PSO-LSSVM-based on-line control method and apparatus for dosing of water island
A control method, the technology of Mizushima, applied in the direction of adaptive control, general control system, control/regulation system, etc., can solve problems such as low work efficiency, waste of medicines, and inability to meet the requirements of effluent standards
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] refer to figure 1 , shows an embodiment of an online control method for water island dosing based on PSO-LSSVM. This embodiment aims at the obvious hysteresis and constancy of the water treatment and dosing system in thermal power plants, combined with LSSVM nonlinear time series prediction As well as the characteristics of PSO parameter optimization, select the inflow monitoring indicators and dosing amount of the corresponding period when the historical water output indicators meet the requirements as samples, use the LSSVM model for sample training, and apply the PSO algorithm to optimize the parameters of the LSSVM model, and finally get the water island The drug dosing model is used to realize intelligent dynamic real-time drug dosing. The method of this embodiment specifically includes the following steps S102 to S112.
[0031] Step S102: Acquiring M groups of historical parameter values of incoming water monitoring indicators for which the outlet water index me...
Embodiment 2
[0044] This embodiment shows a preferred embodiment based on the above-mentioned embodiment 1. The PSO-LSSVM-based online control method for water island dosing provided in this embodiment is aimed at the current production process of water treatment in thermal power plants that only relies on Experience and traditional dosing models are difficult to guarantee the online optimization analysis of dosing amount, and the PSO algorithm falls into the local optimum problem. Using chaos theory to generate the initial population and improve the ergodicity, randomness and diversity of the initial population can avoid PSO randomness. The quality of the initial population is poor and it is concentrated in some local areas so that the algorithm falls into a local optimum. PSO is referenced to the LSSVM training samples to determine the optimal parameters and realize intelligent dynamic water treatment dosing. The specific instructions are as follows:
[0045]Step 1. Obtain the digital si...
Embodiment 3
[0077] Such as Figure 10 As shown, this embodiment provides a PSO-LSSVM-based water island dosing online control device, the control device is applied in the water treatment system of a thermal power plant, and specifically includes a historical data acquisition module 10, a model building module 20, a parameter An optimization module 30 , a real-time monitoring module 40 and a dosage control module 50 .
[0078] Wherein, the historical data acquisition module 10 is used to obtain the M groups of historical parameter values of the incoming water monitoring index that meet the requirements of the water outlet index, and the historical dosing amount of the dosing agent corresponding to each group of historical parameter values, wherein the incoming water monitoring index Including a plurality of indicators, each group of historical parameter values includes the parameter values of a plurality of indicators; the model building module 20 is used to establish an online contr...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com