6 results about "Soft sensing" patented technology

The present application relates to the technical field of thermal power plants, and discloses an intelligent operation method and system for a thermal power plant, a device, and a storage medium. The method comprises: measuring operation parameters of a thermal power plant in real time by means of advanced detection and soft sensing techniques; establishing a fault monitoring model to monitor the operation process of the thermal power plant on the basis of the real-time detected operation parameters, and generating an early warning signal when a fault occurs; performing fault diagnosis, and generating a fault self-healing instruction; and evaluating the operation status of the thermal power plant by means of a performance evaluation model, and then obtaining optimal operation modes and optimal operation parameter setpoints by means of a multi-objective optimization algorithm. The present application achieves high-performance real-time intelligent closed-loop control, improving the adaptability to complex working conditions and the disturbance rejection capability of a thermal power plant production process control system, and the overall performance of a thermal power plant production process; and efficient human-computer interaction is achieved by means of artificial intelligence-based early warning diagnosis and closed-loop self-healing.

This invention relates to the field of online measurement technology, and more particularly to a method and system for soft measurement modeling of industrial processes for incomplete data. The steps include: acquiring historical sample data containing missing values ​​in the industrial process and constructing a BGPLVM model; extracting sample features based on the historical sample data and using them as prior constraints to initialize the hyperparameters of the BGPLVM model; acquiring query sample data and obtaining the latent variable variational distribution of the query sample data based on the BGPLVM model; extracting historical sample data most similar to the latent variable variational distribution to construct a local sample dataset; constructing a Gaussian process regression model and determining the parameters of the Gaussian process regression model by maximizing the log-likelihood; and substituting the latent variable variational distribution of the query sample data into the Gaussian process regression model to predict the output variable corresponding to the query sample data.

Fouling is formation of deposits on the heat exchanger surfaces that adversely affects operation of heat exchanger. Fouling can be approximated through a set of estimated heat exchanger parameters, which may not be accurate, leading to uncertainty in operation / maintenance decisions and hence the losses. A system and a method for identification and forecasting fouling of a plurality of heat exchangers in a refinery has been provided. The system comprises a digital replica of the heat exchanger network. The digital replica is configured to receive real-time sensor data from a plurality of data sources and provides real-time soft sensing of key parameters. The system is also configured to diagnose the reasons behind a specific condition of fouling. Further, an advisory is provided, that alerts and recommends corrective actions. The system provides estimate for the remaining useful life (RUL) of the heat exchangers and suggests the cleaning schedule.

This invention discloses a method for monitoring and evaluating shipborne wastewater treatment based on high-resolution full-spectrum soft sensing, relating to the fields of water quality monitoring and marine environmental protection. It aims to address the technical problems of existing shipborne water quality monitoring systems, which rely on hardware sensors, have weak anti-interference capabilities, poor model generalization, and cannot accurately analyze the status of each stage of the wastewater treatment system in real time, resulting in an incomplete evaluation system. This method uses high-resolution full-spectrum data as a foundation, integrates soft sensing technology, and constructs a water quality parameter prediction model based on machine learning and self-learning to achieve real-time and accurate measurement of key water quality parameters of shipborne wastewater. Simultaneously, it establishes a comprehensive evaluation index system for the shipborne wastewater treatment system, combining monitored water quality parameters and operational data from each stage to complete status analysis and fault prediction for core stages such as sedimentation, oxidation, and biological treatment.

This invention discloses a method for predicting count-type quality variables based on a variational Bayesian Gaussian-Poisson mixture regression model. This method can be used for data analysis and prediction where the dependent variable is count data and the independent variable is continuous numerical data. Its core involves fitting continuous and count data respectively using Gaussian mixture distributions and Poisson mixture regression distributions, assuming that the two mixture distributions share the same mixing coefficients, and employing variational inference techniques for model parameter learning. This invention overcomes the limitation of traditional soft sensing methods in providing discrete probability estimates for count data and can solve the problem of process variables and quality variables exhibiting multiple modalities due to multiple operating conditions in industrial processes.

The application discloses a kind of rock-fill dam concrete faceplate strain soft sensing method and system of structural safety monitoring technical field, the method includes: obtaining the monitoring data of rock-fill body deformation sensor, input to the mapping model constructed in advance, the monitoring data of concrete faceplate strain virtual sensor is calculated;The construction of mapping model includes: according to actual rock-fill dam engineering, finite element simulation model is established;Using finite element simulation model, the situation of rock-fill body deformation and concrete faceplate strain under environmental load is simulated, and simulation result data is obtained;The mapping relationship between rock-fill body deformation and concrete faceplate strain is established by actually collected rock-fill body deformation monitoring data, concrete faceplate strain monitoring data and simulation result data;Based on mapping relationship, the final mapping model is constructed.The rock-fill dam concrete faceplate strain soft sensing method of the application can provide more comprehensive faceplate strain virtual monitoring data under the condition of low monitoring cost.