35results about How to "Realize automatic tuning" patented technology

The invention discloses a method for self-adjusting control parameters of a speed ring of a permanent magnet synchronous motor based on fractional orders. An integer-order proportional integral (PI) controller in an alternating current servo system of the permanent magnet synchronous motor is replaced by a fractional-order PI controller, parameters of the fractional-order PI controller are automatically adjusted, and the alternating current servo system of the permanent magnet synchronous motor can be controlled. The method specifically comprises the following steps of: firstly, acquiring current and speed signals of the alternating current servo system; secondly, identifying a speed ring controlled object model of a permanent magnet synchronous motor servo system according to the acquired signals, and identifying the parameters of the model; and finally, optimally adjusting the control parameters, and thus obtaining optimal control parameters. According to the method, the original integer-order PI controller is replaced by the fractional-order PI controller, and the parameters of the controller are automatically adjusted; the parameters of the controller are optimized by using a pattern search algorithm; and the adjusted parameters of the controller are high in robust, high in anti-disturbance capacity and high in control accuracy.

A relay feedback based AC servo system automatic setting method belonging to the motion control technology field comprises a speed ring setting process and a position ring setting process. The method comprises the following steps: setting the parameters of saturated relay with delay; bringing the relay identification link into the closed speed ring (or position ring) to cause the system to establish a limit ring quickly; evaluating the system delay and the limit oscillation period parameter; identifying the AC servo system model; and setting the PID control parameter automatically by the PID parameter setting principle such as pole assignment method and amplitude phase margin method according to the identified model parameters; By combining the saturated relay feedback and he PID parameter setting principle such as ITAE method and amplitude phase margin method, the invention can accomplish the parameter automatic setting to the controller of AC servo motor.

The invention discloses a neural-network self-correcting control method of a permanent magnet synchronous motor speed loop. The method is characterized by: taking a current loop and a motor as generalized objects; firstly, collecting information, such as a rotating speed, a current and the like; using an adaptive linear time-delay neural network to carry out off-line parameter identification to the motor; then, taking a weight obtained through off-line learning as an initial value of on-line learning; finally, carrying out on-line parameter identification to the system, calculating a load torque of the motor according to the identified parameter; designing a neural-network self-correcting control law according to the obtained parameter value and a load disturbance value, adjusting the network weight on line according to an error between a controlled object and an identification model, and then setting the parameter of the neural-network self-correcting controller on line so as to realize online adjustment of the controller parameter. Uncertainty of the system and influence brought by the external disturbance can be eliminated. Dynamic performance and an anti-disturbance ability of a servo system can be improved.

The invention discloses a HBase configuration parameter automatic tuning method, a HBase configuration parameter automatic tuning device and user equipment, the method comprises the following steps: after acquiring a HBase database configuration parameter, firstly generating multiple groups of HBase configuration files randomly according to the HBase configuration parameter, then, simulating load,completing the same number of parameter configuration according to the generated multiple groups of HBase configuration files, generating a parameter throughput matrix, constructing a performance model based on a random forest according to the parameter throughput matrix, finally, inputting the performance model into a genetic algorithm, and acquiring an optimal HBase configuration parameter through iterative computation of the genetic algorithm. Obviously, by application of the embodiment of the invention, automatic tuning of HBase configuration parameters can be realized without dependenceon personal capability and experience of an implementer, and working performance is improved greatly.

The invention discloses a method, a device and a system for automatically adjusting and optimizing parameters of a key value pair storage engine, which can solve the problem that the system performance is reduced due to default parameter configuration caused by change of workload in a key value pair storage system. The method comprises the steps of preprocessing parameters according to a parameterconfiguration mode in a key value pair storage engine, and constructing a Restful service framework; constructing a Deep PILCO reinforcement learning model based on the model; operating the workloadof the upper database system, generating data and training a model; loading the model, outputting parameter configuration generated by the strategy for the input workloads, and applying the parameterconfiguration to a bottom key value pair storage engine. The invention is applied to a database system with a log structure merging tree as a storage engine and a scene where the workload changes frequently.

The invention, which belongs to the field LF furnace electrode regulator field, relates to a multi-model LF furnace electrode adjusting method based on steel type clearance slag thickness. With the method, problems that the sensitivity of the controller is low and the network is not suitable for a real-time control system can be solved. Input data of an electrode regulator are collected, wherein the data include a three-phase secondary side current and three-phase secondary side voltage that are obtained by direct measurement, an initial current setting value of the electrode regulator, and data of the steel type, clearance, and slag thickness for setting a PID controller; according to the data, parameters of the PID controller are set in an on-line mode; static parameters of the set PID controller as well as the data of the steel type, clearance, and slag thickness are recorded, and an LF electrode PID setting model set is established; and after establishment of the PID setting model set, data of the steel type, clearance, and slag thickness are inputted, determination is carried out, and a proper model is invoked automatically. Therefore, optimization of an original control system is realized, thereby substantially improving the on-line adjusting process of the system and realizing better control of the electrode.

The embodiment of the invention provides a super parameter tuning method, an apparatus and a device. The method comprises the following steps: determining a super parameter to be determined; acquiringa preserved super-parameter candidate value combination, wherein the super-parameter candidate value combination comprises a plurality of candidate values of the super-parameter to be determined; traversing each candidate value of the super-parameter to be determined in the super-parameter candidate value combination, and assigning the candidate value to the function parameter in the establishedmodel function, wherein the function parameter is the super-parameter to be determined; running a training model including the model establishing function, and obtaining the model after training; determining the model score corresponding to the model after training; selecting the maximum value of all model scores, wherein, all model scores include the model scores corresponding to each candidate value; the maximum value is determine to be that value of the super-parameter to be determine. The super parameter tuning method, the apparatus and the device provided by the embodiment of the invention can realize the automatic tuning of the super parameter and reduce the complexity of the super parameter tuning process.

The invention discloses an automatic setting and optimizing method for working parameters of an automatic quantitative packing scale, and relates to the field of automatic quantitative packing scales.The method comprises the steps that a feeding test of whole-process slow feeding is conducted, and then a feeding test of rapid feeding and then slow feeding is conducted; in the two feeding tests, according to the obtained target weight and the slow feeding stable duration, a plurality of key node data are obtained, and according to the obtained key node data, automatic setting and automatic optimizing of two important parameters of the rapid feeding end weight and the slow feeding end weight can be achieved. According to the automatic setting mode, the dependence on the technical level of an operator is eliminated, the complexity factor of material characteristics is eliminated, and the accuracy and the efficiency are high; the automatic quantitative packing scale can exert the speed tothe maximum extent under the condition that the national specified precision requirement is met; and meanwhile, whether the whole parameter setting and optimizing process is stable and reliable or not can be automatically judged, and the trust condition is met.

The invention provides an excitation system PSS parameter setting method and a device and belongs to the technical field of an excitation system. The method comprises steps that the uncompensated phase-frequency characteristic data of the excitation system is acquired; multiple sets of PPS parameters are acquired from a preset PSS parameter sample database, and multiple sets of PSS compensation angle data are respectively determined according to the multiple sets of PPS parameters; the multiple sets of PSS compensation angle data and the uncompensated phase-frequency characteristic data realize superposition at each frequency point position respectively, and multiple sets of compensation phase-frequency characteristic data are generated; the target compensation phase-frequency characteristic data in a value range of -120-60 DEG is acquired from the multiple sets of compensation phase-frequency characteristic data; PSS parameters corresponding to the target compensation phase-frequency characteristic data are determined to be to-be-used PSS parameters of the excitation system. According to the method, problems that PSS parameters acquired through a trial-and-error approach in the prior art are not more-optimized PSS parameters and the PSS parameter setting process is relatively more complex and tedious are solved.

The invention provides a method for automatic adjustment of a linpack performance test. The method specifically includes the following steps that the theoretical value and expected value of CPU performance are calculated; the N value and the NB value are continuously adjusted, and automatic adjustment of the linpack performance test is achieved. The invention further provides a system for automatic adjustment of the linpack performance test. The system comprises a CPU performance value calculation module and an automatic optimization module, wherein the CPU performance value calculation module is used for reading the information of the core number, the number and basic frequency of a CPU, and calculating the theoretical value and expected value of the CPU performance; the automatic optimization module is used for modifying the NB value and N value of a configuration file, wherein N represents the operation order of a linpack, and NB represents the size of a solved matrix block. Automatic optimization of the linpack performance test can be achieved, automated configuration is achieved, automatic running of the test is achieved, the optimal result is output, it is unnecessary to artificially modify the configuration file, the labor resource and the time resource of the test are saved, and simplification and automation of the test are achieved.

The invention discloses a steering wheel zero offset self-learning unmanned vehicle trajectory tracking method. The method comprises a road line type fitting algorithm, a steering wheel zero offset estimation algorithm and a vehicle kinematics model control algorithm. The road line type fitting algorithm uses a section of expected road point sequence in front of a vehicle as input to fit road linetype parameters. Steering wheel zero offset is estimated by a steering wheel zero offset estimation algorithm according to the current and historical road line type parameters. A vehicle kinematics model control algorithm is combined with the road line type parameters, the steering wheel zero offset and the vehicle kinematics model to calculate and output a steering wheel angle for vehicle trajectory tracking control. The method aims to improve the intelligent level of unmanned vehicle trajectory tracking control and improve the tracking precision.

The invention provides an automatic optimization and network pressure test method and system. The method comprises the following steps: configuring server information; the server starts network service; configuring client information; creating a test folder based on preset time; starting a client network service, and executing a test process; and recording and storing the test process log in realtime until the test is finished. The client automatically creates an appropriate test result directory, automatically performs testing according to a unified standard, and stores a test result; and when the specified test is often finished, the script automatically stores information such as the current test log, the server log and the client log in the created test folder without complex manual operation. In the testing process, the situation that the bandwidth of network testing does not reach the highest value due to omission of steps is avoided. And when overload occurs in the test process, dynamic adjustment can be performed, so that the network can reach a balanced range, and a reference is provided for later adjustment of the communication network.

The invention discloses a self-iteration situation prediction method and system based on a data center station, and the method comprises the following steps: S1, data preprocessing; s2, situation assessment; s3, situation prediction; s4, carrying out self-iteration optimization; and S5, binding the situation presentation component. According to the method, the following problems in the prior art are solved: aiming at original security data with wide sources, complicated types and heterogeneous formats, a single fixed situation evaluation and prediction algorithm is difficult to accurately analyze a situation development trend in massive multivariate heterogeneous network security data; the efficiency and efficiency of network security situation assessment and prediction are low.

The invention discloses a control method of a hydrogen fuel cell emergency power supply system, and the method comprises the following steps: judging a power grid voltage state according to a power grid input end voltage value, and entering a power grid mode if the power grid has a voltage; carrying out the power supply switching according to the SOC value of the energy storage unit in the power grid mode; if the power grid has no voltage, further judging whether the voltage exists in the previous step time, and if the voltage exists before the previous step time, entering a power-off mode; in the power-off mode, carrying out the power supply adjustment through the power of the hydrogen fuel cell and the SOC value of the energy storage unit; if no voltage exists before the previous step time, entering an off-grid mode; in the off-grid mode, carrying out the power supply adjustment according to the SOC value of the energy storage unit, the load power and the hydrogen fuel cell power. According to the invention, electric energy is rapidly provided when the power grid is powered off, the control precision is high, the threshold SOC values of different types of energy storage units can be automatically set, and the control performance is better; and mutual matching of operation and environment of the hydrogen fuel cell emergency power supply system can be ensured.

The invention discloses a distributed storage system parameter adjusting method and device, equipment and a medium. The distributed storage system parameter adjusting method comprises the steps of: acquiring a neural network model which is created in advance according to data obtained by interaction between a vdbench client and a storage cluster and is used for evaluating a time delay size; determining actual internal state data of the current storage cluster, wherein the actual internal state data comprises interface time delay data of ganesha; and searching a target parameter enabling an output value to be maximum according to the actual internal state data by utilizing the neural network model, and adjusting parameters of the current storage cluster according to the target parameter, wherein the output value is in negative correlation with the time delay of a client. According to the distributed storage system parameter adjusting method and the device, the neural network model for evaluating the time delay can be created, the actual internal state data of the storage cluster can be obtained, the target parameter capable of maximizing the output value can be searched based on thecreated neural network model, the target parameter capable of minimizing the time delay can be obtained so as to adjust and optimize the storage cluster, and the automatic adjustment and optimizationof the storage cluster can be realized.

The invention discloses an intelligent PID (Proportion Integration Differentiation) control method. The method comprises the following steps: acquiring initial control parameters set by a user and working parameters of a control unit; the acquired working parameters are transmitted in real time; the working parameters are correspondingly adjusted in real time according to the working parameters transmitted in real time, so that the working parameters are consistent with the set values; taking a set target value and an actual value deviation e of the regulation and control parameter object as an input quantity; comparing working parameters in the working links according to a preset program; the input quantity is subjected to proportional control, integral control and differential control, and the output quantity is synthesized; according to the intelligent PID control device, the single-chip microcomputer serves as a control unit, PID control is achieved through an intelligent algorithm, automatic PID parameter setting and automatic combination of proportional differential (PD), proportional integral (PI) and PID control modes can be achieved through the intelligent PID control device, and the intelligent PID control device is high in control precision, convenient and rapid to use and high in execution efficiency.

The embodiment of the invention provides an adjusting and optimizing method and device for MPI parameters, a storage medium and electronic equipment. The adjusting and optimizing method comprises the steps of randomly selecting an unselected non-universal parameter combination from multiple non-universal parameter combinations; under the condition that the non-general parameter combinations are fixed, training the general parameter tuning model by using the plurality of general parameter combinations to obtain a convergence result of the general parameter tuning model, and taking the convergence result as a final general parameter combination; using the non-general parameter combination and the final general parameter combination to perform application test to obtain a test result; and if determining that the test result is a continuous Nth unimproved test result, determining an optimal MPI parameter according to the non-general parameter combination and the final general parameter combination. By means of the above technical scheme, the embodiment of the invention can improve the tuning efficiency.

The invention discloses a blast furnace TRT top pressure control model based on fuzzy adaptive control and a control method. The blast furnace TRT top pressure control model comprises a blast furnaceTRT. One end of the blast furnace TRT is connected with blast furnace gas generated after dust removal, one path of the other end of the blast furnace TRT is connected with a generator through a pipeline, and the other path of the other end of the blast furnace TRT is connected with a gas pipe network outlet. The error e and the error change ec are adopted as input, e and ec are constantly detected during operation, fuzzy inference is carried out through the fuzzy rule, and a fuzzy matrix table is searched for parameter adjustment to meet the requirements of e and ec for PID parameter self-adjusting at different moments; and PID parameters are modified online through the fuzzy rule, the blast furnace TRT system is subjected to reasonable simplification treatment, main disturbance of the blast furnace top pressure under the normal work condition is introduced into the model, a dynamic model of the blast furnace top pressure under the normal work condition is ensured, and therefore the foundation is laid for subsequent study and analysis of the blast furnace top pressure control algorithm.