Intelligent system for chordwise horizontal distance measurement based on wind power blade mold

Abstract

The invention provides an intelligent system for chordwise horizontal distance measurement based on a wind power blade mold. The intelligent system for chordwise horizontal distance measurement based on the wind power blade mold comprises a sensor module used for measuring the chordwise horizontal distance of the wind power blade mold in real time, a data acquisition and processing unit used for acquiring and processing data of at least one sensor selected from a laser sensor, a photoelectric sensor and an ultrasonic sensor; and the processor is connected with the sensor module. According to the intelligent system for chordwise horizontal distance measurement based on the wind power blade mold, by introducing the design of the fault-tolerant module and the redundant sensor, the problem of production line stagnation caused by a sensor or data transmission fault in a traditional system is effectively solved, the system can automatically switch to the redundant sensor to continue measurement when the main sensor breaks down, and the measurement efficiency is improved. And the sensor data is compensated through a data fusion algorithm, so that the continuity and the stability of the measured data are kept.

Description

Technical Field

[0001] The present invention relates to the technical field of chord-wise horizontal distance measurement for wind turbine blade moulds, and in particular to an intelligent system for chord-wise horizontal distance measurement for wind turbine blade moulds. Background Art

[0002] The intelligent system for measuring the chord-wise horizontal distance of wind turbine blade molds consists of five modules. The sensor module is used to obtain the mold's chord-wise horizontal data in real time, providing high-precision measurement information. Secondly, the data acquisition and processing unit is responsible for converting the analog signals collected by the sensor into digital signals, which are then processed and analyzed by the embedded controller. The display and control interface shows the user the measurement results and allows the operator to adjust the parameters. The communication and alarm system uploads the data to the upper-level monitoring system via wired or wireless means, providing timely feedback on abnormal conditions. The power management module provides stable power support for the entire system. The core principle of the system is to obtain the mold's chord-wise horizontal information through precision sensors, transmit and calculate the data in real time, and provide accurate monitoring and adjustment for the production process.

[0003] Although the system can provide relatively accurate distance measurement and monitoring capabilities, it still has several flaws. During the production of wind turbine blade molds, the system may need to respond to various emergencies. If the system design lacks sufficient fault-tolerant mechanisms, such as redundant sensors or backup communication channels, the entire system may not continue to operate normally once a problem occurs, affecting the continuity and stability of the production line. The current system mainly relies on direct sensor measurement and display of results, lacking more advanced data analysis functions such as trend prediction, anomaly detection, and intelligent diagnosis. This makes the system's adaptive capabilities weak, making it difficult to make predictions or automatic adjustments based on historical data, and requires reliance on human intervention to make decisions. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides an intelligent system for chord-wise horizontal distance measurement of wind turbine blade molds, which solves the problem that the system does not have sufficient fault-tolerant mechanisms, affecting the continuity and stability of the production line; the system mainly relies on sensors to directly measure and display the results, lacks more advanced data analysis functions, and is difficult to predict or automatically adjust based on historical data.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent system for chord-wise horizontal distance measurement of wind turbine blade molds, comprising:

[0006] A sensor module, for measuring the chord-wise horizontal distance of the wind turbine blade mold in real time, wherein the sensor module comprises at least one sensor selected from a laser sensor, a photoelectric sensor, and an ultrasonic sensor;

[0007] a data acquisition and processing unit connected to the sensor module, configured to receive and convert the analog signal from the sensor module into a digital signal, and perform real-time data processing via a microprocessor. The microprocessor includes a real-time signal processing function capable of dynamically adjusting the data acquisition frequency according to changes in sensor data;

[0008] A fault-tolerant module is used to monitor the system's operating status and automatically switch or perform data compensation when a sensor or data transmission failure occurs to ensure system stability. The fault-tolerant module includes at least one redundant sensor. When a primary sensor fails, the redundant sensor takes over the measurement function and compensates the data using a data fusion algorithm.

[0009] The advanced data analysis module is used to perform retrospective analysis, trend prediction, and anomaly detection on historical data, and automatically adjust measurement parameters based on the analysis results to improve the system's adaptability and accuracy. The trend prediction adopts the autoregressive integral moving average model:

[0010] Y t =α+βt+φ1Y t-1 +φ2Y t-2 +…+∈ t

[0011] Among them, Y t is the measured value at time t, α is the constant term, β is the trend term, φ1, φ2,… are the autoregressive parameters, ∈ t is the error term;

[0012] A display and control unit, used to display real-time measurement results and historical data to the user and allow the user to manually adjust system parameters. The display unit is a touch screen or a graphical interface;

[0013] A communication module, used to upload the measurement data to a remote monitoring system in real time, supporting wireless transmission protocols such as Wi-Fi, Bluetooth or wired Ethernet transmission;

[0014] The power management module is used to provide stable power support for various components of the system. The power management module includes a backup battery and power failure monitoring functions.

[0015] Preferably, the data acquisition and processing unit includes a fault detection function. When a sensor fails or the data is abnormal, the system automatically triggers an alarm and switches to a redundant sensor for measurement to ensure uninterrupted operation of the system. The fault detection algorithm is:

[0016] ΔD=|D1-D2|

[0017] Among them, D1 and D2 are the measurement values ​​of the main sensor and redundant sensor respectively. If ΔD>∈, the system determines that the main sensor has failed and activates the redundant sensor.

[0018] Preferably, the advanced data analysis module includes an anomaly detection function, which automatically identifies anomalies in the measurement process by analyzing the differences between the data collected by the sensor and the historical data, and issues an alarm or automatically adjusts parameters. The anomaly detection adopts a detection method based on the Z score:

[0019]

[0020] Where X is the currently collected measurement value, μ and σ are the mean and standard deviation of the historical data, respectively. If |Z|>θ, it is judged to be abnormal.

[0021] Preferably, the fault-tolerant module uses a data fusion algorithm to compensate for redundant sensor data, and the data fusion algorithm is a weighted average algorithm:

[0022] D fused =w1·D1+w2·D2

[0023] Where D1 and D2 are the measurement values ​​of the primary sensor and the redundant sensor respectively, w1 and w2 are weight coefficients, satisfying w1+w2=1, and the weight coefficients are dynamically adjusted according to the reliability of the sensor.

[0024] Preferably, the data acquisition and processing unit includes at least two data channels, which process different types of sensor data in parallel, thereby improving the processing efficiency of the system and reducing the risk of failure of a single data channel. The data parallel processing adopts a weighted average model:

[0025] D final =w1·D1+w2·D2

[0026] Where D1 and D2 are the measurement values ​​of the two data channels respectively, w1 and w2 are weighting coefficients, satisfying w1+w2=1, and the weighting coefficients are dynamically adjusted according to the quality of the sensor data.

[0027] Preferably, the system further includes a function of adaptive adjustment through a machine learning model, wherein the machine learning model uses a support vector machine to fit data, predict future system performance and adjust measurement parameters, and the loss function of the support vector machine model is:

[0028]

[0029] Among them, w is the weight vector, b is the bias term, ξ i is the relaxation variable, C is the regularization parameter, and N is the number of samples.

[0030] Preferably, the support vector machine model is used to extract measurement trends from historical data and predict future measurement values, and the prediction results are used to adjust the sampling frequency and sensitivity of the sensor to improve the measurement accuracy of the system.

[0031] Preferably, the system includes a model-based adaptive control function, which can perform model training based on real-time collected measurement data and historical data, automatically optimize the control algorithm, and improve the adaptive ability of the system.

[0032] Preferably, the adaptive control function uses a particle swarm optimization algorithm to optimize the parameters of the control model:

[0033]

[0034] Among them, x is the optimization parameter, Y i is the actual measured value, Y pred is the predicted value.

[0035] Preferably, the system adopts a multi-level alarm mechanism. When the system detects an anomaly, it first issues a warning signal. If the anomaly cannot be automatically repaired, the alarm mechanism notifies the operator to intervene and provides troubleshooting guidance.

[0036] The present invention provides an intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold. It has the following beneficial effects:

[0037] This intelligent system for measuring chord-wise horizontal distance in wind turbine blade molds effectively addresses the problem of production line stalls caused by sensor or data transmission failures in traditional systems by incorporating fault-tolerant modules and redundant sensor designs. If the primary sensor fails, the system automatically switches to the redundant sensor to continue measurement. A data fusion algorithm compensates for sensor data, maintaining the continuity and stability of the measurement data. This design enhances the system's fault tolerance and ensures smooth production line operation, especially during critical production stages, by avoiding interruptions caused by sensor failures and improving the stability and reliability of the production line.

[0038] This invention significantly enhances the system's intelligence by introducing an advanced data analysis module, combined with an autoregressive integrated moving average model and adaptive control capabilities based on support vector machines and particle swarm optimization algorithms. By reviewing historical data and performing trend prediction and anomaly detection, the system can adjust measurement parameters in real time, optimizing data acquisition frequency and sensitivity, thereby improving measurement accuracy. This not only enables the system to predict future measurements but also automatically adjusts measurement strategies based on varying operating conditions, reducing manual intervention and enhancing the system's adaptability and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the fault-tolerant mechanism and data fusion of the present invention;

[0040] Figure 2 Schematic diagram of abnormality detection and automatic adjustment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0042] Example 1

[0043] like Figure 1-2 As shown, an embodiment of the present invention provides an intelligent system for chord-wise horizontal distance measurement of a wind turbine blade mold, comprising a sensor module for real-time measurement of the chord-wise horizontal distance of the wind turbine blade mold, wherein the sensor module comprises at least one sensor selected from a laser sensor, a photoelectric sensor, and an ultrasonic sensor.

[0044] The data acquisition and processing unit is connected to the sensor module and is used to receive and convert the analog signal of the sensor module into a digital signal. The microprocessor performs real-time data processing. The microprocessor includes a real-time signal processing function and can dynamically adjust the data acquisition frequency according to the changes in sensor data. The data acquisition and processing unit includes a fault detection function. When a sensor fails or the data is abnormal, the system automatically triggers an alarm and switches to a redundant sensor for measurement to ensure uninterrupted operation of the system. The fault detection algorithm is as follows:

[0045] ΔD=|D1-D2|

[0046] Where D1 and D2 are the measurement values ​​of the main sensor and the redundant sensor respectively. If ΔD>∈, the system determines that the main sensor has failed and activates the redundant sensor. The data acquisition and processing unit includes at least two data channels, which process different types of sensor data in parallel, thereby improving the processing efficiency of the system and reducing the risk of single data channel failure. The data parallel processing adopts the weighted average model:

[0047] D final =w1·D1+w2·D2

[0048] Where D1 and D2 are the measurement values ​​of the two data channels, respectively. w1 and w2 are weighting coefficients, satisfying w1 + w2 = 1. The weighting coefficients are dynamically adjusted according to the quality of the sensor data. The system further includes the function of adaptive adjustment through a machine learning model. The machine learning model uses a support vector machine to fit the data, predict future system performance and adjust the measurement parameters. The loss function of the support vector machine model is:

[0049]

[0050] Among them, w is the weight vector, b is the bias term, ξ i is the relaxation variable, C is the regularization parameter, and N is the number of samples. The support vector machine model is used to extract measurement trends from historical data and predict future measurement values. The prediction results are used to adjust the sampling frequency and sensitivity of the sensor to improve the measurement accuracy of the system.

[0051] The fault-tolerant module is used to monitor the system's operating status and automatically switch or perform data compensation when a sensor or data transmission failure occurs to ensure system stability. The fault-tolerant module includes at least one redundant sensor. When the main sensor fails, the redundant sensor takes over the measurement function and compensates the data through a data fusion algorithm. The fault-tolerant module uses a data fusion algorithm to compensate for redundant sensor data. The data fusion algorithm is a weighted average algorithm:

[0052] D fused =w1·D1+w2·D2

[0053] Where D1 and D2 are the measurement values ​​of the primary sensor and the redundant sensor respectively, w1 and w2 are weight coefficients, satisfying w1+w2=1, and the weight coefficients are dynamically adjusted according to the reliability of the sensor.

[0054] The advanced data analysis module is used to perform retrospective analysis, trend prediction, and anomaly detection on historical data. It also automatically adjusts measurement parameters based on the analysis results to improve the system's adaptability and accuracy. Trend prediction uses an autoregressive integral moving average model:

[0055] Y t =α+βt+φ1Y t-1 +φ2Y t-2 +…+∈ t

[0056] Among them, Y t is the measured value at time t, α is the constant term, β is the trend term, φ1, φ2,… are the autoregressive parameters, ∈ tThe advanced data analysis module includes an anomaly detection function. By analyzing the difference between the data collected by the sensor and the historical data, it automatically identifies anomalies in the measurement process and issues alarms or automatically adjusts parameters. Anomaly detection uses a detection method based on the Z score:

[0057]

[0058] Where X is the currently collected measurement value, μ and σ are the mean and standard deviation of the historical data, respectively. If |Z|>θ, it is judged as abnormal. The adaptive control function uses the particle swarm optimization algorithm to optimize the parameters of the control model:

[0059]

[0060] Among them, x is the optimization parameter, Y i is the actual measured value, Y pred is the predicted value.

[0061] The display and control unit is used to display real-time measurement results and historical data to the user and allow the user to manually adjust system parameters. The display unit is a touch screen or a graphical interface.

[0062] The communication module is used to upload the measurement data to the remote monitoring system in real time, and supports wireless transmission protocols such as Wi-Fi, Bluetooth or wired Ethernet transmission.

[0063] The power management module is used to provide stable power support for each component of the system. The power management module includes a backup battery and power failure monitoring function. The system includes a model-based adaptive control function, which can perform model training based on real-time measurement data and historical data, automatically optimize the control algorithm, and improve the system's adaptability. The system adopts a multi-level alarm mechanism. When the system detects an anomaly, it first issues a warning signal. If the anomaly cannot be automatically repaired, the alarm mechanism notifies the operator to intervene and provides troubleshooting guidance.

[0064] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent system for measuring horizontal distance in the chord direction of a wind turbine blade mold, characterized in that: include: A sensor module, for measuring the chord-wise horizontal distance of the wind turbine blade mold in real time, wherein the sensor module comprises at least one sensor selected from a laser sensor, a photoelectric sensor, and an ultrasonic sensor; a data acquisition and processing unit connected to the sensor module, configured to receive and convert the analog signal from the sensor module into a digital signal, and perform real-time data processing via a microprocessor. The microprocessor includes a real-time signal processing function capable of dynamically adjusting the data acquisition frequency according to changes in sensor data; A fault-tolerant module is used to monitor the system's operating status and automatically switch or perform data compensation when a sensor or data transmission failure occurs to ensure system stability. The fault-tolerant module includes at least one redundant sensor. When a primary sensor fails, the redundant sensor takes over the measurement function and compensates the data using a data fusion algorithm. The advanced data analysis module is used to perform retrospective analysis, trend prediction, and anomaly detection on historical data, and automatically adjust measurement parameters based on the analysis results to improve the system's adaptability and accuracy. The trend prediction adopts the autoregressive integral moving average model: Y t =α+βt+φ1Y t-1 +φ2Y t-2 +…+∈ t Among them, Y t is the measured value at time t, α is the constant term, β is the trend term, φ1, φ2,… are the autoregressive parameters, ∈ t is the error term; A display and control unit, used to display real-time measurement results and historical data to the user and allow the user to manually adjust system parameters. The display unit is a touch screen or a graphical interface; A communication module, used to upload the measurement data to a remote monitoring system in real time, supporting wireless transmission protocols such as Wi-Fi, Bluetooth or wired Ethernet transmission; The power management module is used to provide stable power support for various components of the system. The power management module includes a backup battery and power failure monitoring functions.

2. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The data acquisition and processing unit includes a fault detection function. When a sensor fails or the data is abnormal, the system automatically triggers an alarm and switches to a redundant sensor for measurement to ensure uninterrupted operation of the system. The fault detection algorithm is: ΔD=|D1-D2| Among them, D1 and D2 are the measurement values ​​of the main sensor and redundant sensor respectively. If ΔD>∈, the system determines that the main sensor has failed and activates the redundant sensor.

3. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The advanced data analysis module includes an anomaly detection function. By analyzing the difference between the data collected by the sensor and the historical data, it automatically identifies anomalies in the measurement process and issues alarms or automatically adjusts parameters. The anomaly detection method uses a Z-score-based detection method: Where X is the currently collected measurement value, μ and σ are the mean and standard deviation of the historical data, respectively. If |Z|>θ, it is judged to be abnormal.

4. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The fault-tolerant module uses a data fusion algorithm to compensate for redundant sensor data, and the data fusion algorithm is a weighted average algorithm: D fused =w1·D1+w2·D2 Where D1 and D2 are the measurement values ​​of the primary sensor and the redundant sensor respectively, w1 and w2 are weight coefficients, satisfying w1+w2=1, and the weight coefficients are dynamically adjusted according to the reliability of the sensor.

5. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The data acquisition and processing unit includes at least two data channels, which process different types of sensor data in parallel, thereby improving the processing efficiency of the system and reducing the risk of failure of a single data channel. The data parallel processing adopts a weighted average model: D final =w1·D1+w2·D2 Where D1 and D2 are the measurement values ​​of the two data channels respectively, w1 and w2 are weighting coefficients, satisfying w1+w2=1, and the weighting coefficients are dynamically adjusted according to the quality of the sensor data.

6. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The system further includes a function for adaptive adjustment through a machine learning model that uses a support vector machine to fit data, predict future system performance and adjust measurement parameters. The loss function of the support vector machine model is: Among them, w is the weight vector, b is the bias term, ξ i is the relaxation variable, C is the regularization parameter, and N is the number of samples.

7. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 6, characterized in that: The support vector machine model is used to extract measurement trends from historical data and predict future measurement values. The prediction results are used to adjust the sampling frequency and sensitivity of the sensor to improve the measurement accuracy of the system.

8. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The system includes a model-based adaptive control function, which can perform model training based on real-time collected measurement data and historical data, automatically optimize the control algorithm, and improve the system's adaptive ability.

9. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The adaptive control function uses the particle swarm optimization algorithm to optimize the parameters of the control model: Among them, x is the optimization parameter, Y i is the actual measured value, Y pred is the predicted value.

10. The intelligent system for measuring horizontal distance along the chord direction of a wind turbine blade mold according to claim 1, characterized in that: The system adopts a multi-level alarm mechanism. When the system detects an anomaly, it first issues a warning signal. If the anomaly cannot be automatically corrected, the alarm mechanism notifies the operator to intervene and provides troubleshooting guidance.

Images