Intelligent cooling control method and system for wind generating set

Abstract

The invention provides an intelligent cooling control method and system for a wind generating set. The method comprises the steps that current, voltage and rotating speed signals of a motor stator are collected; copper loss power and iron loss power are calculated according to the motor loss model, and comprehensive heating power is obtained; a heat balance equation is established according to the heating power change rate and the environment temperature, the motor temperature rise trend is predicted, and the cooling power requirement is calculated. According to the method, a motor loss model is introduced in the cooling control process, and the copper loss power and the iron loss power are calculated by using real-time electrical parameters such as stator current, voltage and rotating speed of the motor, so that the comprehensive heating power of the motor is calculated, a heat balance equation is established, and the dynamic prediction of the actual heat load is realized; the main control unit adjusts the operation power of the cooling fan and the liquid cooling pump according to the predicted cooling power, so that the cooling energy consumption and the heating power are kept in a self-balance state, and the problems of overcooling and energy waste in a traditional constant power or threshold starting and stopping mode are effectively avoided.

Description

Technical Field

[0001] This invention relates to the field of wind turbine generator technology, and in particular to an intelligent cooling control method and system for wind turbine generators. Background Technology

[0002] During long-term operation, wind turbine generators generate continuous heat in components such as generators, pitch motors, and gearboxes under high load conditions. To prevent overheating and damage to these components, independent cooling systems, such as air-cooled or liquid-cooled structures, are typically installed to maintain the temperature of various parts of the unit within a safe range.

[0003] However, traditional cooling control systems mostly rely on temperature thresholds for start / stop or constant flow control, lacking prediction of actual heat load and energy efficiency feedback. When the unit load is low or the ambient temperature varies greatly, the cooling system may still operate at high power, resulting in unnecessary energy waste. In addition, most systems rely on a large number of temperature sensors for temperature monitoring, increasing wiring complexity and maintenance costs, and sensor delays cause temperature response lag, affecting cooling accuracy. To address this, a smart cooling control method and system for wind turbine generator sets is proposed. Summary of the Invention

[0004] In view of this, the present invention provides an intelligent cooling control method and system for wind turbine generator sets to solve or alleviate the technical problems existing in the prior art, and at least provides a beneficial option.

[0005] The technical solution of this invention is implemented as follows: A smart cooling control method for wind turbine generator sets, comprising the following steps: S1. Operational parameter acquisition: Real-time acquisition of stator current, voltage and speed signals of wind turbine generator set; S2. Thermal power calculation: Based on the motor loss model, calculate the copper loss power and iron loss power of the motor and obtain the comprehensive heating power; S3. Cooling demand prediction: Based on the rate of change of heat generation power and ambient temperature parameters, establish a heat balance equation, predict the temperature rise trend of the motor cavity, and calculate the cooling power demand. S4. Energy efficiency self-balancing regulation: The main control unit dynamically adjusts the cooling fan speed and liquid cooling pump flow rate according to the predicted cooling power, so that the energy consumption of the cooling system matches the heat generation power of the motor. S5. Feedback Correction: Based on historical operating data, the parameters of the motor loss model are self-learned and corrected to improve prediction accuracy and control stability.

[0006] More preferably, the motor loss model includes a copper loss model and an iron loss model; The copper loss model is used to calculate the conductor heating power based on the stator current and stator resistance of the motor, establish the relationship Pcu=I2Rs, and obtain a smooth power signal through sampling average filtering. The iron loss sub-model is used to calculate the iron core loss power based on the stator voltage and flux change rate of the motor, and to establish the relationship Pfe=khfB2+kef2B2; Where f is the electric frequency, B is the magnetic flux density, and kh and ke are empirical coefficients used to characterize the ratio of hysteresis loss to eddy current loss.

[0007] More preferably, the heat balance equation established in the cooling demand prediction step includes a time decay term and a cooling efficiency coefficient, which is used to simulate the dynamic changes in motor temperature rise inertia and heat dissipation performance with ambient temperature.

[0008] More preferably, the energy efficiency self-balancing adjustment step adopts a combination of proportional-integral-derivative (PID) control algorithm and fuzzy compensation control, and adjusts the PWM duty cycle of the cooling fan and the liquid cooling pump drive signal according to the heat load prediction results.

[0009] In a further preferred embodiment, the feedback correction step includes a self-learning module that uses historical load, cooling response, and temperature deviation data to fit parameters and periodically update the motor loss model and control coefficients.

[0010] The present invention also provides an intelligent cooling control system for wind turbine generator sets, comprising: The data acquisition module is used to acquire stator current, voltage, and speed signals of the wind turbine generator set; The thermal power calculation module is used to calculate the copper loss power and iron loss power of the motor based on the motor loss model and obtain the comprehensive heating power. The cooling prediction module is used to predict cooling demand based on the overall heat generation power change rate and ambient temperature. The energy efficiency control module is used to adjust the cooling fan speed and liquid cooling pump flow rate according to the prediction results, so as to achieve a dynamic balance between cooling energy consumption and heat generation power. The learning correction module is used to correct the motor loss model and control parameters based on historical operating data.

[0011] The built-in motor loss model in the thermal power calculation module includes a copper loss sub-module and an iron loss sub-module; the copper loss sub-module calculates power loss based on the square of the current and the stator resistance; the iron loss sub-module calculates power loss based on the voltage and the rate of change of magnetic flux.

[0012] The energy efficiency control module is connected to the cooling fan and liquid pump through the communication interface between the main control unit and the main control unit. The main control unit outputs PWM control signals and analog drive signals according to the cooling demand prediction results.

[0013] More preferably, the learning correction module adopts a parameter optimization strategy based on a genetic algorithm, and performs iterative correction by comparing the deviation between the predicted temperature rise and the measured temperature.

[0014] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions: I. This invention introduces a motor loss model into the cooling control process, using real-time electrical parameters such as stator current, voltage, and speed of the motor to calculate copper loss power and iron loss power, thereby estimating the comprehensive heat generation power of the motor and establishing a heat balance equation, achieving dynamic prediction of the actual heat load; the main control unit adjusts the operating power of the cooling fan and liquid cooling pump according to the predicted cooling power, so that the cooling energy consumption and heat generation power remain in a self-balanced state, effectively avoiding the problems of overcooling and energy waste that exist in traditional constant power or threshold start-stop methods.

[0015] Second, this invention achieves cooling control by inferring thermal state from electrical signals. It can obtain thermal load information without the need to deploy a large number of temperature sensors inside the motor, reducing the number of detection points and wiring complexity, and lowering installation and maintenance costs. At the same time, since electrical signals such as current and voltage can be acquired in real time and respond to load changes instantaneously, the main control unit can predict cooling demand and perform adjustments in advance before the temperature rises, thereby avoiding slow temperature control and accuracy deviations caused by temperature sensor lag.

[0016] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the steps of the present invention; Figure 2 This is a system module diagram of the present invention. Detailed Implementation

[0019] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0020] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0021] like Figure 1 As shown in the figure, this embodiment of the invention provides an intelligent cooling control method for wind turbine generator sets, including the following steps: S1. Operation Parameter Acquisition During the operation of the wind turbine generator set, the control system acquires the motor's operating status parameters in real time through the data acquisition module. The main signals acquired include the motor stator three-phase current, voltage, and speed, which reflect the electrical characteristics of the motor under different loads.

[0022] The data sampling frequency is usually set at 100 to 200 times per second to ensure dynamic response. Current signals can be obtained through Hall sensors or shunts, voltage signals can be measured through isolation sampling circuits, and speed signals are provided by encoders or tachogenerators. All signals are transmitted to the main control unit after filtering and standardization to ensure signal stability and strong anti-interference capability.

[0023] S2, Thermal Power Calculation After receiving the above signal, the main control unit calculates the total heat generation power of the motor using the built-in motor loss model. The loss model includes two parts: a copper loss model and an iron loss model. The copper loss sub-model is used to characterize the conductor loss of the motor stator winding; the copper loss is mainly proportional to the square of the current and can be calculated from the stator current and stator resistance; the system uses a moving average filtering algorithm to smooth the sampled values ​​and filter out the instantaneous deviation caused by current fluctuations.

[0024] The iron loss sub-model is used to describe the hysteresis loss and eddy current loss inside the iron core. This part is closely related to voltage, magnetic flux change rate and electric frequency of the motor. The main control unit calculates the magnetic flux density based on voltage and speed, and calculates the iron loss power by combining empirical coefficients. The model can be adaptively corrected to adapt to the changes in iron core characteristics under different machine models or temperatures.

[0025] Finally, the main control unit adds up the two power components to obtain the comprehensive heat generation power of the motor under the current operating state. This method can directly infer the heat load from the electrical signal without the need to install a large number of temperature sensors inside the motor, thereby reducing wiring complexity and maintenance workload.

[0026] S3, Cooling Demand Forecast This invention establishes a heat balance equation to predict future thermal trends before the temperature rises and adjusts the cooling output in advance.

[0027] The main control unit combines parameters such as motor heat capacity, ambient temperature, and cooling efficiency to calculate the temperature rise trend over a future period of time. It also introduces a time decay term to simulate the inertial effect of temperature changes. At the same time, a cooling efficiency coefficient is set to reflect the changes in heat dissipation capacity under different ambient temperatures or wind speeds.

[0028] By solving the thermal balance model, the system can obtain the future temperature rise trend curve. When the predicted temperature rise approaches the set upper limit, the main control unit will issue a control command in advance to increase the output of the cooling fan or liquid cooling pump, thereby preventing the motor from overheating.

[0029] S4, Energy Efficiency Self-Balancing Regulation Based on the predicted cooling demand, the main control unit calculates the target power output values ​​of the fan and liquid cooling pump in real time. The control strategy combines proportional-integral-derivative PID control with fuzzy compensation control. PID control is responsible for precisely adjusting the output to keep the system in balance under stable operating conditions; fuzzy control, on the other hand, dynamically adjusts the PID parameters when the load changes abruptly, thereby improving the control response speed.

[0030] When the system detects that the cooling power is too low, the main control unit will automatically increase the PWM duty cycle of the fan or increase the flow rate of the liquid cooling pump; otherwise, it will reduce the power output to avoid overcooling, and the cooling system will always achieve optimal temperature control with minimal energy consumption.

[0031] S5, Feedback Correction and Self-Learning After each operating cycle, the predicted temperature rise curve is compared with the actual measured temperature curve, and the model parameters are optimized using historical data. The self-learning module adopts an optimization strategy based on genetic algorithm or least squares fitting, using the prediction error as the objective function, and continuously adjusts the key variables such as copper loss model parameters, motor heat capacity coefficient and cooling efficiency coefficient.

[0032] When the system detects that the prediction deviation is continuously below a set threshold, the model parameters are confirmed to have converged and are fixed. If the deviation remains large, a retraining process is triggered.

[0033] like Figure 2 As shown, the present invention also provides an intelligent cooling control system for implementing the above method, comprising the following main modules: The data acquisition module is used to acquire the motor's current, voltage, and speed signals. This module achieves real-time data acquisition through high-precision sensors and anti-interference circuits, and transmits the data to the main control unit via a communication bus.

[0034] The thermal power calculation module, with a built-in motor loss model, consists of a copper loss submodule and an iron loss submodule. The copper loss submodule calculates conductor heating using current and stator resistance; the iron loss submodule calculates core loss using voltage and magnetic flux change rate. The output power of the two submodules is fused to obtain the comprehensive thermal power signal of the motor.

[0035] The cooling prediction module is used to predict cooling demand based on the rate of change of heat generation power and ambient temperature. This module can adjust the heat dissipation coefficient according to environmental variables such as air temperature, humidity, and wind speed to maintain prediction accuracy under different climatic conditions.

[0036] The energy efficiency control module includes a main control processor, a PWM drive interface, and an analog signal output interface. After receiving the cooling prediction results, the main control processor sends control commands to the cooling fan and liquid pump to achieve dynamic power adjustment. The control objective is to make the cooling energy consumption approximately equal to the heat generation power.

[0037] The learning and correction module is responsible for storing and analyzing historical operating data. This module uses a parameter optimization strategy based on a genetic algorithm to iteratively correct the parameters of the motor loss model based on the deviation between the predicted temperature rise and the measured temperature, thereby enabling the system to automatically adapt to equipment aging or environmental changes during long-term operation.

[0038] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method of intelligent cooling control for a wind turbine generator system, characterized by, The method comprises the following steps: S1, collecting operating parameters: collecting wind turbine generator motor stator current, voltage and speed signals in real time; S2, calculating thermal power: calculating motor copper loss power and iron loss power according to the motor loss model and obtaining the comprehensive heat generation power; S3, cooling demand prediction: establishing a heat balance equation according to the heat generation power change rate and the environmental temperature parameters, predicting the motor cavity temperature rise trend and calculating the cooling power demand; S4, energy efficiency self-balancing adjustment: the main control unit dynamically adjusts the cooling fan speed and the liquid cooling pump flow according to the predicted cooling power, so that the cooling system energy consumption and the motor heat generation power are matched; S5, feedback correction: based on historical operation data, the motor loss model parameters are self-learned and corrected to improve the prediction accuracy and control stability.

2. A method of intelligent cooling control for a wind turbine generator system as claimed in claim 1, characterized in that: The motor loss model includes a copper loss sub-model and an iron loss sub-model; The copper loss sub-model is used to calculate the conductor heat generation power according to the motor stator current and the stator resistance, establish a relationship Pcu=I2Rs, and obtain a smooth power signal through sampling average filtering; The iron loss sub-model is used to calculate the iron core loss power according to the motor stator voltage and the magnetic flux change rate, and establish a relationship Pfe=khfB2+kef2B2; Where f is the electrical frequency, B is the magnetic flux density, kh and ke are empirical coefficients, used to represent the proportion of hysteresis loss and eddy current loss.

3. The intelligent cooling control method for a wind turbine generator system according to claim 1, characterized in that: The heat balance equation established in the cooling demand prediction step includes a time decay term and a cooling efficiency coefficient, which is used to simulate the motor temperature rise inertia and the dynamic change of the heat dissipation performance with the environmental temperature.

4. The intelligent cooling control method for a wind turbine generator system according to claim 1, characterized in that: The energy efficiency self-balancing adjustment step adopts a proportional-integral-derivative (PID) control algorithm combined with fuzzy compensation control, and adjusts the cooling fan PWM duty cycle and the liquid cooling pump driving signal according to the thermal load prediction results.

5. The method of intelligent cooling control for a wind turbine generator system according to claim 1, wherein: In the feedback correction step, a self-learning module is provided, which uses historical load, cooling response and temperature deviation data for parameter fitting, and periodically updates the motor loss model and control coefficients.

6. An intelligent cooling control system for a wind turbine generator unit according to the method of any one of claims 1-5, characterized in that, It comprises: A data acquisition module for acquiring stator current, voltage and speed signals of a wind turbine generator; A thermal power calculation module for calculating motor copper loss power and iron loss power according to a motor loss model and obtaining comprehensive heat generation power; A cooling prediction module for predicting cooling demand according to the comprehensive heat generation power change rate and the environmental temperature; An energy efficiency control module for adjusting the cooling fan speed and the liquid cooling pump flow according to the prediction results to realize the dynamic balance of cooling energy consumption and heat generation power; A learning correction module for correcting the motor loss model and control parameters based on historical operation data.

7. An intelligent cooling control system for a wind turbine generator system as claimed in claim 6, wherein: The motor loss model built in the thermal power calculation module includes a copper loss sub-module and an iron loss sub-module; The copper loss sub-module calculates the power loss according to the current square and the stator resistance; The iron loss sub-module calculates the power loss according to the voltage and the magnetic flux change rate.

8. An intelligent cooling control system for a wind turbine generator system as claimed in claim 6, wherein: The energy efficiency control module is connected through the communication interface between the main control unit and the cooling fan and the liquid cooling pump. The main control unit outputs PWM control signal and analog driving signal according to the cooling demand prediction results.

9. An intelligent cooling control system for a wind turbine generator according to claim 6, wherein: The learning correction module adopts a parameter optimization strategy based on a genetic algorithm, and iteratively corrects the temperature deviation between the predicted temperature rise and the measured temperature.

Images