40results about How to "Implement soft sensing" patented technology

The invention relates to a soft sensing method for load parameters of a ball mill. The method is that a hardware supporting platform is used to obtain vibration signals, vibration sound signals and current signals of a ball mill cylinder to soft sense ball mill internal parameters (ratio of material to ball, pulp density and filling ratio) characterizing ball mill load. The method comprises the following steps that: the vibration, the vibration sound, the current data and the time-domain filtering of the ball mill cylinder are acquired, time frequency conversion is conducted to the vibration and the vibration sound data, kernel principal component analysis based nonlinear features of the sub band of the vibration and the vibration sound data in frequency domain are extracted, nonlinear features of the time domain current data are extracted, feature selection is conducted to the fused nonlinear feature data and a soft sensing model based on a least squares support vector machine is established. The soft sensing method of the invention has the advantages that the sensitivity is high, the sensed results are accurate, the practical value and the popularization prospect are very good, and the realization of the stability control, the optimization control, the energy saving and the consumption reduction of the grinding production process is facilitated.

The invention relates to a robust random-weight neural network-based molten-iron quality multi-dimensional soft measurement method which belongs to the blast-furnace smelting automatic control field, in particular to a Cauchy distribution weighted M-estimation random-weight neural network (M-RVFLNs) based method for multi-dimensional parameter-dynamic soft measurement of the molten-iron quality in the blast-furnace smelting process. According to the method of the invention, the principal component analysis (PCA) method is adopted to chose main parameters which affect the blast-furnace molten iron quality as model input variables, a molten-iron quality multi-dimensional dynamic prediction model which has an output self-feedback structure and takes into account input-output data at different moments is constructed, and it is possible to carry out multi-dimensional dynamic soft measurement of the main parameters Si content, P content, S content and molten iron temperature which represent the blast-furnace molten iron quality. The method of the invention comprises the following steps of (1) choosing auxiliary variables and determining model input variables and (2) training and using the M-RVFLNs soft measurement model.

The invention provides a method for soft measurement of the effluent total phosphorus (TP) in the sewage disposal process based on the neural network, and belongs to the field of sewage disposal field. The mechanism is complex in the sewage disposal process, and to enable a sewage disposal system to be in a good running working condition and to obtain the higher effluent quality, the procedure parameters and the water quality parameters in the sewage disposal system need to be detected. The invention provides a soft measurement model established based on the self-organization radial-based neural network to solve the problem that the effluent total phosphorus of a current sewage disposal plant cannot be obtained in real time. The initial structure and the initial parameters of the neural network are determined according to the self-organization method, the structure of the neural network is simplified, and real-time soft measurement is carried out on the effluent TP. According to the soft measurement result, the related control link in the sewage disposal process and materials in the biochemical reaction are adjusted, the quality of the effluent obtained after sewage disposal is improved, and a theoretical support and a technological guarantee are provided for safe and stable running in the sewage disposal process.

The invention discloses a soft measuring method of product quality of an industrial fluidized bed gas-phase polyethylene device. The method comprises the following steps: selecting a plurality of key variables influencing product quality to set up a process detection variable set; applying the projection principle of multivariate statistics to establish a soft measuring model between product resin melt index and density and process detection variables; adopting a nonlinear partial least square method of embedded Taylor series approximation (used for carrying out process nonlinear characteristic representation) as core technology; and determining the number of optimal pivot elements through cross check technology. The soft measuring method avoids complex process mechanism analysis and has convenient site implementation and high precision of soft measuring; therefore, the method is particularly suitable for nonlinear industrial occasions with high dimension and abundant progress data similar to the industrial fluidized bed gas-phase polyethylene production device. Moreover, the soft measuring method can be used for real-time monitoring or production guidance to improve product quality, increase output and ensure smooth device operation, thereby bringing greater economic benefits.

The invention discloses an oxygen content detecting method for boiler fuel gas of a coal-fired power station. The oxygen content detecting method includes: step 1, acquiring and preprocessing primary data; step 2, screening variables; step 3, selecting training samples; step 4, establishing at least square supported vector machine model; step 5, comparing relation between an output value of a soft-measuring model and a measured value of a zirconia sensor, and selecting one of the output value and the measured value as a detecting value of a fuel gas oxygen content detecting system. The oxygen content detecting method has the advantages of no added hardware equipment, good reliability, sufficient precision and the like, and can realize precise measurement for oxygen content of the fuel gas of large boilers.

The invention discloses an energy-saving control-oriented hybrid electric vehicle energy and heat integrated model, and belongs to the technical field of hybrid electric vehicle modeling. The invention aims to provide the energy-saving-control-oriented hybrid electric vehicle energy and heat integrated model of each power transmission node module in a power chain from a power driving device such as an engine and a motor to wheels. A model establishing method comprises the steps of determining power chain input, describing an energy flow state in the power chain, establishing a battery model, establishing an engine energy consumption and temperature model, establishing an air conditioner heat transfer model, receiving a heat chain input instruction and establishing a cockpit temperature model. According to the method, the coupling relation among the cab heat supply requirement, the driver power requirement and the vehicle energy consumption under the high and cold weather condition is established, the soft measurement of part of important thermodynamic variables is achieved, and support is provided for driver comfort evaluation.

The invention provides a method for detecting the length of a calcium carbide furnace electrode. The method comprises the steps: obtaining a non-linear prediction model of electrode consumption according to a model training sample set, wherein electrode temperature T, electrode power P, a furnace charge ratio R and calcium carbide output G are sample input variables, and the electrode consumption is a sample output variable; determining electrode consumption in a current working condition according to the non-linear prediction model of electrode consumption; and determining the length of an electrode according to the electrode consumption in the current working condition. The method can monitor the position changes of an electrode in real time and then guide pressing and releasing for electrodes, so the pressing and releasing amount for electrodes can be accurately controlled, and electrodes are made to work in a balance manner. The method guarantees stable production and energy-saving operation of a calcium carbide furnace.

The invention relates to a method for detecting hydroquinone in compost on line, which comprises putting a biosensor in measured solution, utilizing an electrochemical analyzer to analyze current variation data which are adopted by the biosensor, getting response current change characteristic values, response current stabilization time and steady-state current values, outputting the parameter values in a neural network analysis apparatus, and getting the concentration value of hydroquinone after analyzing and calculating. The invention also relates to an on-line detection system which is used in the detecting method, which comprises a three-electrode device, an electrochemical analyzer and a neural network analysis apparatus, wherein the three-electrode device is connected with the electrochemical analyzer, and the electrochemical analyzer is connected with the neural network analysis apparatus, the three-electrode device utilizes a carbon paste electrode which decorates a laccase-Fe3O4 magnetic nano-particle cross-linking body to a working electrode. The one-line detection method and the on-line detection system have the advantages of convenience, high effective, sensitivity, strong anti-interference capability, low production cost and the like.

The invention provides a knowledge-based robust effluent ammonia nitrogen soft measurement method, and belongs to the field of sewage treatment. As the urban sewage treatment process is complex in mechanism and serious in uncertain interference, and it is difficult to detect the current effluent ammonia nitrogen concentration and it is hard to establish an accurate mathematical model, a robust soft measurement method urgently needs to be researched. A fuzzy neural network based on modeling error probability density function distribution is utilized to establish a soft measurement model of effluent ammonia nitrogen concentration: to begin with, establishing a robustness criterion based on modeling error probability density function distribution; and then, adjusting parameters of the fuzzy neural network based on an adaptive gradient descent algorithm until the model meets the requirement of information processing. The method realizes accurate measurement of the effluent ammonia nitrogenconcentration, helps to improve the monitoring level of the effluent ammonia nitrogen concentration in the urban sewage treatment process, and provides necessary guarantee for stable and efficient operation of the sewage treatment process.

The invention relates to a blasting bead wall material capable of regulating and controlling bursting pressure and a method for measuring the bursting pressure of a blasting bead, which belong to thetechnical field of blasting bead production. The wall material is prepared from the following raw materials in parts by weight: 100 parts of deionized water, 1 to 4 parts of colloid, 4 to 10 parts oftoughening agent, 0.05 to 1 part of filling agent and 0.1 to 1 part of edible pigment, wherein the colloid is selected from one or a mixture of more of carrageenan, gelatin, Arabic gum and pectin; andthe toughening agent is selected from one or a mixture of more of glycerol and sorbitol. The bursting bead prepared from the wall material has the advantages that under the condition of ensuring theflowability, the bursting pressure of the bursting bead can be controlled within the range of 6-10 N/mm, and the bursting bead has stronger environmental adaptability and better stability; meanwhile,soft measurement of the bursting pressure of the blasting bead is realized, and experiments prove that the fitting degree of the actual bursting pressure and the bursting pressure calculated by utilizing the pressure index is high, so that the method can be applied to prediction of the bursting pressure for preparing the blasting bead.

The invention discloses a steel mill gas sulfur content soft measurement method. The theoretical dry flue gas amount generated by unit volume of gas combustion is directly calculated through the gas heat value, the actual dry flue gas amount generated by unit volume of gas combustion is further obtained by combining with flue gas oxygen content calculation, and finally the sulfur content of the gas is calculated by combining with the SO2 emission concentration in the flue gas. The measuring method is particularly suitable for gas combustion equipment such as a gas boiler. The sulfur content ofthe coal gas can be deduced reversely by means of online monitoring SO2 emission concentration, coal gas heat value configured by combustion equipment, flue gas oxygen content and other online measurement data, and therefore online soft measurement of the sulfur content of the coal gas is achieved. Compared with a traditional measurement method, the calculation precision is not reduced, but the solving process is greatly simplified.

The invention discloses a coal-fired boiler NOX soft measurement method based on a whale algorithm for optimizing a long-short term memory network. The method comprises the following steps: analyzing and selecting related auxiliary variables according to an NOX generation mechanism and a boiler combustion process; extracting data corresponding to the auxiliary variables from a DCS (Distributed Control System) of the coal-fired power plant and carrying out data preprocessing; carrying out secondary screening on the auxiliary variables by adopting a principal component analysis method, and solving each principal component and the contribution rate thereof; adding a whale optimization algorithm, and obtaining a proper hyper-parameter value through optimization; substituting the hyper-parameter values into the network, and constructing a coal-fired power plant boiler NOX soft measurement model of the whale algorithm optimized long-short term memory neural network; taking the obtained data of the auxiliary variables as input, obtaining a soft measurement value of the NOX content through a coal-fired power plant boiler NOX soft measurement model, and assisting hard measurement equipment by establishing the soft measurement model. The defects of traditional equipment are overcome, and the economic cost of production monitoring is reduced.

The invention belongs to the technical field of petrochemical engineering, and provides an automatic control method for hydrogen supplementing of an intermittent polypropylene device based on soft measurement. A programmable controller is used for calculating a hydrogen dissolution amount according to temperature and pressure of a high pressure propylene storage tank, the responded dissolution concentration in the tank according to built-in hydrogen-propylene phase balance data, and the total flow of high-pressure recovered propylene into a next kettle, finally, the amount of fresh hydrogen needed to be supplemented is calculated according to the required amount of hydrogen, and the corresponding amount of hydrogen is automatically supplemented. According to the method, human experience factors in operation can be reduced, produced polypropylene products are more stable, and the polypropylene products with the corresponding grades can be produced more accurately.

The invention provides a rotor revolving speed and displacement soft measurement method of a bearingless permanent magnet synchronous motor, which creates conditions for realizing real-time online control of torque and radial suspension force of the bearingless permanent magnet synchronous motor and is suitable for high-performance control of the bearingless permanent magnet synchronous motor. Inorder to construct a relation among the rotor revolving speed and displacement and other easy-to-measure auxiliary variables, a soft measurement model which is established based an adaptive BP neuralnetwork is provided, and being different from the conventional parameter self-adaption, the method performs adaptive control for the number of hidden layers of the BP neural network, directly determines least square approximation weight and network precision of the neural network through a weight direct determination method, and can realize adaptive design of a hidden layer structure of the neuralnetwork through comparison with expected precision. The neural network model is not dependent on motor parameters, and thus, detection precision and system reliability are improved.

The invention discloses an online monitoring method for the contact resistance of multiple key contact points in a medium-voltage switch cabinet, and relates to the technical field of power equipment.Finite element software is adopted to analyze and solve the temperature rise under different contact resistance distributions. During simulation calculation, the influence of the contact resistance of each point location on the temperature rise can be fully considered by reasonably setting the contact resistance distribution of different point locations. And neural network training is performed by taking data obtained by simulation as a sample, so the accuracy of a neural network prediction result can be ensured. And finite element software is adopted to analyze and calculate the relationshipbetween the temperature rise of each temperature measurement point and the effective value of the load current. Temperature rise data under different loads are calculated through finite element simulation, and the result obtained through the method is accurate. And fitting is performed according to the obtained data, and the obtained relational expression is accurate and reliable. By adopting theprediction method of the neural network, the contact resistance of multiple key points in the switch cabinet can be predicted at the same time, the prediction result is accurate, the process is rapid, and the problem that the contact condition in the switch cabinet cannot be monitored online is solved.

The invention discloses a soft measurement method for a pichia pastoris fermentation process based on ONLINE-RLSSVM. The soft measurement method comprises the following steps of firstly, analyzing a pichia pastoris fermentation process technology mechanism, selecting appropriate auxiliary variables, and establishing a training sample database according to historical tank batch data; performing pretreatment on sample data, performing normalizing treatment, performing dimension reduction on the auxiliary variables by a principal component analysis method, and using several main component aggregative variables as a training sample database of ONLINE-RLSSVM; and then, using a firefly-fruit fly hybrid optimization algorithm for on-line optimizing a punishment coefficient c and a breadth factorsigma 2, using the training sample database for training the ONLINE-RLSSVM, establishing a soft measurement model, and finally, obtaining an inulase concentration predicted value. The firefly-fruit fly hybrid optimization algorithm is adopted, so that the overall optimization capacity and the prediction precision of the soft measurement model are improved, and the method can be effectively used for guiding the production of inulase.