86 results about "Soft sensor" patented technology

A computer method and apparatus of online automated model identification of multivariable processes is disclosed. The method and apparatus carries out automatically all the four basic steps of industrial process identification: 1) identification test signal design and generation, 2) identification plant test, 3) model identification and 4) model validation. During the automated plant test, process models will be automatically generated at a given time interval, for example, every hour, or on demand; the ongoing test can be automatically adjusted to meet the process constraints and to improve the data quality. Plant test can be in open loop operation, closed-loop operations or partly open loop and partly closed-loop. In a (partial) closed-loop plant test, any type of controller can be used which include proportional-integral-derivative (PID) controllers and any industrial model predictive controller (MPC). The obtained process models can be used as the model in advanced process controllers such as model predictive control (MPC) and linear robust control; they can also be used as inferential models or soft sensors in prediction product qualities. The apparatus can be used in new MPC controller commissioning as well as in MPC controller maintenance.

A hybrid cascade Model-Based Predictive control (MBPC) and conventional control system for thermal processing equipment of semiconductor substrates, and more in particular for vertical thermal reactors is described. In one embodiment, the conventional control system is based on a PID controller. In one embodiment, the MBPC algorithm is based on both multiple linear dynamic mathematical models and non-linear static mathematical models, which are derived from the closed-loop modeling control data by using the closed-loop identification method. In order to achieve effective dynamic linear models, the desired temperature control range is divided into several temperature sub-ranges. For each temperature sub-range, and for each heating zone, a corresponding dynamic model is identified. During temperature ramp up/down, the control system is provided with a fuzzy control logic and inference engine that switches the dynamic models automatically according to the actual temperature. When a thermocouple (TC) temperature measurement is in failure, a software soft sensor based on dynamic model computing is used to replace the real TC sampling in its place as a control system input. Consequently, when a TC failure occurs during a process, the process can be completed without the loss of the semiconductor substrate(s) being processed.

In servomechanisms, like for example used in disk drives, disturbances, for example, friction, shock and vibration, prevent the system positioning accuracy from further improvement. These disturbances occur in a relatively low-frequency range compared to the electrical dynamics. In the present invention, an acceleration feedback control loop using a frequency-separated acceleration soft sensor (350) replaces the conventionally used current control loop in the low frequency range, where the disturbances occur, so as to attenuate the influence of the disturbances enclosed in the loop. The current feedback continues to manage the electrical dynamics in the high-frequency range. Estimating the required acceleration signal by a soft sensor (350) eliminates the need for physical accelerometers, which reduce system reliability and increase system cost. The acceleration feedback control loop constructed with the obtained acceleration signal also makes the system more robust to the parameter inaccuracies and variations within the loop. This invention can be easily implemented with either software or hardware.

A system for the computer-aided measurement of quality and/or process data during the production and/or conversion of a material web, in particular paper or board web, by way of correlation with raw measured data. The raw measured data is present in the form of other quality and process data during the production or conversion process. Measurements of quality parameters in the laboratory may also be incorporated in the raw measured data. The raw measured data is combined to form data sets which in each case are determined simultaneously. Specific laboratory or quality measurements are selected as target data which, by way of at least one soft-sensor algorithm running in a computer-based operation and linking unit, can be calculated from the other data serving as input data, and each data set containing measured data, which relates approximately to the same monitored volume of web and raw material, in particular paper and paper raw material.

The invention discloses a method for building adaptive soft sensor. The method comprises the following steps. The input and schedule vectors are constructed, and a novel learning algorithm that uses online subtractive clustering is used to recursively update the structure and parameters of a local model network. Three rules are proposed for updating centers and local model coefficients of existing clusters, for generating new clusters and new models as well as for merging existing clusters and their corresponding models. Once verified, the online inferential model can be created to generate the predicted value of process. Thus, it does not need much memory space to process the method and can be easily applied to any other machine.

A system and method for optimization of a continuous digester operation of a continuous digester are presented. The system includes a tracking module for tracking of process variables in the continuous digester operation and developing non-linear empirical model for one or more quality variables. A soft sensor module is used for deploying a soft sensor based on the non-linear empirical model and for generating soft measurements corresponding to the quality variables at different locations. A constraint management module is used for generating dynamically a set of constraints that are used by a model predictive controller for computing set points for optimization of continuous digester operation.

The invention discloses an identification method of nonlinear parameter varying models (NPV) and belongs to the industrial identification field. The invention carries out identification tests and model identification for an identified object with nonlinear parameter varying characteristics. Firstly, the multi-input single-output nonlinear parameter varying model is identified through the steps of local nonlinear model tests, local nonlinear models identification, and operating point variable transition tests; after completing the identification of all the multi-input single-output nonlinear parameter varying models with respect to all the controlled variables, the completed multi-input multi-output nonlinear parameter varying models are built. The nonlinear parameter varying models of an identified object can be obtained by the identification method of the present invention with limited input/output data without detailed mechanism knowledge of the identified object. The nonlinear parameter varying models obtained can be used in model-based control algorithm design and process simulation, as well as in product quality prediction reasoning models and soft sensors.

Soft-sensing method of crucial biochemical quantity in penicillin fermentation process based on fuzzy neural inverse and system structure thereof is a method for resloving the problem that the crucial biochemical quantity in penicillin fermentation process is difficult to be measured by physical sensor on-line and real-time. Fuzzy neural inverse soft-sensing method establishes a soft-sensor (11) model based on a kinetic equation in penicillin fermentation process (1), on this basis eatablishes an inverse model of the soft-sensor according to inverse system method, and then uses static fuzzy neural network (41) and a differentor to establish fuzzy neural inverse (4) through a free parameters determined by training the static fuzzy neural network, then the soft-sensor inverse is implemented, finally links the fuzzy neural inverse after the penicillin fermentation process to implement on-line and real-time soft-sensing of fungi concentration x[1], substrate concentration x[2] and products concentration x[3]. Specific implementation of the fuzzy neural inverse is the constructed fuzzy neural inverse system applies embedded microprocessor ARM processor.

The invention discloses a soft mechanical arm based on SMA springs. The soft mechanical arm comprises a platform. Multiple mechanical arm fingers are arranged below the platform. Each mechanical arm finger comprises a silica gel outer shell. Each silica gel outer shell is internally provided with a soft sensor and the corresponding two SMA springs. Every two SMA springs are arranged in the corresponding silica gel outer shell at the set angle from top to bottom. The top end of each SMA spring is provided with a lead wire. The SMA springs are connected with a control circuits through the lead wires. The extending-and-contracting state of the SMA springs is controlled through the control circuit, and thus, work of the mechanical arm fingers is achieved. The control circuit comprises a singlechip microcomputer, a PWM electronic switch control panel and a voltage-controlled current source, wherein the single chip microcomputer is provided with multiple analog input ports. The STM32 singlechip microcomputer is used for achieving a PWM control constant flow source circuit and outputting the specific frequency and PWM waveforms of specific duty ratios. The PWM electronic switch controlpanel is used for converting PWM signals into the voltage. The voltage-controlled current source controls the current to change through voltage changes. By means of the soft mechanical arm, gripping control of the soft mechanical arm can be achieved.

A case base generator divides an input space of history data into unit input spaces according to a desired output allowable error, and creates a representative case from the history data arranged in the unit input spaces, thereby generating a case base. A case retrieving section of a soft sensor retrieves a case corresponding to new input data from the case base. An output estimating section calculates and outputs estimated output data corresponding to the new input data on the basis of the output data on the retrieved case. An output evaluating section calculates and outputs an estimation error in the estimated output data on the basis of the topological distance between the new input data and the retrieved case. A function evaluating section evaluates the soft sensor on the basis of the estimation error, the estimated output data, and true output data.

The invention relates to a neural network inverse-based soft sensing and soft sensor construction method for variables during an operation process of a power distribution network intelligent capacitor; that is, the invention relates to an on-line estimation method for variables, so that a problem that it is difficult to carry out on-line and real-time measurement on variables by a sensor during a capacitor operation process can be solved. According to an operation process model of a capacitor, a model of an embedded sensor is established; a neural network inverse that is in series connection after the capacitor operation process is constructed to realize a contained sensor inverse; and at last, on-line soft sensing on a compensation capacity and a medium loss of the capacitor is realized. Besides, the neural network inverse is realized by employing a digital signal processor. In addition, the invention relates to an on-line monitoring system for a power distribution network intelligent capacitor. The on-line monitoring system comprises an on-site preset device and a signal acquisition terminal. A sensor detects a corresponded physical quantity on a capacitor unit; after digital analog conversion, the detected physical quantity is sent to a digital signal processor to make fault determination; and an output of a programming logic device controls on-off of a breaker. The on-line monitoring system is sensitive and reliable; and moreover, safe operation of an intelligent capacitor can be guaranteed.

A system for wastewater treatment process control comprising a set of measuring means arranged to obtain a dataset, the dataset comprises a plurality of process variables related to a parameter of the wastewater treatment process; a prediction module arranged to receive the dataset and predict the parameter of wastewater treatment process based on a soft sensor; a troubleshooting module arranged to compare the predicted parameter with a predetermined criterion; wherein if the predicted parameter does not satisfy the predetermined criterion; the troubleshooting module is operable to identify at least one process variable from the plurality of process variables which causes the predicted parameter not to satisfy the predetermined criterion and determine whether the identified at least one process variable from the plurality of process variables is controllable. An optimisation module for use in a wastewater treatment system is also disclosed.

The invention discloses a public opinion analysis method based on probability feature association. The method comprises the steps of 1, collecting long-term information of a certain news event, and obtaining long-term feature word items in the long-term information to form a long-term dictionary of the text information; 2, obtaining a current feature set formed by the feature word items of the current news text information; 3, adopting the current feature word items as the center, arranging a circular association gate according to the radius of the certain association gate, and obtaining a feature set of the feature word items inside the association gate; 4, obtaining the association probability between word vectors of the long-term feature word items inside the association gate and word vectors of the current feature word items; 5, calculating an optimal feature weight of the current feature word items and a corresponding optimal current feature weight vector, and adopting the optimal current feature weight vector for a soft sensor model for performing situation estimation on the current news event, and obtaining situation fusion estimation and whole feature expression of the current news event. The event situation estimation fusion effect is improved, and the situation estimation is more reliable.

A method and apparatus for simulating the operation of a rechargeable battery. A value is obtained for at least one parameter that describes an internal state of the battery. The obtained value is used for calculating a prediction value for a characteristic of the battery that is observable outside the battery. These steps are repeated a multitude of times in order to simulate the operation of the battery over a certain period of time. A difference is detected between a calculated prediction value and a known value of a corresponding characteristic in a corresponding situation. The obtained value of the at least one parameter is corrected before a further prediction value is calculated by an amount that is proportional to the detected difference.

The invention discloses a method for screening sensitive variables influencing product quality in a complex industrial process based on step-by-step reduction, which belongs to the technical field ofsoft measurement and comprises the following steps of: selecting auxiliary variables influencing the product quality through expert knowledge and collecting data samples; calculating an auxiliary variable sensitivity index by comprehensively considering the variable correlation and the sensitivity of the variable to the working condition change, and preliminarily screening the sensitive variable influencing the dominant variable; and constructing a weighted cosine Mahalanobis system, and accurately screening key sensitive variables influencing the product quality. According to the method, thecorrelation and the working condition information of the variables can be accurately reflected, meanwhile, the redundancy of the variables is well reduced, the product quality prediction precision canbe improved, the complexity of the prediction model can be effectively reduced, and the method also has important significance for maintenance of the soft sensor model.

The invention discloses a multi-motion-pattern soft crawling robot. The multi-motion-pattern soft crawling robot comprises a first soft driver, a second soft driver and a third soft driver which are sequentially connected, a soft sensor located at the front end of the first soft driver, front feet located below the first soft driver, and rear feet located below the third soft driver, wherein eachsoft driver comprises a multi-air-bag structure and a bottom structure located at the bottom of the multi-air-bag structure. In combination with trapezoidal-cavity multi-air-bag type drivers and a soft tactile sensor, the multi-motion-pattern soft crawling robot is provided, multiple motion patterns such as crawling, crossing and climbing can be self-adaptively finished in a complex environment, and the robot has good environmental adaptability.

The invention describes a method for predicting a parameter of wastewater treatment process. The method comprises the following steps: obtaining a data set comprising a plurality of process variables related to the parameter of the wastewater treatment process; obtaining a predetermined number of measurement values of the parameter to be predicted; preprocessing the obtained data set, wherein preprocessing steps comprises classifying the data set into input groups which comprise the data set and the measurement values of the parameters to be predicted; obtaining a synthesized output at each soft sensor; averaging the synthesized outputs of each soft sensor crossing the soft sensors; and setting the synthesized output after the averaging as a final prediction parameter.

A method for on-line soft measurement of coal-fired carbon oxidation factor of power generation boiler include such steps as selecting key variables, coal property parameter and boiler/unit property parameters as input vectors of soft measurement model, selecting them as input vectors, selecting them as input vectors, and selecting them as input vectors of soft measurement model. At the same time,the parameters of ash and fly ash after coal combustion are measured, and the carbon oxidation factor is calculated as the output vector of the soft sensor model. An on-line soft-sensing model of carbon oxidation factor was established, After establishing the soft-sensing model of coal-fired carbon oxidation factor of power generation boiler, if on-line measurement of coal-fired carbon oxidationfactor under a certain operating condition is required, only the measurement data of the following variables are assigned to the input vector X, and the calculated y is the carbon oxidation factor OFdifferent kinds of coal under different boiler loads. The invention modifies the carbon oxidation factor issued by the Intergovernmental Panel on Climate Change, so that the result is closer to the actual value. It can realize on-line measurement, real-time monitoring and boiler carbon combustion control of coal-fired boilers.

A thin, soft sensor array system that can be deployed over the surfaces of bag bioreactors. The sensor array is fabricated using microfabrication processes along with functionalization methods necessary for measuring pH, glucose, and temperature. Miniature integrated circuit (IC) components are incorporated with the thin-film circuits, allowing for the real-time, on-board data analysis and wireless data communication.