Intelligent land wind power energy conservation and emission reduction management method and system

Abstract

The invention relates to the technical field of wind power management systems, and discloses an intelligent land wind power energy conservation and emission reduction management method and system. Comprising a data perception and acquisition module, a data transmission layer, a data processing and analysis layer, a power generation efficiency optimization module, an equipment health management module, a power grid coordination and energy storage optimization module, a carbon footprint tracking and reporting module and an application layer. The data sensing and collecting module collects wind speed, wind direction, temperature and air pressure data and generator rotating speed, gearbox temperature, blade angle and vibration frequency data in real time through a high-precision sensor, and low-delay data preprocessing is achieved through an edge calculation unit. In the invention, aiming at the delay problem of traditional yaw and variable pitch control, the system utilizes an intelligent algorithm to realize dynamic yaw and variable pitch control, and by accurately predicting the wind direction change and adjusting the fan direction and the blade angle in advance, the influence caused by complex wind conditions is effectively overcome, and the wind energy capture efficiency is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power management systems, and particularly to an intelligent onshore wind power energy conservation and emission reduction management method and system. Background Art

[0002] Wind power generation is a renewable energy technology that converts wind energy into electrical energy. Its basic principle is that the blades of a wind turbine are rotated by the wind force, converting the wind energy into mechanical energy, and then the mechanical energy is converted into electrical energy by a generator. A wind power generation system usually consists of a wind turbine, a generator, a gearbox, a control system, and grid connection equipment;

[0003] The operation of a wind turbine generator set is realized through the deployment of a wind power management system, which can realize functions such as real-time monitoring of the wind farm status, operation and maintenance of wind turbines, weather and power load prediction, etc., to increase power generation. However, in the actual operation of onshore wind power, traditional yaw and pitch control have delays due to complex factors such as wind direction changes and turbulence, resulting in a reduction in wind energy capture efficiency. In areas with complex wind conditions, the wind turbines cannot adjust the direction and blade angle in a timely manner, causing a large amount of wind energy waste, greatly affecting the power generation efficiency. In addition, the energy consumption of the pitch system, cooling system, etc. of the wind turbine itself accounts for a relatively large proportion, and there is a lack of refined energy consumption management, which not only increases the operating cost but also reduces the energy utilization efficiency, and there is a lack of carbon footprint tracking and optimization for the entire life cycle of the wind turbine operation. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent onshore wind power energy conservation and emission reduction management method and system, which can effectively solve the problems in the background art.

[0005] To achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An intelligent onshore wind power energy conservation and emission reduction management method and system, including a data perception and acquisition module, a data transmission layer, a data processing and analysis layer, a power generation efficiency optimization module, an equipment health management module, a grid coordination and energy storage optimization module, a carbon footprint tracking and reporting module, and an application layer.

[0007] As a further preferred solution of the present invention, the data perception and acquisition module collects wind speed, wind direction, temperature, air pressure data, as well as generator speed, gearbox temperature, blade angle, vibration frequency data in real time through high-precision sensors, and uses an edge computing unit to achieve low-latency data preprocessing.

[0008] As a further preferred embodiment of the present invention, the data transmission layer adopts a hybrid communication technology combining 5G and LoRa. The 5G network is used to quickly transmit data with high real-time requirements such as fan fault signals and emergency control instructions, and LoRa is used to transmit a large amount of conventional operation data to reduce communication costs and energy consumption. At the same time, a data encryption mechanism is established.

[0009] As a further preferred embodiment of the present invention, the data processing and analysis layer further includes a data cleaning, equipment status monitoring, fault prediction module, and energy optimization scheduling module;

[0010] The data cleaning uses principle to clean the received data, remove abnormal data points, and ensure the accuracy of subsequent analysis. If the data point meets

[0011] ,

[0012] then it is determined as an outlier, where is the data mean, is the standard deviation;

[0013] The equipment status monitoring is through establishing a multiple linear regression model:

[0014] ,

[0015] Combining multi-dimensional data to monitor the equipment health status in real time, is the equipment status index, is the monitoring parameter, is the regression coefficient, is the error term;

[0016] The fault prediction module adopts the long short-term memory network LSTM algorithm, and processes time series data through the input gate , forget gate , output gate control mechanism to predict the future fault occurrence probability of the equipment. The specific formula is as follows:

[0017] ,

[0018] Among them, is the sigmoid activation function, is the weight matrix, is the bias vector, is the hidden state, is the memory cell;

[0019] The energy optimization scheduling module is based on the Particle Swarm Optimization (PSO) algorithm. With the objective of maximizing power generation efficiency and minimizing energy consumption, it combines meteorological data, grid load demand data, and equipment availability information to optimize the combined operation of wind turbines as follows:

[0020] Objective function: , , is the energy consumption loss of the th wind turbine, is the power generation of the th wind turbine;

[0021] Update formula: , , where is the velocity, is the position, is the inertia weight, , are the learning factors, , are random numbers, is the individual optimal position, is the global optimal position.

[0022] As a further preferred solution of the present invention, the power generation efficiency optimization module uses an LSTM neural network to predict wind direction changes, dynamically adjusts the yaw angle, reduces energy losses, and optimizes the pitch control strategy based on a reinforcement learning algorithm to balance power generation efficiency and mechanical loads above the rated wind speed, thereby improving power generation efficiency.

[0023] As a further preferred solution of the present invention, the equipment health management module constructs digital twin models of the gearbox and generator, compares the operating data with the health baseline in real time to achieve fault warning, and can optimize the equipment maintenance cycle through predictive maintenance scheduling, reducing maintenance costs and downtime.

[0024] As a further preferred solution of the present invention, the carbon footprint tracking and reporting module has a built-in carbon emission factor library and automatically calculates the carbon emission reduction report for a single unit / full plant.

[0025] As a further preferred solution of the present invention, the application layer integrates functional modules such as real-time equipment monitoring, energy management strategy formulation, and intelligent maintenance plan generation. Managers can fine-tune the optimized wind turbine operation strategy. The system calculates the impact of the adjusted strategy on power generation and energy consumption in real time and displays it in a visual manner to assist in decision-making. At the same time, the optimized strategy works in coordination with each module to ensure that the equipment is always in good operating condition.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. In the present invention, to address the latency issues in traditional yaw and pitch control, the system utilizes intelligent algorithms to achieve dynamic yaw and pitch control. By accurately predicting wind direction changes, the wind turbine direction and blade angles are adjusted in advance, effectively overcoming the impacts brought by complex wind conditions and significantly improving the wind energy capture efficiency.

[0028] 2. In the present invention, through refined energy consumption management, optimized control is carried out on high-energy-consuming devices such as the pitch system and cooling system of the wind turbine itself. According to the real-time operating status of the devices and environmental parameters, the system operation mode is intelligently adjusted to reduce unnecessary energy consumption. With the help of the carbon footprint tracking and reporting module, carbon footprint tracking and optimization throughout the entire life cycle of the wind turbine operation are achieved. Through efficient operation and energy storage optimization, energy waste and curtailment are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is the system architecture diagram of the present invention;

[0030] Figure 2 is the system operation flow chart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0031] To make the technical means, creative features, achieved purposes, and effects of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0032] As Figure 1-2 shown, an intelligent onshore wind power energy conservation and emission reduction management method and system provided by the present invention includes a data perception and acquisition module, a data transmission layer, a data processing and analysis layer, a power generation efficiency optimization module, an equipment health management module, a grid coordination and energy storage optimization module, a carbon footprint tracking and reporting module, and an application layer.

[0033] The data perception and acquisition module uses high-precision sensors to collect wind speed, wind direction, temperature, pressure data, as well as generator speed, gearbox temperature, blade angle, and vibration frequency data in real time, and uses an edge computing unit to achieve low-latency data preprocessing.

[0034] The data transmission layer adopts a hybrid communication technology combining 5G and LoRa. The 5G network is used to quickly transmit data with high real-time requirements such as wind turbine fault signals and emergency control instructions, and LoRa is used to transmit a large amount of regular operation data to reduce communication costs and energy consumption. At the same time, a data encryption mechanism is established.

[0035] The data processing and analysis layer also includes a data cleaning, equipment status monitoring, and fault prediction module, and an energy optimization scheduling module;

[0036] Data cleaning uses Principle, clean the received data, remove abnormal data points, and ensure the accuracy of subsequent analysis. If a data point meets

[0037] ,

[0038] then it is determined as an outlier, where is the data mean, is the standard deviation;

[0039] Equipment status monitoring is carried out by establishing a multiple linear regression model:

[0040] ,

[0041] Combine multi-dimensional data to monitor the equipment health status in real time. is the equipment status index, is the monitoring parameter, is the regression coefficient, is the error term;

[0042] The fault prediction module adopts the long short-term memory network LSTM algorithm, and processes time series data through the input gate , forget gate , output gate control mechanism to predict the future fault occurrence probability of the equipment. The specific formula is as follows:

[0043] ,

[0044] where, is the sigmoid activation function, is the weight matrix, is the bias vector, is the hidden state, is the memory cell;

[0045] The energy optimization scheduling module is based on the particle swarm optimization PSO algorithm, with the objective function of maximizing power generation efficiency and minimizing energy consumption. Combine meteorological data, grid load demand data, and equipment availability information to optimize the combined operation of wind turbines as follows:

[0046] Objective function: , , is the th wind turbine energy consumption loss, is the th wind turbine power generation;

[0047] Update formula: , , where is the velocity, is the position, is the inertia weight, , are the learning factors, , are the random numbers, is the individual optimal position, is the global optimal position.

[0048] The power generation efficiency optimization module uses an LSTM neural network to predict wind direction changes, dynamically adjusts the yaw angle, reduces energy losses, and optimizes the pitch control strategy based on a reinforcement learning algorithm to balance power generation efficiency and mechanical loads above the rated wind speed, improving power generation efficiency.

[0049] The equipment health management module constructs digital twin models of the gearbox and generator, compares operation data with the health baseline in real time, realizes fault early warning, and can optimize the equipment maintenance cycle through predictive maintenance scheduling, reducing maintenance costs and downtime.

[0050] The carbon footprint tracking and reporting module has a built-in carbon emission factor library and automatically calculates the carbon emission reduction amount and report for a single unit / entire plant.

[0051] The application layer integrates functional modules such as real-time equipment monitoring, energy management strategy formulation, and intelligent generation of maintenance plans. Managers can fine-tune the optimized wind turbine operation strategy. The system calculates the impact of the adjusted strategy on power generation and energy consumption in real time and displays it visually to assist in decision-making. At the same time, the optimized strategy works in coordination with each module to ensure that the equipment is always in good operating condition.

[0052] The above has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent onshore wind power energy conservation and emission reduction management method and system, characterized by: It includes data perception and collection module, data transmission layer, data processing and analysis layer, power generation efficiency optimization module, equipment health management module, grid coordination and energy storage optimization module, carbon footprint tracking and reporting module and application layer.

2. According to claim 1, an intelligent onshore wind power energy conservation and emission reduction management method and system is characterized by: The data sensing and acquisition module collects wind speed, wind direction, temperature, air pressure data as well as generator speed, gearbox temperature, blade angle, and vibration frequency data in real time through high-precision sensors, and uses an edge computing unit to achieve low-latency data preprocessing.

3. According to claim 1, an intelligent onshore wind power energy conservation and emission reduction management method and system is characterized by: The data transmission layer adopts a hybrid communication technology that combines 5G and LoRa. The 5G network is used to quickly transmit data with high real-time requirements, such as wind turbine fault signals and emergency control instructions.

4. The intelligent onshore wind power energy conservation and emission reduction management method and system according to claim 3 is characterized by: The data processing and analysis layer also includes data cleaning, equipment status monitoring and fault prediction modules, and energy optimization scheduling modules; The data cleaning application Principle, clean the received data and remove abnormal data points to ensure the accuracy of subsequent analysis. satisfy ， It is considered as an outlier, is the data mean, is the standard deviation; The equipment condition monitoring is carried out by establishing a multivariate linear regression model: ， Combine multi-dimensional data to monitor the health status of equipment in real time. is the device status indicator, To monitor the parameters, is the regression coefficient, is the error term; The fault prediction module adopts the long short-term memory network LSTM algorithm through the input gate , Forget Gate , output gate The control mechanism processes time series data and predicts the probability of future equipment failure. The specific formula is as follows: ， in, is the sigmoid activation function, is the weight matrix, is the bias vector, is the hidden state, For memory unit; The energy optimization scheduling module is based on the particle swarm optimization PSO algorithm, with maximizing power generation efficiency and minimizing energy consumption as the objective function, combined with meteorological data, grid load demand data and equipment availability information, to optimize the wind turbine combination operation, as follows: Objective function: , , For the Typhoon energy loss, For the Typhoon turbine power generation; Update formula: , ,in For speed, For location, is the inertia weight, , is the learning factor, , is a random number, is the optimal position of an individual, is the global optimal position.

5. The intelligent onshore wind power energy conservation and emission reduction management method and system according to claim 1 is characterized by: The power generation efficiency optimization module adopts LSTM neural network to predict wind direction changes, dynamically adjusts the yaw angle, reduces energy loss and optimizes the pitch strategy based on reinforcement learning algorithm.

6. The intelligent onshore wind power energy conservation and emission reduction management method and system according to claim 1 is characterized by: The equipment health management module builds digital twin models of gearboxes and generators, compares operating data with health baselines in real time, and implements fault warnings.

7. The intelligent onshore wind power energy conservation and emission reduction management method and system according to claim 1 is characterized by: The grid coordination and energy storage optimization module accesses grid load forecast data and starts the energy storage system during low-load periods; reduces wind abandonment rate and participates in grid demand response through virtual power plants (VPPs), thereby improving the economic efficiency of wind power consumption.

8. According to the intelligent onshore wind power energy conservation and emission reduction management method and system described in claim 1, the carbon footprint tracking and reporting module has a built-in carbon emission factor library to automatically calculate the carbon emission reduction report of a single unit / the entire site.

9. According to the intelligent onshore wind power energy conservation and emission reduction management method and system as described in claim 1, the application layer integrates functional modules such as real-time monitoring of equipment, formulation of energy management strategies, and intelligent generation of maintenance plans.

Images