100 results about "Fuzzy prediction" patented technology

The invention relates to a method and a system for centralized management of an electric saver of a central air-conditioner; a water flow pressure difference sensor between a water supply main pipe and a return water main pipe of a central air-conditioner freezing water system, a flow meter for a two-way freezing water return pipe, a water temperature sensor for a back-way freezing water return pipe of a freezing water pump, the water temperature sensor for a freezing water outlet pipe of an air conditioning mainframe, the water temperature sensor for a cooling water outlet pipe of the air conditioning mainframe and the water temperature sensor for a cooling water inlet main pipe of the air conditioning mainframe respectively collect pressure difference, flow speed and water temperature of the corresponding position; collection values are transferred into a fuzzy controller, the fuzzy controller gains dynamic flow and speed parameters through the control of a fuzzy prediction model and an optimal algorithm model, the dynamic flow and speed parameters are transferred into each electric saver, and the speed and the flow of corresponding fans and water pumps are controlled through the frequency change of the electric saver. The invention has the advantages of the high temperature-adjusting precision, the good dynamic performance, the small mechanical loss, the fully-automatic remote monitoring, the closed-loop control of temperature, the soft starting and stopping of a motor and the optimum system electricity-saving rate.

The invention discloses a statistical analysis method of accelerated life tests based on a fuzzy theory. The statistical analysis method comprises a first step of reasonably fuzzifying failure terminated censoring of constant-stress accelerated life tests, thereby obtaining fuzzy failure data, a second step of building a fuzzy statistical model of the accelerated life tests by use of a maximum likelihood method, and a third step of performing estimation on model parameters and fuzzy prediction on lifetime and reliability. The statistical analysis method is capable of providing the fuzzy estimation values of the model parameters according to the built model and further providing the fuzzy lifetime prediction interval and the fuzzy reliability interval of products; compared with point estimation values provided by a traditional statistical analysis method, the results of the statistical analysis method are more reasonable and have better reference value.

The invention discloses an urban people flow prediction method based on a Seq2Seq generative adversarial network, and the method comprises the steps: abstracting the urban people flow data at different times into image frames, and representing the people flow through a thermodynamic diagram; Dividing the observation data into training data and labels according to time, and converting the problem into an image problem; The idea of WGAN generative adversarial network is generally adopted, a generator generates pedestrian flow in a certain period of time in the future on the basis of historical data by using a Seq2Seq method, and external factors such as weather are added at the same time; The discriminator uses a Waserstein distance to discriminate true and false data; In the training process, the generator and the discriminator are continuously optimized by combining the generative adversarial loss and back propagation. And finally, when the discriminator cannot discriminate the authenticity, the optimized generator is used for predicting the future urban pedestrian flow. According to the method provided by the invention, the generative adversarial network is used for carrying out urban people flow prediction for the first time, and the problems of fuzzy prediction and slow algorithm convergence are solved in combination with external environment factors.

The invention provides a cold-rolled strip steel plate shape prediction control method, comprising the following steps: for cold-rolled strip steel of the same specification, establishing a corresponding plate shape prediction control fuzzy reasoning model; setting fuzzy membership functions of various parameters in the plate shape prediction control fuzzy reasoning model by being combined with the characteristics of influence of rolling force change on the strip steel plate shape; establishing plate shape fuzzy prediction control models by utilizing a Takagi-Sugeno fuzzy model modeling rule; selecting a corresponding plate shape fuzzy prediction control model to carry out online adjustment on a working roller bending device. A dynamic relationship is established among rolling force variation, forward pull variation of a roll mill, backward pull variation of the roll mill, and online adjustment variable of the working roller bending device by using a fuzzy modeling method, the adverse effect of transmission time lag existing between the roll mill body and a plate shape instrument on the plate shape control at the outlet of the cold-rolled strip steel, and two familiar plate shape defects of intermediate waves and edge waves existing in the cold-rolled strip steel products are effectively overcome.

The invention discloses a switching method utilizing a fuzzy prediction model. According to the method, through introducing the fuzzy prediction model, reception signal intensity and the position of a user are predicted, excellent noise tolerance capability is realized, the relatively accurate prediction result can be acquired; through introducing short-period prediction of reception signal intensity of the user in a switching mechanism, a switching target base station and switching opportunity can be determined, and call drop caused by triggering time delay can be avoided; through introducing long-period prediction of the user position in the switching mechanism, locus of the user can be determined, and the ping-pong effect caused by short-period prediction restrictions can be avoided. The method is advantaged in that through introducing the fuzzy prediction model, reception signal intensity and the position of the user are predicted, according to the prediction result, switching opportunity and the target base station are determined, a prediction switching decision mechanism compatible with switching mechanisms in the prior art are employed, and seamless network switching is realized.

The invention discloses a rotor position robust observation method used for a flywheel energy storage system. The rotor position robust observation method comprises the steps of establishing a composite counter electromotive force model sliding-mode observer firstly, and next, by taking composite counter electromotive force estimation value feedback of a current state equation in a two-phase static coordinate as system disturbance, enabling a virtual parameter identification method-based multimode disturbance observer to perform accurate evaluation on the rotor position information; meanwhile,performing fuzzy prediction on the positioning torque of an FSPM motor by the virtual parameter identification method-based multimode disturbance observer, and further improving the positioning torque prediction precision of the FSPM motor through an error online training compensator; and meanwhile, performing control by taking the positioning torque as known disturbance. By virtue of the rotor position robust observation method, the positioning torque prediction value of the FSPM motor can quickly and accurately follow a real value, so that wide-speed-range position-free accurate tracking ofthe FSPM motor used for the flywheel energy storage system in different working condition operating conditions can be realized.

The invention discloses a method and system for predicting a degradation trend interval of a hydroelectric generating set. The method comprises the following steps: based on the historical state monitoring data of the hydroelectric generating set, establishing a set health model by using power and waterhead and set vibration data in fault-free healthy state in a previous period, obtaining a set degradation trend model by using the power and waterhead data in a faulty state in a later period, and finally establishing a fuzzy interval prediction model of the degradation trend of the hydroelectric generating set. Further, structural division is performed on the model, and model parameter optimization is performed by using the coverage of a fuzzy model interval prediction result and a comprehensive index of an interval width. By adoption of the method and system disclosed by the invention, the identification precision of the fuzzy interval prediction model of the degradation trend of the hydroelectric generating set is improved, more accurate identification parameters can be obtained, and the prediction process is simplified.

The invention discloses a fuzzy prediction method of corrosion rate of a transformer substation grounding grid. The fuzzy prediction method comprises the steps of determining the degree of membership according to the correlativity of soil physicochemical indexes and corrosion of the transformer substation grounding grid; determining the corrosion contribution degree of different soil physicochemical indexes on the grounding grid, and calculating the close degree between different areas of transformer substation grounding grids. The problems of a plurality of involved factors, intricate relation, and uncertainty and fuzziness in related factors in prediction of the corrosion rate of the grounding grid are solved by the fuzzy prediction model; poor model prediction accuracy caused by a small sample is avoided at the same time; and the corrosion rate of the transformer substation grounding grid can be rapidly and effectively predicted on engineering as to grounding grid sites which are adjacent in region or in soil physicochemical indexes.

The invention discloses an accelerated degradation experiment modeling method based on a fuzzy theory. The accelerated degradation experiment modeling method comprises the specific steps of 1 utilizing the fuzzy theory to enable degradation data to be reasonably fuzzified so as to obtain fuzzy degradation data, 2 utilizing fuzzy degradation regression to establish an accelerated degradation test fuzzy linear degradation model and 3 performing model parameter evaluation and reliability degree prediction. According to the established fuzzy linear degradation model, a fuzzy evaluation value of a model parameter is given, and a fuzzy life prediction interval and a fuzzy reliability interval of a product are further given. Compared with a point estimated value given by means of a traditional statistical analysis method, the result obtained by means of the accelerated degradation experiment modeling method is reasonable and has reference value.

The invention discloses a base station dormancy method based on traffic prediction and base station state. The method predicts the future traffic load of each base station in the cellular network by introducing a fuzzy prediction model, which has better robustness and may obtain more accurate predicting result. By introducing traffic prediction in the sleep mode of the base station, the proportionof reserved resources of each base station may be reasonably set to improve the utilization of network resources, so that more base stations may switch to the sleep state so as to reduce the networkenergy consumption. Adding state factors of the base station to the value function may reduce the number of times of switching the working state of the base station and improve the stability of the base station state. By introducing a fuzzy prediction model, the invention predicts the future traffic of the base station, dynamically sets the reserved resources of the base station according to the prediction result, performs pre-sorting of the dormancy test on each base station by using the value function, and finally determines the dormant base station in the cellular network, thereby reducingthe network energy consumption.

The invention discloses a short-period wind speed prediction method and a system based on an interval type-2 T-S fuzzy model. The method is characterized by carrying out variational modal decomposition VMD on historical real wind speed observation data and decomposing into K modals, carrying out attribute selection and normalization processing on each modal and establishing a predictive fuzzy model; using interval type-2 fuzzy C regression cluster IT2-FCR to carry out structure division on the model, and taking a weighted root mean square error of actual observation wind speed data and a fuzzymodel prediction result as a target function, and using a gravity search algorithm GSA to carry out model front component parameter optimization; and using a least square method to identify a model parameter so as to acquire a short-period wind speed prediction interval type-2 T-S fuzzy model taking the historical real observation data as input. In the invention, a novel type-2 hyperplane membership function is adopted, identification precision of a wind speed fuzzy prediction model can be increased, an accurate identification parameter can be acquired, and a corresponding wind speed prediction result matches with an actual observation wind speed.

A system and a method for an automated intelligent information mining includes receiving unstructured text from various text sources; extracting multiple key-phrases from the unstructured text; generating template and dynamic information contextual relation maps by mapping the extracted key-phrases to three-dimensional maps using a self organizing map, and a gaussian distribution technique. Further, the technique includes forming word clusters and constructing corresponding key-phrase frequency histograms for each of the generated contextual relation maps. Template and dynamic information three-dimensional structured document maps from the constructed phrase frequency histograms and the generated self-organizing maps. Desired information is extracted by mapping the generated dynamic information three-dimensional structured map onto the template three-dimensional structured map. A fuzzy prediction algorithm is used in possible error correction in extracting the desired intelligent information. A negative learning error correcting algorithm is used to correct the three-dimensional template relation maps depending on the fuzzy feedback.

The invention discloses a method for predicting storage battery faults, and belongs to the field of storage battery fault prediction and diagnosis. The method is characterized in that whether a battery is broken down is predicted according to related data during the battery use process; according to the knowledge-based method for predicting the health status of the storage battery, namely, a fuzzy prediction method, degrees of membership of various faults are solved according to degrees of membership of certain symptoms and used for representing tendency of various faults, and scientific basis is provided for predicting the health status of the storage battery; and the method is proposed in order to effectively predict the faults of the battery and a battery pack, experimental data is obtained with a nickel-cadmium battery serving as an experimental subject, the DOH (degree of health) of the battery or the battery pack in the whole operation process can be obtained through analysis and processing for real-time data of the nickel-cadmium battery, and simultaneously maintenance information of the battery is given. The method is simple and effective, the disassembly and the discharge testing of the battery are avoided, and the accurate battery health level is obtained.

The invention discloses a tunnel gushing risk grade fuzzy prediction method based on a comprehensive advanced geological prediction technology, and the method comprises the steps: 1, building a tunnelgushing risk grade evaluation index system, and building a tunnel gushing risk grade standard and a quantitative judgment standard of each evaluation index; 2, establishing a tunnel gushing risk fuzzy evaluation model; 3, taking a detection result of a comprehensive advanced geological prediction technology of a certain section in front of the tunnel face as an input value; repeating the step 1,substituting each value into the tunnel gushing risk fuzzy evaluation model in the step 2 to obtain a tunnel gushing risk grade prediction model, and taking the gushing risk grade of a certain sectionin front of the tunnel face obtained by the model as a gushing risk grade of a certain range in front of the tunnel face. By adopting the method provided by the invention, the gushing risk grade prediction problem in front of the tunnel face is solved according to the gushing risk grade evaluation result of the tunnel face and the comprehensive advanced geological prediction technology.

The invention discloses a disturbance observer-based MEMS gyroscope combined learning control method, which is used for solving the technical problem that the modal control method of the existing MEMSgyroscope is poor in practicability. According to the technical scheme, the disturbance observer-based MEMS gyroscope combined learning control method comprises the following steps: firstly, designing a disturbance observer, estimating and compensating disturbance so as to reduce buffeting of a slip formwork; and according to fuzzy prediction errors and tracking error, designing the combined self-adaptive rule of fuzzy logic weight, correcting fuzzy logic weight coefficient, thus realizing the effective dynamic estimation of unknown dynamics. Considering the prediction error and tracking error, the effective dynamic estimation of unknown dynamics can be realized by designing the combined learning innovation rule of fuzzy logic weight, correcting fuzzy logic weight coefficient. By combining slip formwork control theory, the feedforward compensation on the unknown dynamics of the MEMS gyroscope can be realized, and the control precision of the MEMS gyroscope can be further improved. Thedisturbance observer is designed to compensate the disturbance in slip formwork control, so that the buffeting of the slip formwork can be reduced, and the practicability is good.

The invention discloses a method for vaguely predicting, compensating and controlling tower top temperature during desulfurization of sintering flue gas. Aiming at the problem that the tower top temperature cannot be stably controlled due to the influence of system time delay and external disturbance during desulfurization of the sintering flue gas, the method comprises the following steps of: building a prediction model of the tower top temperature by using a heat transfer mechanism; designing a vague prediction and compensation controller of the tower top temperature by taking the difference between a prediction value and a set value as input; and compensating water injection quantity by using model rule. By the method, main disturbance in a system is introduced into the prediction model, and a compensation value is calculated according to the difference between the prediction value and the set value, so the problems of poor stability of the system caused by large fluctuation of disturbance factors and the time delay of the system are solved.

The invention discloses a fuzzy prediction control system of a power supply for electrostatic dust collection and a control method of the fuzzy prediction control system. The control method comprises the steps that an analog signal acquisition unit converts an acquired analog signal to an electrical signal, and outputs the electrical signal to a T-S fuzzy controller after carrying out conditioning such as filtering on the electrical signal, and the T-S fuzzy controller first recognizes a first component and a conclusion part of a T-S fuzzy model according to the conditioned signal, obtains the T-S fuzzy model, then converts the T-S fuzzy model to a step response model, and outputs the step response model to a prediction controller 23 to act as a prediction model; the prediction controller takes the step response model as the prediction model, carries out rolling optimization and feedback compensation, and outputs a control signal to a digital logic unit; and the control signal passes the digital logic unit and then acts as a driving signal of a control driving unit to carry out fuzzy prediction control on the power supply. The problem that a mathematical model can not be established easily for an electrostatic dust collection system is solved, and the dependence of the prediction controller on the accurate mathematical model is reduced.

The invention discloses a subway transfer channel traffic state fuzzy prediction method, which comprises the following steps: forming a collection environment by cameras arranged at an entrance and an exit of a subway transfer channel; calculating average travel time that passengers pass through the subway transfer channel according to the time that the passengers pass through the entrance and the exit and which is recorded by the cameras; identifying and eliminating the abnormal values of data recorded at the average travel time; making up the missing data of the average travel time; calculating the time duty ratio corresponding to the arriving time of each subway at that day; carrying out traffic state fuzzy division on all time duty ratio data recorded at that time and before that time by applying a fuzzy C-mean clustering analyzing method according to the preset traffic state, so as to obtain a fuzzy set; calculating Gaussian subordinate function parameters corresponding to each cluster; selecting a first order Sugeno fuzzy inference system as a prediction model basic frame; establishing a fuzzy prediction model for prediction through learning training samples; and carrying out defuzzification on a prediction result, and finally outputting an accurate value and a fuzzy value of the traffic state prediction result.

The invention discloses a thermal power generating unit mechanical furnace coordination control method based on improved T-S fuzzy prediction modeling. The method comprises utilizing a fuzzy clustering method to determine the optimal number of clusters; identifying the parameters of a T-S fuzzy model based on a least square method; and finally designing a multi-step prediction controller. The thermal power generating unit mechanical furnace coordination control method can guarantee good adjusting quality and higher robustness within the whole working condition range when making a mechanical furnace coordination control system to adjust the load in the large range of the thermal power generating unit, thus being significant in improving the operation performance of a power generation system. The prediction algorithm can realize organic fusion of T-S fuzzy modeling and multi-step prediction control, and can realize prediction control of the mechanical furnace coordination system, and is advantaged in algorithm and high in the prediction precision.

The invention discloses a thermal load control method for a combined heat and power supply system of a micro gas turbine based on robust fuzzy prediction control, which comprises the steps of acquiring input fuel quantity and hot water temperature data of the combined heat and power supply system of the micro gas turbine, and establishing a T-S fuzzy affine model of the thermal load control process; establishing a global amplification state T-S fuzzy model of the thermal load control process; establishing an off-line fuzzy observer based on the global amplification state T-S fuzzy model; and establishing a robust fuzzy prediction controller based on the global amplification state T-S fuzzy model and the off-line fuzzy observer. According to the method, the influence of system nonlinearityon the controller is weakened by using the T-S fuzzy model, the problem that the state cannot be measured is solved by using the observer, steady-state errors are overcome by using state amplification, the degree of freedom of the controller is enhanced, and the method is a high-quality stable model prediction control method suitable for an actual complex industrial process.

When used for treatment ray projection, a respiration synchronous tracking system can monitor the respiration of a patient and compensate tumor target movement. Time delay exists between the command and the response of the treatment ray projection system, and the delay can cause accidental even dangerous vibration. In order to increase the performance of synchronous tracking, the signal prediction technology can be used for making up the time delay. The invention provides a fuzzy new prediction method and a predictor for a position signal of a new synchronous respiration tracking system. The predictor can handle the problem of the amplitude and the frequency changing along with time, and well solve the problem of synchronous tracking during radiation therapy.

The present invention discloses a fuzzy forecasting model based method for detecting pulp concentration in an ore grinding process of a dressing plant. The ore grinding concentration and overflow concentration are predicted and estimated online by using a fuzzy model construction method based on soft computing, a characteristic variable set in a forecasting model is established based on applying an attribute set evaluation metric based on neighborhood decision resolution and a characteristic set selection method on field record data, a fuzzy scheme is established based on applying the fuzzy scheme construction method based on an effective information rate on the field record data, and a prediction rule is obtained by performing fuzzy prediction rule extraction on the field data. By means of the method provided by the present invention, the subjectivity and limitation of a conventional fuzzy modeling method are avoided, a stable and reliable prediction result can be provided for the detection of a key parameter in the ore grinding process of the dressing plant, and a basis is established for the optimization control and process monitoring of the ore grinding process.

The invention discloses a reliability fuzzy prediction method based on hierarchical division of a welding robot system. The method comprises the following steps: firstly, the appointed hierarchical division is performed for the welding robot system to determine subsystems of the robot system and modules and parts included in all the subsystems; a reliability block diagram of the robot system is built; a reliability mathematical model of the system is built; the total failure rate of the subsystems is determined and controlled; grading coefficients of all the subsystems are determined; the failure rates of other unknown subsystems are determined according to the failure rates of the known subsystems and the grading coefficients of the subsystems; and the total failure rate, namely the MTBF value of the welding robot system can be obtained according to the reliability mathematical model of the welding robot system. The method has no need to perform the reliability prediction for all parts of the welding robot system, and meanwhile, adopts the fuzzy theory and eliminates the defects in a traditional expert grading method to provide new thoughts for reliability prediction of complex electromechanical systems.

The invention discloses a self-cleaning type central air conditioner based on a fuzzy prediction algorithm. The self-cleaning type central air conditioner comprises a fan fence box, a driving motor, a dust collection slope plate, an air conditioner shell body, a heating box and a filter, a partition plate is installed on the inner wall of the air conditioner shell body, two sets of splash-proof dust collection boxes are installed on the surface of the top of the partition plate, two sets of longitudinally-arranged cleaning plates are installed on the top wall of the interior of the air conditioner shell body, a heating box is installed on the bottom wall of the interior of the air conditioner shell body, the filter is installed on the back face of the heating box, a storage battery box is installed on the bottom wall of the interior of the air conditioner shell body, the storage battery box is located on one side of the heating box, a water-cooling barrel is installed on the bottom wall in the interior of the air conditioner shell body and, the water-cooling barrel is located behind a compression refrigerating machine. According to the self-cleaning type central air conditioner based on the fuzzy prediction algorithm, the storage battery box is arranged, storage can be carried out on the electric quantity when the electricity consumption peak is relatively low and the electricity price is low at night, then use of electric quantity when the electricity consumption peak is high and the electricity price is relatively high in the daytime of the next day is reduced, and therefore the overall electricity consumption cost of the air conditioner is reduced.