Wastewater treatment plant online monitoring and control
US-2015034553-A1 · Feb 5, 2015 · US
US12187633B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12187633-B2 |
| Application number | US-201916551297-A |
| Country | US |
| Kind code | B2 |
| Filing date | Aug 26, 2019 |
| Priority date | Aug 29, 2018 |
| Publication date | Jan 7, 2025 |
| Grant date | Jan 7, 2025 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
To solve problems of frequent occurrence and great harm of membrane fouling during MBR wastewater treatment process, the invention proposes a membrane fouling intelligent early warning method to realize online and accurate early warning of membrane fouling. This early warning method achieves accurate prediction of water permeability by constructing soft-computing model based on recurrent fuzzy neural network. The intelligent early warning of membrane fouling is achieved by the comprehensive evaluation method, which solves the problem that membrane fouling is difficult to be early warning in the MBR wastewater treatment process, improves the pretreatment ability of membrane fouling, reduces the damage caused by membrane fouling, ensures the safe operation of MBR wastewater treatment process, and promotes efficient and stable operation of MBR wastewater treatment plant.
Opening claim text (preview).
What is claimed is: 1. Membrane bioreactor-MBR membrane fouling intelligent early warning method for a wastewater treatment process (WWTP), comprising the following steps: (1) data acquisition of the wastewater treatment process comprises: collect WWTP data by an acquisition instrument installed on site of the wastewater treatment process, the WWTP data including the following variables: water flow volume, water pressure, influent chemical oxygen demand (COD), pH, influent biological oxygen demand (BOD), effluent total phosphorus (TP), oxidation-reduction potential (ORP), dissolved oxygen (DO), nitrate, aeration volume; the data acquisition of the WWTP further comprises transmitting the acquired WWTP data to a Programmable Logic Controller (PLC) through Modbus communication protocol for pretreatment by the PLC, wherein the PLC transmits pretreated WWTP data to a host computer through RS232 communication protocol for intelligent prediction and early warning of membrane fouling; intelligent prediction result and early warning information of membrane fouling obtained in the host computer is transmitted to a database server through a local area network and displayed on a computer interface through a browser; (2) the pretreatment of the acquired WWTP data by the PLC comprises: using a partial least squares method to extract five principal component variables, which are the water flow volume, the water pressure, the aeration volume, the ORP and the nitrate; these five principal component variables are used as input variables of a membrane fouling intelligent prediction model, and water permeability is used as output variable of the membrane fouling intelligent prediction model and as one of evaluation indexes of membrane fouling; (3) the intelligent prediction of membrane fouling via the host computer comprises: establish a soft-computing model to predict the water permeability based on a recurrent fuzzy neural network in the host computer to obtain predicted water permeability, a structure of the recurrent fuzzy neural network contains four layers: an input layer, a membership function layer, a normalized layer and an output layer, the recurrent fuzzy neural network is 5−M−M−1, M is an integer and 2<M<30; connecting weights between the input layer and the membership function layer are assigned 1, an output of the recurrent fuzzy neural network is y(t); prediction method of water permeability based on the recurrent fuzzy neural network is: y ( t ) = f ( x ( t ) ) = ∑ j = 1 M w j ( t ) ∏ i = 1 5 exp [ - [ β ij ( t ) x i ( t ) + θ ij ( t ) O ij 2 ( t - 1
Pressure · CPC title
O2 · CPC title
N03-N · CPC title
Chemical Oxygen Demand [COD]; Biological Oxygen Demand [BOD] · CPC title
pH · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.