threshold value H is set1And high liquid level reminding early warning threshold value H2In which H1>H2. The system collects the liquid level value at the time t in real time as h (t), the liquid level value 10 minutes before the time t is h (t-10), and the early warning rule is set as follows:
when H (t) is not less than H1And the field monitoring and control layer sends out the highest liquid level emergency early warning information, transmits the highest liquid level emergency early warning information to the remote monitoring layer and waits for emergency treatment by workers.
When H is present2<h(t)<H1And h (t)>And h (t-10), the on-site monitoring and control layer sends out high liquid level reminding early warning information, and the high liquid level reminding early warning information is transmitted to a remote monitoring layer to remind a worker to process in time.
When H is present2<h(t)<H1And h (t) is less than or equal to h (t-10), the on-site monitoring and control layer sends out higher liquid level attention early warning information and transmits the higher liquid level attention early warning information to the remote monitoring layer to remind workers to pay attention to the processing.
For a low liquid level alarm decision-making system, three levels of minimum liquid level emergency early warning, low liquid level reminding early warning and lower liquid level attention early warning are set from high to low according to the emergency degree.
A lowest liquid level emergency early warning threshold value L is arranged in the field monitoring and control layer1And low liquid level reminding early warning threshold value L2Wherein L is1<L2. The system collects the level value at the time t in real time as h (t), the level value 10 minutes before the time t is h (t-10), and the early warning rule is set as follows:
when h (t) is less than or equal to L1And the field monitoring and control layer sends out minimum liquid level emergency early warning information, transmits the minimum liquid level emergency early warning information to the remote monitoring layer and waits for emergency treatment by workers.
When L is1<h(t)<L2And h (t)<h (t-10), the on-site monitoring and control layer sends out low liquid level reminding early warning information, and transmits the low liquid level reminding early warning information to the remote monitoring layer to remind workers to process the low liquid level reminding early warning information in time.
When L is1<h(t)<L2And h (t) ≧ hAnd h (t-10), the field monitoring and control layer sends out lower liquid level attention early warning information and transmits the lower liquid level attention early warning information to the remote monitoring layer to remind workers to pay attention to the lower liquid level attention early warning information.
And an active early warning mode and a passive early warning mode are adopted for the system operation environment temperature. The passive early warning adopts a threshold value comparison mode, and the active early warning adopts a temperature prediction mode.
Setting the maximum temperature warning value as T1The data acquisition and detection layer acquires the current temperature value, transmits the current temperature value to the field monitoring and control layer, and when the acquired system operation environment temperature exceeds the highest temperature early warning value T1And when the monitoring and control layer on site sends out passive early warning information, the passive early warning information is transmitted to a remote monitoring layer, and a worker waits for emergency treatment.
The remote monitoring layer carries out temperature prediction according to historical temperature information of the system operating environment, and when the predicted value exceeds the highest early warning value T1And the remote monitoring layer sends out active early warning information.
And predicting future temperature data information based on historical temperature data information, forming a training sample pair by utilizing the historical temperature data, and predicting by adopting a BP network. And (3) if the system operating environment temperature acquired at the moment k is x (k), constructing a training sample pair for P-step prediction as follows: { [ x (k), x (k-1), x (k-2),.., x (k-m) ], x (k + P) }. Thus, the temperature value x (k + P) at time (k + P) is associated with the temperature values at (m +1) times x (k), x (k-1), x (k-2),.. times, x (k-m). Thus, the input layer of the BP neural network is set to (m +1) neurons, which correspond to x (k), x (k-1), x (k-2),. so, x (k-m) numerical inputs, and the output layer is set to 1 neuron, which corresponds to x (k + P).
Wherein, the selection of the parameter m has a great influence on the prediction accuracy. When m is selected too much, input data redundancy can be caused, and the prediction performance is not high; when m is selected too small, data loss and prediction performance degradation are caused.
For the purpose, the invention designs an integrated prediction network model containing three BP (back propagation) sub-networks for predicting the temperature data of the operating environment of the future system, the structure of the integrated prediction network model is shown as figure 2, and the integrated prediction network model comprises three BP sub-networksBP sub-networks, the input layer of the first BP sub-network comprising (M)1+1) neurons, the input layer of the second BP subnetwork contains (M)2+1) neurons, the input layer of the third BP subnetwork contains (M)3+1) neurons, wherein M1<M2<M3The outputs of the three subnetworks are respectively AND (M)1+1)、(M2+1)、(M3+1) historical data, the first subnetwork is associated with historical short-term data, and its training sample pairs are: { [ x (k), x (k-1), x (k-2),. times.x (k-M)1)]X (k + P) }, the second subnetwork is associated with historical interim data with training sample pairs of: { [ x (k), x (k-1), x (k-2),. -, x (k-M)2)]X (k + P) }, the third subnet is associated with historical long-term data, and its training sample pair is: { [ x (k), x (k-1), x (k-2),. -, x (k-M)3)]X (k + P) }. And (3) independently training the three BP sub-networks respectively, after the training is finished, taking the output of the three sub-networks as the input of a final prediction neuron, performing fine tuning training, and predicting the system operation environment temperature data of the trained comprehensive network. Setting the final predicted value of the comprehensive prediction network model as y, and when y is less than or equal to T1When the system is in use, the system does not send out active early warning information; when y is>T1When the system sends out active early warning information, and gives out an active early warning probability value p (y) which is as follows:
wherein exp () is an exponential function with a natural constant e as a base, and c is an active early warning emergency coefficient. The active early warning probability value provides information reference for the routing inspection maintenance work planning and scheduling of workers, and the safety and reliability of system operation are improved.
Because each sub-network in the comprehensive prediction network is associated with historical data information with different lengths, the prediction function of each sub-network can be adaptively adjusted through fine tuning training, the defect of reduced prediction performance caused by improper selection of neurons in an input layer of a single network can be overcome, and the prediction precision is improved.
The invention has the advantages that through multi-level liquid level early warning, maintenance emergency degree reference can be provided for workers, and the maintenance planning and scheduling of the workers are facilitated. The comprehensive prediction network is adopted to predict the temperature, so that the prediction precision of the temperature can be improved, and the active early warning of the sewage treatment monitoring system is realized. The invention is suitable for the field of intelligent monitoring of sewage treatment.
Claims (3)
1. An intelligent monitoring system for sewage treatment is characterized in that the intelligent monitoring system for sewage treatment adopts a three-layer structure and comprises a data acquisition and detection layer, a field monitoring and control layer and a remote monitoring layer; the system collects working condition data of operating equipment in real time, and stores and analyzes the collected data; the transmission of alarm information can be realized, and the alarm device relates to high water level multi-level alarm, low water level multi-level alarm, over-temperature passive alarm and over-temperature active alarm;
designing an integrated prediction network model containing three BP (back propagation) sub-networks to predict the temperature data of the operating environment of the future system, wherein the integrated prediction network model comprises the three BP sub-networks, and the input layer of the first BP sub-network contains (M)1+1) neurons, the input layer of the second BP subnetwork contains (M)2+1) neurons, the input layer of the third BP subnetwork contains (M)3+1) neurons, wherein M1<M2<M3The outputs of the three subnetworks are respectively AND (M)1+1)、(M2+1)、(M3+1) historical data are associated, the system operating environment temperature acquired at the moment k is set as x (k), the first sub-network is associated with historical short-term data, and the training sample pair is as follows: { [ x (k), x (k-1), x (k-2),. times.x (k-M)1)]X (k + P) }, the second subnetwork is associated with historical interim data, whose training sample pairs are: { [ x (k), x (k-1), x (k-2),. times.x (k-M)2)]X (k + P) }, the third sub-network is associated with historical long-term data, and the training sample pair is: { [ x (k), x (k-1), x (k-2),. times.x (k-M)3)]X (k + P) }; three BP sub-networks are respectively trained independently, and after the training is finished, the output of the three sub-networks is used as the input of a final prediction neuron to carry outFine tuning training, namely predicting the temperature data of the system operating environment of the trained comprehensive network; setting the final predicted value of the comprehensive prediction network model as y, and when y is less than or equal to T1When the system is in use, the system does not send out active early warning information; when y is>T1When the system sends out active early warning information, and gives out an active early warning probability value p (y) which is as follows:
wherein exp () is an exponential function with a natural constant e as a base, and c is an active early warning emergency coefficient; the active early warning probability value provides information reference for the routing inspection maintenance work planning and scheduling of workers, and the safety and reliability of system operation are improved.
2. The intelligent sewage treatment monitoring system according to claim 1, wherein in a high liquid level alarm decision-making system of a field monitoring and control layer, three levels of a highest liquid level emergency early warning, a high liquid level reminding early warning and a higher liquid level attention early warning are set from high to low according to the degree of emergency;
in the field monitoring and control layer, a maximum liquid level emergency early warning threshold value H is set1And high liquid level reminding early warning threshold value H2In which H is1>H2(ii) a The system collects the level value at the time t in real time as h (t), the level value 10 minutes before the time t is h (t-10), and the early warning rule is set as follows:
when H (t) is not less than H1The on-site monitoring and control layer sends out the emergency early warning information of the highest liquid level, and transmits the emergency early warning information to the remote monitoring layer to wait for the emergency treatment of the staff;
when H is present2<h(t)<H1And h (t)>h (t-10), the on-site monitoring and control layer sends out high liquid level reminding early warning information, and transmits the high liquid level reminding early warning information to a remote monitoring layer to remind workers to process the high liquid level reminding early warning information in time;
when H is present2<h(t)<H1H (t) is less than or equal to h (t-10), the on-site monitoring and control layer sends out higher liquid level attention early warning information and transmits the information to the far endThe monitoring layer is used for reminding workers to pay attention to the processing;
for a low liquid level alarm decision-making system, setting three levels of minimum liquid level emergency early warning, low liquid level reminding early warning and lower liquid level attention early warning from high to low according to the emergency degree;
a lowest liquid level emergency early warning threshold value L is arranged in the field monitoring and control layer1And low liquid level reminding early warning threshold value L2Wherein L is1<L2(ii) a The system collects the level value at the time t in real time as h (t), the level value 10 minutes before the time t is h (t-10), and the early warning rule is set as follows:
when h (t) is less than or equal to L1The on-site monitoring and control layer sends out minimum liquid level emergency early warning information, transmits the minimum liquid level emergency early warning information to a remote monitoring layer and waits for emergency treatment by workers;
when L is1<h(t)<L2And h (t)<h (t-10), the on-site monitoring and control layer sends out low liquid level reminding early warning information, and transmits the low liquid level reminding early warning information to a remote monitoring layer to remind a worker to process in time;
when L is1<h(t)<L2And h (t) is not less than h (t-10), the on-site monitoring and control layer sends out low liquid level attention early warning information and transmits the low liquid level attention early warning information to the remote monitoring layer to remind workers to pay attention to the low liquid level attention processing.
3. The intelligent sewage treatment monitoring system according to claim 1, wherein an active early warning and a passive early warning are adopted for the system operating environment temperature; a threshold comparison mode is adopted for passive early warning, and a temperature prediction mode is adopted for active early warning;
setting the highest early warning value of temperature as T1The data acquisition and detection layer acquires the current temperature value and transmits the current temperature value to the field monitoring and control layer, and when the acquired system operating environment temperature exceeds the maximum temperature early warning value T1When the monitoring and control layer is in use, the on-site monitoring and control layer sends out passive early warning information, and transmits the passive early warning information to the remote monitoring layer to wait for emergency treatment of workers;
the remote monitoring layer carries out temperature prediction according to historical temperature information of the system operating environment, and when the predicted value exceeds the highest early warning valueValue T1And the remote monitoring layer sends out active early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111221431.7A CN113885596B (en) | 2021-10-20 | 2021-10-20 | Intelligent monitoring system for sewage treatment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111221431.7A CN113885596B (en) | 2021-10-20 | 2021-10-20 | Intelligent monitoring system for sewage treatment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113885596A CN113885596A (en) | 2022-01-04 |
| CN113885596B true CN113885596B (en) | 2022-07-22 |
Family
ID=79003712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111221431.7A Active CN113885596B (en) | 2021-10-20 | 2021-10-20 | Intelligent monitoring system for sewage treatment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113885596B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103968913B (en) * | 2014-05-19 | 2017-01-04 | 清华大学 | Intelligent online level monitoring early warning system |
| CN104460577A (en) * | 2014-07-24 | 2015-03-25 | 上海市城市排水有限公司 | Water quality safety early warning decision making system |
| CN104236626B (en) * | 2014-09-04 | 2016-05-25 | 北京清控人居环境研究院有限公司 | The integrated on-line monitoring system of drainage pipeline liquid level and flow |
| CN110374047B (en) * | 2019-05-28 | 2020-05-05 | 中国水利水电科学研究院 | Deformation-based arch dam operation period real-time safety monitoring threshold determination method |
| CN111003883A (en) * | 2019-12-05 | 2020-04-14 | 广州中国科学院先进技术研究所 | Intelligent integrated real-time information alarm method and system for sewage treatment equipment |
| CN111580570B (en) * | 2020-05-28 | 2023-03-17 | 爱瑟福信息科技(上海)有限公司 | Container liquid level monitoring method and system |
| CN112598368A (en) * | 2020-12-04 | 2021-04-02 | 贵州昱清浩瑞科技有限公司 | Sewage treatment online supervision platform |
-
2021
- 2021-10-20 CN CN202111221431.7A patent/CN113885596B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113885596A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111556032A (en) | Industrial big data processing system based on artificial intelligence algorithm | |
| CN109146093A (en) | A kind of electric power equipment on-site exploration method based on study | |
| CN113592128A (en) | Big data electric wire netting operation monitoring system | |
| CN105574604B (en) | Monitoring pre-judging analysis system for power grid operation event | |
| KR20150026230A (en) | Self running building energy management system using bim data | |
| CN115423301B (en) | Intelligent electric power energy management and control method, device and system based on Internet of things | |
| CN104243184A (en) | Alarm information processing method and apparatus | |
| CN112270429A (en) | Cloud edge cooperation-based power battery pole piece manufacturing equipment maintenance method and system | |
| RU2713077C1 (en) | Decision support system with a modular structure for double-acting operators | |
| CN117354171B (en) | Platform health condition early warning method and system based on Internet of things platform | |
| CN113885596B (en) | Intelligent monitoring system for sewage treatment | |
| CN111624874A (en) | Pump station cluster intelligent prediction method and system for urban sewage treatment | |
| CN110989042A (en) | Intelligent prediction method for highway fog-clustering risk | |
| CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
| CN113658415B (en) | Early warning method and system of intelligent gateway | |
| CN111381573B (en) | Method and system for predicting safety of industrial control system | |
| CN108572631B (en) | Intelligent control system and method based on two-type fuzzy cognitive map | |
| Huu et al. | Development of warning and predicting system for quality of air in smart cities using RNN | |
| CN112526945A (en) | Full-process monitoring and early warning system with feedback and closed-loop control functions | |
| Yuwana et al. | An ontology tropical weather model for sensor network interoperability | |
| CN111832832B (en) | District self-inspection system based on thing networking | |
| CN117111540B (en) | Environment monitoring and early warning method and system for IO remote control bus module | |
| CN211319082U (en) | Liquid level monitoring system of drainage system | |
| Yang et al. | Investigation on data-driven life prediction methods | |
| KR100803561B1 (en) | System and method for managing housing facilities using intelligent real-time diagnosis |
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 |